初始化项目，由ModelHub XC社区提供模型
Model: hiyouga/Qwen-14B-Chat-LLaMAfied 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
|
||||
166
README.md
Normal file
166
README.md
Normal file
@@ -0,0 +1,166 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
- zh
|
||||
license: other
|
||||
library_name: transformers
|
||||
tags:
|
||||
- llama
|
||||
- qwen
|
||||
license_name: qwen
|
||||
license_link: https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT
|
||||
pipeline_tag: text-generation
|
||||
inference: false
|
||||
model-index:
|
||||
- name: Qwen-14B-Chat-LLaMAfied
|
||||
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: 57.51
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hiyouga/Qwen-14B-Chat-LLaMAfied
|
||||
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: 82.11
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hiyouga/Qwen-14B-Chat-LLaMAfied
|
||||
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: 65.57
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hiyouga/Qwen-14B-Chat-LLaMAfied
|
||||
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: 51.99
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hiyouga/Qwen-14B-Chat-LLaMAfied
|
||||
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: 72.93
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hiyouga/Qwen-14B-Chat-LLaMAfied
|
||||
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: 39.5
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hiyouga/Qwen-14B-Chat-LLaMAfied
|
||||
name: Open LLM Leaderboard
|
||||
---
|
||||
|
||||
This is the LLaMAfied version of [Qwen-14B-Chat](https://huggingface.co/Qwen/Qwen-14B-Chat) model by Alibaba Cloud.
|
||||
|
||||
This model is converted with https://github.com/hiyouga/LLaMA-Factory/blob/main/tests/llamafy_qwen.py
|
||||
|
||||
The tokenizer is borrowed from https://huggingface.co/CausalLM/72B-preview-llamafied-qwen-llamafy
|
||||
|
||||
You may use this model for fine-tuning in downstream tasks, we recommend using our efficient fine-tuning toolkit. https://github.com/hiyouga/LLaMA-Factory
|
||||
|
||||
- **Developed by:** Alibaba Cloud.
|
||||
- **Language(s) (NLP):** Chinese/English
|
||||
- **License:** [Tongyi Qianwen License](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT)
|
||||
|
||||
Usage:
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained("hiyouga/Qwen-14B-Chat-LLaMAfied")
|
||||
model = AutoModelForCausalLM.from_pretrained("hiyouga/Qwen-14B-Chat-LLaMAfied", torch_dtype="auto", device_map="auto")
|
||||
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
|
||||
|
||||
messages = [
|
||||
{"role": "user", "content": "Who are you?"}
|
||||
]
|
||||
inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
|
||||
inputs = inputs.to("cuda")
|
||||
generate_ids = model.generate(inputs, streamer=streamer)
|
||||
```
|
||||
|
||||
You could also alternatively launch a CLI demo by using the script in [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory)
|
||||
|
||||
```bash
|
||||
python src/cli_demo.py --template qwen --model_name_or_path hiyouga/Qwen-14B-Chat-LLaMAfied
|
||||
```
|
||||
|
||||
# [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_hiyouga__Qwen-14B-Chat-LLaMAfied)
|
||||
|
||||
| Metric |Value|
|
||||
|---------------------------------|----:|
|
||||
|Avg. |61.60|
|
||||
|AI2 Reasoning Challenge (25-Shot)|57.51|
|
||||
|HellaSwag (10-Shot) |82.11|
|
||||
|MMLU (5-Shot) |65.57|
|
||||
|TruthfulQA (0-shot) |51.99|
|
||||
|Winogrande (5-shot) |72.93|
|
||||
|GSM8k (5-shot) |39.50|
|
||||
|
||||
24
config.json
Normal file
24
config.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 13696,
|
||||
"max_position_embeddings": 8192,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 40,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 40,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 10000.0,
|
||||
"rope_scaling": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.34.0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 152064,
|
||||
"attention_bias": true
|
||||
}
|
||||
9
generation_config.json
Normal file
9
generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"eos_token_id": [151643, 151645],
|
||||
"pad_token_id": 151643,
|
||||
"max_new_tokens": 1024,
|
||||
"do_sample": true,
|
||||
"top_k": 0,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "4.34.0"
|
||||
}
|
||||
109172
merges.txt
Normal file
109172
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00013.safetensors
Normal file
3
model-00001-of-00013.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:96e462a8b583712dfd5b2fde912e4843cafaaee6b3185e40763ac60138b457c2
|
||||
size 2381819504
|
||||
3
model-00002-of-00013.safetensors
Normal file
3
model-00002-of-00013.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:595f8eebd91b4632cf6fb7df1680d7f7c8bf4af3ece5ef8aa95c442fe48c2dcf
|
||||
size 2381829824
|
||||
3
model-00003-of-00013.safetensors
Normal file
3
model-00003-of-00013.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8a28e5201614dba0521f6523288313febeed5a45fe99096864e59a3793385063
|
||||
size 2381829872
|
||||
3
model-00004-of-00013.safetensors
Normal file
3
model-00004-of-00013.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f921b19d443b4b414c18098c0b8ae5d0eaec06227ae0690f9c5b5596aa828714
|
||||
size 2312340632
|
||||
3
model-00005-of-00013.safetensors
Normal file
3
model-00005-of-00013.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0dc1fe5e94eee95d0bfb778322ee5e41d835900f993b88a07828ea3a6f4e8511
|
||||
size 2381798792
|
||||
3
model-00006-of-00013.safetensors
Normal file
3
model-00006-of-00013.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1513be0b082c1bfabef66d6263e2601193aded9f279bf493c7f211596a17a7aa
|
||||
size 2047397248
|
||||
3
model-00007-of-00013.safetensors
Normal file
3
model-00007-of-00013.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:08c2919d45da18a553f942ebc615a1e424a51ec2214dfe375574a8f5fafcdace
|
||||
size 2381829872
|
||||
3
model-00008-of-00013.safetensors
Normal file
3
model-00008-of-00013.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2987c3bba78c6d1feda0ea590b34423fa337f50084377f44f560b6e8b336e219
|
||||
size 2381840176
|
||||
3
model-00009-of-00013.safetensors
Normal file
3
model-00009-of-00013.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3feb5961f4d879b30ada2ff29bf62daf0cbad41d67a2a3c15f14d54c57070715
