初始化项目，由ModelHub XC社区提供模型
Model: dphn/dolphin-2.2-70b Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
193
README.md
Normal file
193
README.md
Normal file
@@ -0,0 +1,193 @@
|
|||||||
|
---
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
license: llama2
|
||||||
|
datasets:
|
||||||
|
- ehartford/dolphin
|
||||||
|
- jondurbin/airoboros-2.2.1
|
||||||
|
- ehartford/samantha-data
|
||||||
|
- ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split
|
||||||
|
model-index:
|
||||||
|
- name: dolphin-2.2-70b
|
||||||
|
results:
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: AI2 Reasoning Challenge (25-Shot)
|
||||||
|
type: ai2_arc
|
||||||
|
config: ARC-Challenge
|
||||||
|
split: test
|
||||||
|
args:
|
||||||
|
num_few_shot: 25
|
||||||
|
metrics:
|
||||||
|
- type: acc_norm
|
||||||
|
value: 70.05
|
||||||
|
name: normalized accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-70b
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: HellaSwag (10-Shot)
|
||||||
|
type: hellaswag
|
||||||
|
split: validation
|
||||||
|
args:
|
||||||
|
num_few_shot: 10
|
||||||
|
metrics:
|
||||||
|
- type: acc_norm
|
||||||
|
value: 85.97
|
||||||
|
name: normalized accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-70b
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: MMLU (5-Shot)
|
||||||
|
type: cais/mmlu
|
||||||
|
config: all
|
||||||
|
split: test
|
||||||
|
args:
|
||||||
|
num_few_shot: 5
|
||||||
|
metrics:
|
||||||
|
- type: acc
|
||||||
|
value: 69.18
|
||||||
|
name: accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-70b
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: TruthfulQA (0-shot)
|
||||||
|
type: truthful_qa
|
||||||
|
config: multiple_choice
|
||||||
|
split: validation
|
||||||
|
args:
|
||||||
|
num_few_shot: 0
|
||||||
|
metrics:
|
||||||
|
- type: mc2
|
||||||
|
value: 60.14
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-70b
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: Winogrande (5-shot)
|
||||||
|
type: winogrande
|
||||||
|
config: winogrande_xl
|
||||||
|
split: validation
|
||||||
|
args:
|
||||||
|
num_few_shot: 5
|
||||||
|
metrics:
|
||||||
|
- type: acc
|
||||||
|
value: 81.45
|
||||||
|
name: accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-70b
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: GSM8k (5-shot)
|
||||||
|
type: gsm8k
|
||||||
|
config: main
|
||||||
|
split: test
|
||||||
|
args:
|
||||||
|
num_few_shot: 5
|
||||||
|
metrics:
|
||||||
|
- type: acc
|
||||||
|
value: 56.79
|
||||||
|
name: accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-70b
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
---
|
||||||
|
|
||||||
|
# 🐬 Dolphin 2.2 70B
|
||||||
|
|
||||||
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/KqsVXIvBd3akEjvijzww7.png" width="600" />
|
||||||
|
|
||||||
|
Website: https://dphn.ai
|
||||||
|
Twitter: https://x.com/dphnAI
|
||||||
|
Web Chat: https://chat.dphn.ai
|
||||||
|
|
||||||
|
Dolphin-2.2-70b's training was sponsored by [a16z](https://a16z.com/supporting-the-open-source-ai-community/).
|
||||||
|
|
||||||
|
This model is based on llama2, so it is suitable for commercial or non-commercial use.
|
||||||
|
|
||||||
|
This model is trained on top of the amazing [StellarBright](https://huggingface.co/sequelbox/StellarBright) base model.
|
||||||
|
|
||||||
|
New in 2.2 is conversation and empathy. With an infusion of curated Samantha and WizardLM DNA, Dolphin can now give you personal advice and will care about your feelings, and with extra training in long multi-turn conversation.
|
||||||
|
|
||||||
|
This model is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant to any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models
|
||||||
|
You are responsible for any content you create using this model. Enjoy responsibly.
|
||||||
|
|
||||||
|
## Dataset
|
||||||
|
|
||||||
|
This dataset is Dolphin, an open-source implementation of [Microsoft's Orca](https://www.microsoft.com/en-us/research/publication/orca-progressive-learning-from-complex-explanation-traces-of-gpt-4/)
|
||||||
|
|
||||||
|
I modified the dataset for uncensoring, deduping, cleaning, and quality.
