初始化项目，由ModelHub XC社区提供模型
Model: TeeZee/GALAXY_v03_slimorca_1_epoch_50k_DPO_1_epoch_30k 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
|
||||
136
README.md
Normal file
136
README.md
Normal file
@@ -0,0 +1,136 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
license: apache-2.0
|
||||
datasets:
|
||||
- Open-Orca/SlimOrca
|
||||
- allenai/ultrafeedback_binarized_cleaned
|
||||
model-index:
|
||||
- name: GALAXY_v03_slimorca_1_epoch_50k_DPO_1_epoch_30k
|
||||
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: 65.27
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/GALAXY_v03_slimorca_1_epoch_50k_DPO_1_epoch_30k
|
||||
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: 85.62
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/GALAXY_v03_slimorca_1_epoch_50k_DPO_1_epoch_30k
|
||||
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: 65.61
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/GALAXY_v03_slimorca_1_epoch_50k_DPO_1_epoch_30k
|
||||
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: 53.46
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/GALAXY_v03_slimorca_1_epoch_50k_DPO_1_epoch_30k
|
||||
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: 82.72
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/GALAXY_v03_slimorca_1_epoch_50k_DPO_1_epoch_30k
|
||||
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: 0.08
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/GALAXY_v03_slimorca_1_epoch_50k_DPO_1_epoch_30k
|
||||
name: Open LLM Leaderboard
|
||||
---
|
||||
### TeeZee/GALAXY-XB-v1.03-SFT-DPO ###
|
||||
|
||||
Experiment, can DUS be taken one or more steps further?
|
||||
|
||||
### Technical notes:
|
||||
- model v03 finetuned on 50k entries from SlimOrca dataset and then DPO on 30k entries from ultrachat
|
||||
- 12 layers removed from both models, 4 more than in original paper but its 1/4 of all layers(48) as per original paper.
|
||||
- base version of upstage/SOLAR-10.7B-v1.0 used for merge
|
||||
|
||||
|
||||
### To evaluate
|
||||
- model performance after DPO, did it recover all initial performance loss after merge?
|
||||
# [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_TeeZee__GALAXY_v03_slimorca_1_epoch_50k_DPO_1_epoch_30k)
|
||||
|
||||
| Metric |Value|
|
||||
|---------------------------------|----:|
|
||||
|Avg. |58.79|
|
||||
|AI2 Reasoning Challenge (25-Shot)|65.27|
|
||||
|HellaSwag (10-Shot) |85.62|
|
||||
|MMLU (5-Shot) |65.61|
|
||||
|TruthfulQA (0-shot) |53.46|
|
||||
|Winogrande (5-shot) |82.72|
|
||||
|GSM8k (5-shot) | 0.08|
|
||||
|
||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"_name_or_path": "TeeZee/GALAXY_v03_slimorca_1_epoch_50k",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 4096,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 72,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 2,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.39.1",
|
||||
"unsloth_version": "2024.3",
|
||||
"use_cache": false,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.39.1",
|
||||
"use_cache": false
|
||||
}
|
||||
3
model-00001-of-00007.safetensors
Normal file
3
model-00001-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:45bc06f58472deac6918e8b01baffc59db0ad1d85ac519e37832c29bc25fd262
|
||||
size 4943162336
|
||||
3
model-00002-of-00007.safetensors
Normal file
3
model-00002-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cb6e4dce9591fc122a0dc9192ec6bb54afdc3cbbc644830a073d55d81918e62b
|
||||
size 4999819336
|
||||
3
model-00003-of-00007.safetensors
Normal file
3
model-00003-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d327c7f92e1ce2afed082166c10ae71d6476bb66068fc22b8bdfae141147dc4d
|
||||
size 4915916184
|
||||
3
model-00004-of-00007.safetensors
Normal file
3
model-00004-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:495cdf12351bbff9514a4d48eedd7b98a50a67052f6620b2888b95d4a44f863b
|
||||
size 4915916176
|
||||
3
model-00005-of-00007.safetensors
Normal file
3
model-00005-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:12063dc100eb3498bd5257a6bfcf5ccd8b65ef9f273b03636cca03879f303f68
|
||||
size 4999819336
|
||||
3
model-00006-of-00007.safetensors
Normal file
3
model-00006-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b8776f3a06a542d19be58b6371c405bcfa0a41e7cd58ac5bca49b60010b22799
|
||||
size 4915916184
|
||||
3
model-00007-of-00007.safetensors
Normal file
3
model-00007-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4e1340f6e78352c9902446226ab6ec427f5d53821a9cce7dd12c4c161457b2e5
|
||||
size 2241950456
|
||||
658
model.safetensors.index.json
Normal file
658
model.safetensors.index.json
Normal file
@@ -0,0 +1,658 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 31932424192
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00007-of-00007.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.48.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.48.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.48.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.48.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.48.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.48.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.48.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.48.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.48.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.49.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.49.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.49.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.49.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.49.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.49.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.49.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.49.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.49.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.50.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.50.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.50.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.50.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.50.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.50.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.50.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.50.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.50.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.51.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.51.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.51.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.51.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.51.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.51.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.51.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.51.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.51.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.52.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.52.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.52.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.52.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.52.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.52.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.52.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.52.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.52.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.53.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.53.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.53.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.53.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.53.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.53.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.53.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.53.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.53.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.54.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.54.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.54.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.54.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.54.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.54.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.54.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.54.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.54.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.55.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.55.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.55.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.55.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.55.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.55.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.55.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.55.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.55.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.56.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.56.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.56.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.56.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.56.