初始化项目，由ModelHub XC社区提供模型
Model: SJ-Donald/SJ-SOLAR-10.7b-DPO 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
|
||||
185
README.md
Normal file
185
README.md
Normal file
@@ -0,0 +1,185 @@
|
||||
---
|
||||
license: cc-by-nc-4.0
|
||||
tags:
|
||||
- DPO
|
||||
model-index:
|
||||
- name: SJ-SOLAR-10.7b-DPO
|
||||
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: 68.26
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SJ-Donald/SJ-SOLAR-10.7b-DPO
|
||||
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: 86.95
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SJ-Donald/SJ-SOLAR-10.7b-DPO
|
||||
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: 66.73
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SJ-Donald/SJ-SOLAR-10.7b-DPO
|
||||
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: 67.74
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SJ-Donald/SJ-SOLAR-10.7b-DPO
|
||||
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: 84.21
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SJ-Donald/SJ-SOLAR-10.7b-DPO
|
||||
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: 62.09
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SJ-Donald/SJ-SOLAR-10.7b-DPO
|
||||
name: Open LLM Leaderboard
|
||||
---
|
||||
|
||||
# SJ-Donald/SJ-SOLAR-10.7b-DPO
|
||||
|
||||
SJ-Donald/SJ-SOLAR-10.7b-DPO is fine-tuned using DPO method.
|
||||
|
||||
## Environment
|
||||
|
||||
Using **Google CoLab A100**
|
||||
|
||||
## Base model
|
||||
|
||||
* [SJ-Donald/SOLAR-10.7B-slerp](https://huggingface.co/SJ-Donald/SOLAR-10.7B-slerp)
|
||||
|
||||
## Datasets
|
||||
|
||||
* [SJ-Donald/orca-dpo-pairs-ko](https://huggingface.co/datasets/SJ-Donald/orca-dpo-pairs-ko)
|
||||
|
||||
## Benchmark
|
||||
|
||||
### Open-LLM-Leaderboard(https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
||||
|
||||
| Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
|
||||
| ------: | -----: | -----------: | ------: | -----------: | ---------: | ------: |
|
||||
| 72.67 | 68.26 | 86.95 | 66.73 | 67.74 | 84.21 | 62.03 |
|
||||
|
||||
### open-ko-llm-leaderboard(https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)
|
||||
|
||||
| Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
|
||||
| ------: | -----: | -----------: | ------: | ------------: | --------------: |
|
||||
| 56.93 | 53.67 | 61.99 | 53.36 | 57.2 | 58.44 |
|
||||
|
||||
## How to use
|
||||
|
||||
```Python
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
repo = 'SJ-Donald/SJ-SOLAR-10.7b-DPO'
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(repo)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
repo,
|
||||
return_dict=True,
|
||||
torch_dtype=torch.float16,
|
||||
device_map='auto'
|
||||
)
|
||||
```
|
||||
|
||||
## Chat Template
|
||||
|
||||
```Python
|
||||
template = """### System:
|
||||
{{system_content}}
|
||||
|
||||
### User:
|
||||
{{question}}
|
||||
|
||||
### Assistant:
|
||||
"""
|
||||
```
|
||||
|
||||
## GGUF Version
|
||||
|
||||
You can use gguf model file here! -> [SJ-Donald/SJ-SOLAR-10.7b-DPO-GGUF](https://huggingface.co/SJ-Donald/SJ-SOLAR-10.7b-DPO-GGUF)
|
||||
# [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_SJ-Donald__SJ-SOLAR-10.7b-DPO)
|
||||
|
||||
| Metric |Value|
|
||||
|---------------------------------|----:|
|
||||
|Avg. |72.67|
|
||||
|AI2 Reasoning Challenge (25-Shot)|68.26|
|
||||
|HellaSwag (10-Shot) |86.95|
|
||||
|MMLU (5-Shot) |66.73|
|
||||
|TruthfulQA (0-shot) |67.74|
|
||||
|Winogrande (5-shot) |84.21|
|
||||
|GSM8k (5-shot) |62.09|
|
||||
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"_name_or_path": "SJ-Donald/SOLAR-10.7b-slerp",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"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": 48,
|
||||
"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": "float16",
|
||||
"transformers_version": "4.35.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 48000
|
||||
}
|
||||
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,
|
||||
"pad_token_id": 2,
|
||||
"transformers_version": "4.35.2"
|
||||
}
|
||||
3
model-00001-of-00005.safetensors
Normal file
3
model-00001-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4fb548a329a7fb7515b557bc679644395a5c88f62a25abc35682797b1b83737c
|
||||
size 4956793616
|
||||
3
model-00002-of-00005.safetensors
Normal file
3
model-00002-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d41961e74b0a1a53a96d623f5f927c134f5fbaae04d08853f5b2f642922ba05b
|
||||
size 4915916080
|
||||
3
model-00003-of-00005.safetensors
Normal file
3
model-00003-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:08e009f3a388374298a8b21596b2d6063c8e9271dd5ddff159a8a46a9b4f65df
|
||||
size 4999819232
|
||||
3
model-00004-of-00005.safetensors
Normal file
3
model-00004-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1b46cbe68869b989a1d844e1f82b6a37859ce4224dd9c72f421c8ca6b2a60bf7
|
||||
size 4915916080
|
||||
3
model-00005-of-00005.safetensors
Normal file
3
model-00005-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5ef2f60e158c5cb6bddbf9c877cb03672fe3cfa2c45c97141072f8b586ccbb60
|
||||
size 1936797384
|
||||
442
model.safetensors.index.json
Normal file
442
model.safetensors.index.json
Normal file
@@ -0,0 +1,442 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 21725192192
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00005-of-00005.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.norm.weight": "model-00005-of-00005.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": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
235122
tokenizer.json
Normal file
235122
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
128041
tokenizer_config.json
Normal file
128041
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user