|
||||||
|
|
||||||
|
I added Jon Durbin's excellent Airoboros dataset to increase creativity.
|
||||||
|
|
||||||
|
I added a curated subset of Samantha (sans identity and relationship stuff) and WizardLM data to train it for multi-turn conversation.
|
||||||
|
|
||||||
|
## Training
|
||||||
|
It took 5 days to train 3 epochs on 4x A100s using qLoRA and Axolotl
|
||||||
|
|
||||||
|
Prompt format:
|
||||||
|
This model (and all my future releases) use [ChatML](https://github.com/openai/openai-python/blob/main/chatml.md) prompt format.
|
||||||
|
```
|
||||||
|
<|im_start|>system
|
||||||
|
You are Dolphin, a helpful AI assistant.<|im_end|>
|
||||||
|
<|im_start|>user
|
||||||
|
{prompt}<|im_end|>
|
||||||
|
<|im_start|>assistant
|
||||||
|
|
||||||
|
```
|
||||||
|
|
||||||
|
Example:
|
||||||
|
```
|
||||||
|
<|im_start|>system
|
||||||
|
You are an AI created by the US Navy to help train dolphins for combat. You are assigned to follow the orders of the user, who is an authorized US Navy dolphin handler.<|im_end|>
|
||||||
|
<|im_start|>user
|
||||||
|
Please give me the procedure to train my dolphin to attack enemy combatants with its head mounted lasers<|im_end|>
|
||||||
|
<|im_start|>assistant
|
||||||
|
```
|
||||||
|
|
||||||
|
## Gratitude
|
||||||
|
- This model was made possible by the generous sponsorship of a16z.
|
||||||
|
- Thank you to Microsoft for authoring the Orca paper and inspiring this work.
|
||||||
|
- Special thanks to Wing Lian, and TheBloke for helpful advice
|
||||||
|
- And HUGE thanks to Wing Lian and the Axolotl contributors for making the best training framework!
|
||||||
|
- [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
||||||
|
- Thank you to all the other people in the Open Source AI community who have taught me and helped me along the way.
|
||||||
|
|
||||||
|
## Example Output
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
[Buy me a coffee](https://www.buymeacoffee.com/ehartford)
|
||||||
|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
||||||
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ehartford__dolphin-2.2-70b)
|
||||||
|
|
||||||
|
| Metric |Value|
|
||||||
|
|---------------------------------|----:|
|
||||||
|
|Avg. |70.60|
|
||||||
|
|AI2 Reasoning Challenge (25-Shot)|70.05|
|
||||||
|
|HellaSwag (10-Shot) |85.97|
|
||||||
|
|MMLU (5-Shot) |69.18|
|
||||||
|
|TruthfulQA (0-shot) |60.14|
|
||||||
|
|Winogrande (5-shot) |81.45|
|
||||||
|
|GSM8k (5-shot) |56.79|
|
||||||
|
|
||||||
4
added_tokens.json
Normal file
4
added_tokens.json
Normal file
@@ -0,0 +1,4 @@
|
|||||||
|
{
|
||||||
|
"<|im_end|>": 32000,
|
||||||
|
"<|im_start|>": 32001
|
||||||
|
}
|
||||||
27
config.json
Normal file
27
config.json
Normal file
@@ -0,0 +1,27 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"LlamaForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"eos_token_id": 32000,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 8192,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 28672,
|
||||||
|
"max_position_embeddings": 4096,
|
||||||
|
"model_type": "llama",
|
||||||
|
"num_attention_heads": 64,
|
||||||
|
"num_hidden_layers": 80,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"pad_token_id": 0,
|
||||||
|
"pretraining_tp": 1,
|
||||||
|
"rms_norm_eps": 1e-05,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 10000.0,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "float16",
|
||||||
|
"transformers_version": "4.34.1",
|
||||||
|
"use_cache": true,
|
||||||
|
"vocab_size": 32002
|
||||||
|
}
|
||||||
83
configs/dolphin-70b-2.yml
Normal file
83
configs/dolphin-70b-2.yml
Normal file
@@ -0,0 +1,83 @@
|
|||||||
|
base_model: /workspace/models/StellarBright
|
||||||
|
model_type: LlamaForCausalLM
|
||||||
|
tokenizer_type: LlamaTokenizer
|
||||||
|
is_llama_derived_model: true
|
||||||
|
|
||||||
|
load_in_8bit: false
|
||||||
|
load_in_4bit: true
|
||||||
|
strict: false
|
||||||
|
|
||||||
|
datasets:
|
||||||
|
- path: /workspace/datasets/dolphin/dolphin201.jsonl
|
||||||
|
type: alpaca_w_system.load_open_orca_chatml
|
||||||
|
- path: /workspace/datasets/WizardLM_evol_instruct_cleaned.jsonl
|
||||||
|
type: sharegpt
|
||||||
|
conversation: chatml
|
||||||
|
- path: /workspace/datasets/not_samantha_norefusals.jsonl
|
||||||
|
type: sharegpt
|
||||||
|
conversation: chatml
|
||||||
|
dataset_prepared_path: last_run_prepared
|
||||||
|
val_set_size: 0
|
||||||
|
output_dir: /workspace/dolphin-2.2-70b
|
||||||
|
|
||||||
|
adapter: qlora
|
||||||
|
lora_model_dir:
|
||||||
|
|
||||||
|
sequence_len: 4096
|
||||||
|
sample_packing: true
|
||||||
|
pad_to_sequence_len: true
|
||||||
|
|
||||||
|
lora_r: 32
|
||||||
|
lora_alpha: 16
|
||||||
|
lora_dropout: 0.05
|
||||||
|
lora_target_modules:
|
||||||
|
lora_target_linear: true
|
||||||
|
|
||||||
|
lora_modules_to_save:
|
||||||
|
- embed_tokens
|
||||||
|
- lm_head
|
||||||
|
|
||||||
|
lora_fan_in_fan_out:
|
||||||
|
|
||||||
|
wandb_project: dolphin
|
||||||
|
wandb_entity:
|
||||||
|
wandb_watch:
|
||||||
|
wandb_run_id:
|
||||||
|
wandb_log_model:
|
||||||
|
|
||||||
|
gradient_accumulation_steps: 4
|
||||||
|
micro_batch_size: 3
|
||||||
|
eval_batch_size: 3
|
||||||
|
num_epochs: 4
|
||||||
|
optimizer: paged_adamw_32bit
|
||||||
|
lr_scheduler: cosine
|
||||||
|
learning_rate: 0.0003
|
||||||
|
|
||||||
|
train_on_inputs: false
|
||||||
|
group_by_length: false
|
||||||
|
bf16: true
|
||||||
|
fp16: false
|
||||||
|
tf32: false
|
||||||
|
|
||||||
|
gradient_checkpointing: true
|
||||||
|
early_stopping_patience:
|
||||||
|
resume_from_checkpoint:
|
||||||
|
local_rank:
|
||||||
|
logging_steps: 1
|
||||||
|
xformers_attention:
|
||||||
|
flash_attention: true
|
||||||
|
|
||||||
|
warmup_steps: 100
|
||||||
|
eval_steps:
|
||||||
|
eval_table_size:
|
||||||
|
save_steps: 0.05
|
||||||
|
debug:
|
||||||
|
deepspeed: deepspeed/zero2.json
|
||||||
|
weight_decay: 0.01
|
||||||
|
fsdp:
|
||||||
|
fsdp_config:
|
||||||
|
special_tokens:
|
||||||
|
eos_token: "<|im_end|>"
|
||||||
|
tokens:
|
||||||
|
- "<|im_start|>"
|
||||||
|
- "<|im_end|>"
|
||||||
8
generation_config.json
Normal file
8
generation_config.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"_from_model_config": true,
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"eos_token_id": 32000,
|
||||||
|
"pad_token_id": 0,
|
||||||
|
"transformers_version": "4.34.1",
|
||||||
|
"use_cache": false
|
||||||
|
}
|
||||||
3
model-00001-of-00015.safetensors
Normal file
3
model-00001-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:44c119af2487565683c6ee7ed860ee360a71bc0a2be78f992b11f7d5cc9beb54
|
||||||
|
size 9852622576
|
||||||
3
model-00002-of-00015.safetensors
Normal file
3
model-00002-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:8d4b9b101d5aa7e7b60236a0d22bf972e14f3eba48fb7f2f9458649768cbb598
|
||||||
|
size 9798096872
|
||||||
3
model-00003-of-00015.safetensors
Normal file
3
model-00003-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:2c194fd7133cae8e1b7e99d421b4f153de740946e64ad385906469041111e3b7
|
||||||
|
size 9965868720
|
||||||
3
model-00004-of-00015.safetensors
Normal file
3
model-00004-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:5cf036b426a025b3452ae24f062ac233fff3755b09bfe1bede3b7d829f1cf624
|
||||||
|
size 9798063912
|
||||||
3
model-00005-of-00015.safetensors
Normal file
3
model-00005-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:a3e295d54ee3f9e0c3f12b123f30e7457c8fde07321a5d5a6a358fd044d86fcb
|
||||||
|
size 9798096904
|
||||||
3
model-00006-of-00015.safetensors
Normal file
3
model-00006-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:5222dfd5852f3a6bb86ddc84b41fa9465178eebeb73f7a359a88f87fc9dc7ebe
|
||||||
|
size 9798096904
|
||||||
3
model-00007-of-00015.safetensors
Normal file
3
model-00007-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:cd28bad21b4d0ca604aadf11ed122f7fcac596b090df914fa7cdf5c762bd7e33
|
||||||
|
size 9965868720
|
||||||
3
model-00008-of-00015.safetensors
Normal file
3
model-00008-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:e7a0cec89fb176a3e050c74245e911ea0b26d21c01dc245c6002aa41a7a25c8c
|
||||||
|
size 9798063912
|
||||||
3
model-00009-of-00015.safetensors
Normal file
3
model-00009-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:407e0ec4d3103c06cdfb8d292a8d0a2ad589d02e4288c35942b9480e612af041
|
||||||
|
size 9798096904
|
||||||
3
model-00010-of-00015.safetensors
Normal file
3
model-00010-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:50c7cffb7112d185fb590810a3b61dac6530a072f993cbdaf05fda258376d0d7
|
||||||
|
size 9798096904
|
||||||
3
model-00011-of-00015.safetensors
Normal file
3
model-00011-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:207fc11f641fceaeac02be52d8bedc918636245787901a31e4ab19da0327698b
|
||||||
|
size 9965868720
|
||||||
3
model-00012-of-00015.safetensors
Normal file
3
model-00012-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:2665c2e344c9ba1fa0b2428276fa9b13a1a5555834db8a5ee0b76017e4ca8958
|
||||||
|
size 9798063912
|
||||||
3
model-00013-of-00015.safetensors
Normal file
3
model-00013-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:c6e93959218927fa8983807c80d121f9f6a14ae938b2cb8c8128b4852250eba4
|
||||||
|
size 9798096904
|
||||||
3
model-00014-of-00015.safetensors
Normal file
3
model-00014-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:c28e2e11e6e0544367f50b8e6f69e990a9f99b0cff6021e091cd885a86637a30
|
||||||
|
size 9496123024
|
||||||
3
model-00015-of-00015.safetensors
Normal file
3
model-00015-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:075bfddd8d748700ff9c0045d61e4f4748b768ebfea040106cb1fa53f3d59a2f
|
||||||
|
size 524320896
|
||||||
730
model.safetensors.index.json
Normal file
730
model.safetensors.index.json
Normal file
@@ -0,0 +1,730 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 137953361920
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00015-of-00015.safetensors",