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.56.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.56.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.56.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.56.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.57.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.57.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.57.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.57.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.57.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.57.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.57.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.57.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.57.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.58.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.58.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.58.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.58.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.58.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.58.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.58.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.58.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.58.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.59.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.59.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.59.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.59.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.59.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.59.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.59.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.59.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.59.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.60.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.60.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.60.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.60.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.60.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.60.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.60.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.60.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.60.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.61.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.61.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.61.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.61.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.61.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.61.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.61.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.61.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.61.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.62.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.62.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.62.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.62.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.62.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.62.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.62.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.62.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.62.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.63.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.63.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.63.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.63.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.63.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.63.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.63.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.63.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.63.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.64.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.64.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.64.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.64.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.64.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.64.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.64.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.64.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.64.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.65.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.65.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.65.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.65.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.65.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.65.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.65.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.65.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.65.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.66.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.66.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.66.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.66.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.66.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.66.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.66.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.66.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.66.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.67.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.67.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.67.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.67.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.67.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.67.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.67.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.67.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.67.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.68.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.68.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.68.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.68.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.68.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.68.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.68.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.68.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.68.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.69.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.69.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.69.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.69.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.69.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.69.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.69.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.69.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.69.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.70.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.70.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.70.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.70.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.70.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.70.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.70.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.70.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.70.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.71.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.71.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.71.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.71.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.71.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.71.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.71.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.71.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.71.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.norm.weight": "model-00007-of-00007.safetensors"
|
||||
}
|
||||
}
|
||||
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": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
91122
tokenizer.json
Normal file
91122
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
44
tokenizer_config.json
Normal file
44
tokenizer_config.json
Normal file
@@ -0,0 +1,44 @@
|
||||
{
|
||||
"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
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [],
|
||||
"bos_token": "<s>",
|
||||
"chat_template": "\n{{ bos_token }}{% for message in messages %}{% if message['role'] == 'system' %}{% if message['content']%}{{'### System:\n' + message['content']+'\n\n'}}{% endif %}{% elif message['role'] == 'user' %}{{'### User:\n' + message['content']+'\n\n'}}{% elif message['role'] == 'assistant' %}{{'### Assistant:\n' + message['content'] + '</s>' + '\n'}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% endif %}{% endfor %}\n",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": true,
|
||||
"model_max_length": 4096,
|
||||
"pad_token": "<unk>",
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": true
|
||||
}
|
||||
Reference in New Issue
Block a user