|
||||
size 2312330288
|
||||
3
model-00010-of-00013.safetensors
Normal file
3
model-00010-of-00013.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8e849097a5c2337db4c32b3d16fc971753a650767ab2a3201bf529c728f04ebd
|
||||
size 1891526720
|
||||
3
model-00011-of-00013.safetensors
Normal file
3
model-00011-of-00013.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:491100d982b4c4b8e96f5b5208c31392e6af6e1f0dd1c4c326a89cdc5ce6d658
|
||||
size 2047407576
|
||||
3
model-00012-of-00013.safetensors
Normal file
3
model-00012-of-00013.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5c86af1395d933d96d2862e3a100486f0d86c092ee13f59153f9813c7666d198
|
||||
size 2381829840
|
||||
3
model-00013-of-00013.safetensors
Normal file
3
model-00013-of-00013.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0da1070a57a97b3fbdc0f92e2f0e58b6d0a0b704b0e8577bcad908ecc2f8af41
|
||||
size 1051271056
|
||||
530
model.safetensors.index.json
Normal file
530
model.safetensors.index.json
Normal file
@@ -0,0 +1,530 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 24139868160
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00011-of-00013.safetensors",
|
||||
"model.embed_tokens.weight": "model-00006-of-00013.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.bias": "model-00005-of-00013.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00011-of-00013.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.bias": "model-00011-of-00013.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.bias": "model-00001-of-00013.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.bias": "model-00001-of-00013.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.bias": "model-00001-of-00013.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.bias": "model-00006-of-00013.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.bias": "model-00007-of-00013.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.bias": "model-00007-of-00013.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.bias": "model-00003-of-00013.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.bias": "model-00003-of-00013.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.bias": "model-00003-of-00013.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.bias": "model-00009-of-00013.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.bias": "model-00012-of-00013.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.bias": "model-00009-of-00013.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.bias": "model-00009-of-00013.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.bias": "model-00007-of-00013.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.bias": "model-00007-of-00013.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.bias": "model-00008-of-00013.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.bias": "model-00002-of-00013.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.bias": "model-00002-of-00013.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.bias": "model-00003-of-00013.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00013.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.bias": "model-00005-of-00013.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.bias": "model-00005-of-00013.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.bias": "model-00012-of-00013.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.bias": "model-00005-of-00013.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00005-of-00013.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.bias": "model-00010-of-00013.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.bias": "model-00010-of-00013.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.bias": "model-00010-of-00013.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00010-of-00013.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.bias": "model-00004-of-00013.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.bias": "model-00004-of-00013.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.bias": "model-00004-of-00013.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00004-of-00013.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.bias": "model-00012-of-00013.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.bias": "model-00012-of-00013.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00013-of-00013.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00013-of-00013.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00012-of-00013.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.bias": "model-00001-of-00013.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.bias": "model-00002-of-00013.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.bias": "model-00002-of-00013.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00013.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.bias": "model-00008-of-00013.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.bias": "model-00008-of-00013.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.bias": "model-00008-of-00013.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.norm.weight": "model-00013-of-00013.safetensors"
|
||||
}
|
||||
}
|
||||
9
special_tokens_map.json
Normal file
9
special_tokens_map.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>"
|
||||
],
|
||||
"bos_token": "<|endoftext|>",
|
||||
"eos_token": "<|endoftext|>",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
11
tokenizer_config.json
Normal file
11
tokenizer_config.json
Normal file
@@ -0,0 +1,11 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"add_bos_token": false,
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "<|endoftext|>",
|
||||
"bos_token": "<|endoftext|>",
|
||||
"eos_token": "<|endoftext|>",
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful assistant.' %}{% endif %}{{ '<|im_start|>' + 'system' + '\\n' + system_message + '<|im_end|>' + '\\n' }}{% for message in loop_messages %}{{ '<|im_start|>' + message['role'] + '\\n' + message['content']}}{% if (loop.last and add_generation_prompt) or not loop.last %}{{ '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{ '<|im_start|>' + 'assistant' + '\\n' }}{% endif %}"
|
||||
}
|
||||
151853
vocab.json
Normal file
151853
vocab.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user