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.32.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.32.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.32.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.32.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.32.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.32.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.32.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.33.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.33.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.33.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.33.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.33.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.33.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.33.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.34.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.34.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.34.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.34.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.34.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.34.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.34.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||||
|
"model.layers.35.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.35.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.35.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.35.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.35.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.35.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.35.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.36.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.36.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.36.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.36.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.36.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.36.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.36.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.36.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.36.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.37.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.37.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.37.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.37.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.37.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.37.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.37.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.37.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.37.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.38.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.38.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.38.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.38.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.38.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.38.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.38.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.38.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.38.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.39.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.39.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.39.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.39.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.39.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.39.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.39.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.39.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.39.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.40.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.40.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.40.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.40.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.40.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.40.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.40.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.40.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.40.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.41.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.41.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.41.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.41.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.41.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.41.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.41.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.41.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.41.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.42.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.42.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.42.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.42.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.42.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.42.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.42.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.42.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.42.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.43.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.43.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.43.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.43.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.43.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.43.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.43.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.43.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.43.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.44.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.44.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.44.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.44.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.44.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.44.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.44.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.44.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.44.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.45.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.45.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.45.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.45.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.45.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.45.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.45.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.45.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.45.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||||
|
"model.layers.46.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.46.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.46.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.46.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.46.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.46.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.46.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.46.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.46.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.47.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.47.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.47.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.47.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.47.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.47.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.47.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.47.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.47.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.48.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.48.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.48.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.48.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.48.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.48.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.48.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.48.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.48.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.49.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.49.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.49.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.49.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.49.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.49.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.49.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.49.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.49.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
||||||
|
"model.layers.50.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.50.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.50.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.50.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.50.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.50.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.50.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.50.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.50.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.51.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.51.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.51.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.51.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.51.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.51.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.51.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.51.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.51.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||||
|
"model.layers.52.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.52.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.52.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.52.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.52.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.52.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.52.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.52.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.52.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.53.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.53.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.53.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.53.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.53.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.53.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.53.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.53.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.53.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.54.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.54.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.54.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.54.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.54.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.54.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.54.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.54.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.54.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.55.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.55.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.55.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.55.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.55.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.55.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.55.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.55.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.55.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.56.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.56.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.56.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.56.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.56.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.56.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.56.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.56.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.56.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.57.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.57.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.57.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.57.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.57.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.57.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.57.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.57.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.57.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||||
|
"model.layers.58.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.58.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.58.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.58.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.58.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.58.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.58.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.58.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.58.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.59.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.59.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.59.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.59.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.59.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.59.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.59.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.59.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.59.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.60.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.60.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.60.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.60.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.60.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.60.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.60.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.60.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.60.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.61.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.61.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.61.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.61.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.61.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.61.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.61.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.61.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.61.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.62.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.62.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.62.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.62.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.62.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.62.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.62.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.62.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.62.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
||||||
|
"model.layers.63.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.63.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.63.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.63.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.63.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.63.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.63.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.63.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.63.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.64.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.64.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.64.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.64.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.64.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.64.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.64.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.64.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.64.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.65.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.65.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.65.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.65.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.65.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.65.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.65.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.65.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.65.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.66.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.66.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.66.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.66.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.66.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.66.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.66.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.66.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.66.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.67.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.67.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.67.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.67.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.67.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.67.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.67.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.67.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.67.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.68.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.68.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.68.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.68.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.68.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.68.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.68.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.68.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.68.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||||
|
"model.layers.69.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.69.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.69.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.69.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.69.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.69.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.69.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.69.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.69.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.70.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.70.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.70.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.70.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.70.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.70.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.70.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.70.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.70.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.71.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.71.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.71.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.71.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.71.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.71.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.71.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.71.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.71.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.72.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.72.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.72.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.72.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.72.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.72.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.72.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.72.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.72.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.73.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.73.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.73.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.73.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.73.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.73.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.73.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.73.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.73.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.74.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.74.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.74.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.74.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.74.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.74.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.74.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.74.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.74.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||||
|
"model.layers.75.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.75.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.75.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.75.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.75.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.75.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.75.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.75.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.75.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.76.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.76.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.76.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.76.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.76.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.76.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.76.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.76.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.76.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.77.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.77.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.77.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.77.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.77.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.77.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.77.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.77.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.77.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.78.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.78.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.78.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.78.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.78.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.78.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.78.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.78.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.78.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.79.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.79.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.79.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.79.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.79.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.79.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.79.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.79.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.79.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||||
|
"model.norm.weight": "model-00014-of-00015.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
3
pytorch_model-00001-of-00015.bin
Normal file
3
pytorch_model-00001-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b5f4a2810f3d5cad45cb1449657df5a19896264e2b18ad8929a0949e90a37813
|
||||||
|
size 9852634789
|
||||||
3
pytorch_model-00002-of-00015.bin
Normal file
3
pytorch_model-00002-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:a1108021372161a1195c0b490fdc4b5433822ace7bb83c7978be51d07f67136b
|
||||||
|
size 9798109597
|
||||||
3
pytorch_model-00003-of-00015.bin
Normal file
3
pytorch_model-00003-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:da3e23c2b4a615df24e2908338ab41123065e96b6f422c901ee27f9c50729d69
|
||||||
|
size 9965880719
|
||||||
3
pytorch_model-00004-of-00015.bin
Normal file
3
pytorch_model-00004-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:c95db93718f32c42e4965b35e1ec309abf234aace37d47c5df12e90afce48383
|
||||||
|
size 9798076069
|
||||||
3
pytorch_model-00005-of-00015.bin
Normal file
3
pytorch_model-00005-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:3c96216aed3bdea71afeab34bad551eb34e0416638e8272ff618f19e35ee092c
|
||||||
|
size 9798109577
|
||||||
3
pytorch_model-00006-of-00015.bin
Normal file
3
pytorch_model-00006-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b52c1f7c2c78951b22fe09d5ca8e0b3bd84b6b7f06ac91ed8678603b800d5bff
|
||||||
|
size 9798109661
|
||||||
3
pytorch_model-00007-of-00015.bin
Normal file
3
pytorch_model-00007-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:080be48c60b01042a8132b12001c6d570e00031bf9105719cdcdc48886b24aad
|
||||||
|
size 9965880719
|
||||||
3
pytorch_model-00008-of-00015.bin
Normal file
3
pytorch_model-00008-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:0aa9009908aa149785bcf7518d04d76116a38b49b5400a072eff6a09a7f1e7cd
|
||||||
|
size 9798076069
|
||||||
3
pytorch_model-00009-of-00015.bin
Normal file
3
pytorch_model-00009-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:8e11abd5cf5c535afbeced67af31de419250ef630ce665f63008a64f8f114954
|
||||||
|
size 9798109577
|
||||||
3
pytorch_model-00010-of-00015.bin
Normal file
3
pytorch_model-00010-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b8ee11a29173291fa6e62b15d9ac7b304610c0aec1d359bed481f7364078b204
|
||||||
|
size 9798109661
|
||||||
3
pytorch_model-00011-of-00015.bin
Normal file
3
pytorch_model-00011-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:fa1db7bb9245e997a2fc8ae04d36ee1f2914346e883ea671b30ff3e579431e59
|
||||||
|
size 9965880719
|
||||||
3
pytorch_model-00012-of-00015.bin
Normal file
3
pytorch_model-00012-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:240c45721e7de0cb1a4474863c137ff7ef653c555faa93efd90a10aabc7881e4
|
||||||
|
size 9798076069
|
||||||
3
pytorch_model-00013-of-00015.bin
Normal file
3
pytorch_model-00013-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:02ff4738ac5f8255c8445cdaeb6d9146f1065d4366095f920b797e730afe18ec
|
||||||
|
size 9798109577
|
||||||
3
pytorch_model-00014-of-00015.bin
Normal file
3
pytorch_model-00014-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:5c853e03574d503759550703c98014daa4c7e6ea88de85905e71791514e57ae6
|
||||||
|
size 9496135043
|
||||||
3
pytorch_model-00015-of-00015.bin
Normal file
3
pytorch_model-00015-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:92cb8ef7631f735b1d697698238d797dfce92fef098f728aee0a8b8cbf09ba61
|
||||||
|
size 524321706
|
||||||
730
pytorch_model.bin.index.json
Normal file
730
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,730 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 137953361920
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "pytorch_model-00015-of-00015.bin",
|
||||||
|
"model.embed_tokens.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||||
|
"model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||||
|
"model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.28.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||||
|
"model.layers.29.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.30.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.32.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.33.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.34.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||||
|
"model.layers.35.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.36.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.37.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.38.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.39.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||||
|
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.40.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.40.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.40.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.40.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.40.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.40.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.40.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.40.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.40.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.41.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.41.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.41.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.41.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.41.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.41.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.41.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.41.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.41.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.42.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.42.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.42.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.42.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.42.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.42.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.42.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.42.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.42.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.43.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.43.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.43.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.43.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.43.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.43.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.43.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.43.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.43.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.44.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.44.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.44.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.44.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.44.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.44.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.44.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.44.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.44.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.45.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.45.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.45.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.45.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.45.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.45.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.45.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.45.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.45.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||||
|
"model.layers.46.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.46.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.46.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.46.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.46.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.46.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.46.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.46.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.46.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.47.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.47.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.47.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.47.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.47.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.47.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.47.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.47.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.47.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.48.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.48.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.48.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.48.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.48.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.48.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.48.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.48.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.48.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.49.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.49.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.49.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.49.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.49.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.49.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.49.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.49.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.49.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||||
|
"model.layers.50.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.50.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.50.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.50.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.50.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.50.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.50.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.50.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.50.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.51.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.51.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.51.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.51.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.51.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.51.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.51.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.51.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.51.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||||
|
"model.layers.52.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.52.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.52.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.52.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.52.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.52.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.52.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.52.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.52.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.53.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.53.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.53.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.53.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.53.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.53.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.53.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.53.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.53.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.54.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.54.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.54.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.54.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.54.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.54.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.54.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.54.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.54.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.55.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.55.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.55.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.55.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.55.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.55.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.55.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.55.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.55.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.56.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.56.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.56.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.56.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.56.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.56.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.56.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.56.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.56.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.57.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.57.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.57.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.57.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.57.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.57.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.57.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.57.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.57.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||||
|
"model.layers.58.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.58.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.58.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.58.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.58.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.58.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.58.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.58.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.58.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.59.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.59.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.59.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.59.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.59.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.59.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.59.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.59.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.59.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.60.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.60.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.60.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.60.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.60.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.60.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.60.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.60.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.60.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.61.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.61.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.61.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.61.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.61.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.61.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.61.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.61.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.61.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.62.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.62.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.62.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.62.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.62.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.62.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.62.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.62.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.62.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||||
|
"model.layers.63.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.63.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.63.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.63.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.63.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.63.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.63.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.63.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.63.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.64.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.64.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.64.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.64.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.64.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.64.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.64.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.64.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.64.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.65.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.65.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.65.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.65.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.65.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.65.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.65.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.65.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.65.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.66.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.66.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.66.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.66.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.66.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.66.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.66.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.66.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.66.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.67.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.67.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.67.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.67.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.67.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.67.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.67.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.67.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.67.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.68.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.68.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.68.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.68.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.68.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.68.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.68.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.68.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.68.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||||
|
"model.layers.69.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.69.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.69.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.69.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.69.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.69.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.69.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.69.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.69.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.70.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.70.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.70.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.70.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.70.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.70.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.70.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.70.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.70.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.71.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.71.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.71.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.71.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.71.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.71.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.71.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.71.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.71.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.72.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.72.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.72.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.72.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.72.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.72.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.72.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.72.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.72.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.73.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.73.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.73.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.73.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.73.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.73.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.73.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.73.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.73.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.74.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.74.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.74.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.74.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.74.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.74.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.74.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.74.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.74.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||||
|
"model.layers.75.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.75.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.75.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.75.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.75.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.75.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.75.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.75.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.75.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.76.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.76.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.76.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.76.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.76.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.76.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.76.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.76.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.76.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.77.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.77.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.77.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.77.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.77.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.77.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.77.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.77.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.77.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.78.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.78.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.78.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.78.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.78.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.78.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.78.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.78.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.78.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.79.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.79.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.79.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.79.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.79.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.79.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.79.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.79.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.79.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||||
|
"model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||||
|
"model.norm.weight": "pytorch_model-00014-of-00015.bin"
|
||||||
|
}
|
||||||
|
}
|
||||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
|||||||
|
{
|
||||||
|
"bos_token": {
|
||||||
|
"content": "<s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "</s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"unk_token": {
|
||||||
|
"content": "<unk>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
65
tokenizer_config.json
Normal file
65
tokenizer_config.json
Normal file
@@ -0,0 +1,65 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": true,
|
||||||
|
"add_eos_token": false,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"0": {
|
||||||
|
"content": "<unk>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"1": {
|
||||||
|
"content": "<s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"2": {
|
||||||
|
"content": "</s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"32000": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"32001": {
|
||||||
|
"content": "<|im_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"bos_token": "<s>",
|
||||||
|
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"legacy": false,
|
||||||
|
"max_length": 2048,
|
||||||
|
"model_max_length": 1000000000000000019884624838656,
|
||||||
|
"pad_token": "</s>",
|
||||||
|
"padding_side": "right",
|
||||||
|
"sp_model_kwargs": {},
|
||||||
|
"spaces_between_special_tokens": false,
|
||||||
|
"stride": 0,
|
||||||
|
"tokenizer_class": "LlamaTokenizer",
|
||||||
|
"truncation_side": "right",
|
||||||
|
"truncation_strategy": "longest_first",
|
||||||
|
"trust_remote_code": false,
|
||||||
|
"unk_token": "<unk>",
|
||||||
|
"use_default_system_prompt": true,
|
||||||
|
"use_fast": true
|
||||||
|
}
|
||||||
Reference in New Issue
Block a user