初始化项目，由ModelHub XC社区提供模型
Model: CallComply/SOLAR-10.7B-Instruct-v1.0-128k 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
|
||||
295
README.md
Normal file
295
README.md
Normal file
@@ -0,0 +1,295 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
license: cc-by-nc-4.0
|
||||
datasets:
|
||||
- c-s-ale/alpaca-gpt4-data
|
||||
- Open-Orca/OpenOrca
|
||||
- Intel/orca_dpo_pairs
|
||||
- allenai/ultrafeedback_binarized_cleaned
|
||||
base_model:
|
||||
- upstage/SOLAR-10.7B-v1.0
|
||||
model-index:
|
||||
- name: SOLAR-10.7B-Instruct-v1.0-128k
|
||||
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: 65.96
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CallComply/SOLAR-10.7B-Instruct-v1.0-128k
|
||||
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: 84.35
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CallComply/SOLAR-10.7B-Instruct-v1.0-128k
|
||||
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: 57.63
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CallComply/SOLAR-10.7B-Instruct-v1.0-128k
|
||||
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: 65.42
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CallComply/SOLAR-10.7B-Instruct-v1.0-128k
|
||||
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: 80.51
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CallComply/SOLAR-10.7B-Instruct-v1.0-128k
|
||||
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: 7.13
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CallComply/SOLAR-10.7B-Instruct-v1.0-128k
|
||||
name: Open LLM Leaderboard
|
||||
---
|
||||
|
||||
# **Meet 10.7B Solar: Elevating Performance with Upstage Depth UP Scaling!**
|
||||
|
||||
# **With 128k Context!**
|
||||
|
||||
**(This model is [upstage/SOLAR-10.7B-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-v1.0) fine-tuned version for single-turn conversation.)**
|
||||
|
||||
|
||||
# **Introduction**
|
||||
We introduce SOLAR-10.7B, an advanced large language model (LLM) with 10.7 billion parameters, demonstrating superior performance in various natural language processing (NLP) tasks. It's compact, yet remarkably powerful, and demonstrates unparalleled state-of-the-art performance in models with parameters under 30B.
|
||||
|
||||
We present a methodology for scaling LLMs called depth up-scaling (DUS) , which encompasses architectural modifications and continued pretraining. In other words, we integrated Mistral 7B weights into the upscaled layers, and finally, continued pre-training for the entire model.
|
||||
|
||||
|
||||
SOLAR-10.7B has remarkable performance. It outperforms models with up to 30B parameters, even surpassing the recent Mixtral 8X7B model. For detailed information, please refer to the experimental table.
|
||||
Solar 10.7B is an ideal choice for fine-tuning. SOLAR-10.7B offers robustness and adaptability for your fine-tuning needs. Our simple instruction fine-tuning using the SOLAR-10.7B pre-trained model yields significant performance improvements.
|
||||
|
||||
For full details of this model please read our [paper](https://arxiv.org/abs/2312.15166).
|
||||
|
||||
|
||||
# **Instruction Fine-Tuning Strategy**
|
||||
|
||||
We utilize state-of-the-art instruction fine-tuning methods including supervised fine-tuning (SFT) and direct preference optimization (DPO) [1].
|
||||
|
||||
We used a mixture of the following datasets
|
||||
- c-s-ale/alpaca-gpt4-data (SFT)
|
||||
- Open-Orca/OpenOrca (SFT)
|
||||
- in-house generated data utilizing Metamath [2] (SFT, DPO)
|
||||
- Intel/orca_dpo_pairs (DPO)
|
||||
- allenai/ultrafeedback_binarized_cleaned (DPO)
|
||||
|
||||
where we were careful of data contamination by not using GSM8K samples when generating data and filtering tasks when applicable via the following list.
|
||||
```python
|
||||
filtering_task_list = [
|
||||
'task228_arc_answer_generation_easy',
|
||||
'ai2_arc/ARC-Challenge:1.0.0',
|
||||
'ai2_arc/ARC-Easy:1.0.0',
|
||||
'task229_arc_answer_generation_hard',
|
||||
'hellaswag:1.1.0',
|
||||
'task1389_hellaswag_completion',
|
||||
'cot_gsm8k',
|
||||
'cot_gsm8k_ii',
|
||||
'drop:2.0.0',
|
||||
'winogrande:1.1.0'
|
||||
]
|
||||
```
|
||||
|
||||
Using the datasets mentioned above, we applied SFT and iterative DPO training, a proprietary alignment strategy, to maximize the performance of our resulting model.
|
||||
|
||||
[1] Rafailov, R., Sharma, A., Mitchell, E., Ermon, S., Manning, C.D. and Finn, C., 2023. Direct preference optimization: Your language model is secretly a reward model. NeurIPS.
|
||||
|
||||
[2] Yu, L., Jiang, W., Shi, H., Yu, J., Liu, Z., Zhang, Y., Kwok, J.T., Li, Z., Weller, A. and Liu, W., 2023. Metamath: Bootstrap your own mathematical questions for large language models. arXiv preprint arXiv:2309.12284.
|
||||
|
||||
# **Data Contamination Test Results**
|
||||
|
||||
Recently, there have been contamination issues in some models on the LLM leaderboard.
|
||||
We note that we made every effort to exclude any benchmark-related datasets from training.
|
||||
We also ensured the integrity of our model by conducting a data contamination test [3] that is also used by the HuggingFace team [4, 5].
|
||||
|
||||
Our results, with `result < 0.1, %:` being well below 0.9, indicate that our model is free from contamination.
|
||||
|
||||
*The data contamination test results of HellaSwag and Winograde will be added once [3] supports them.*
|
||||
|
||||
| Model | ARC | MMLU | TruthfulQA | GSM8K |
|
||||
|------------------------------|-------|-------|-------|-------|
|
||||
| **SOLAR-10.7B-Instruct-v1.0**| result < 0.1, %: 0.06 |result < 0.1, %: 0.15 | result < 0.1, %: 0.28 | result < 0.1, %: 0.70 |
|
||||
|
||||
[3] https://github.com/swj0419/detect-pretrain-code-contamination
|
||||
|
||||
[4] https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard/discussions/474#657f2245365456e362412a06
|
||||
|
||||
[5] https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard/discussions/265#657b6debf81f6b44b8966230
|
||||
|
||||
# **Evaluation Results**
|
||||
|
||||
| Model | H6 | Model Size |
|
||||
|----------------------------------------|-------|------------|
|
||||
| **SOLAR-10.7B-Instruct-v1.0** | **74.20** | **~ 11B** |
|
||||
| mistralai/Mixtral-8x7B-Instruct-v0.1 | 72.62 | ~ 46.7B |
|
||||
| 01-ai/Yi-34B-200K | 70.81 | ~ 34B |
|
||||
| 01-ai/Yi-34B | 69.42 | ~ 34B |
|
||||
| mistralai/Mixtral-8x7B-v0.1 | 68.42 | ~ 46.7B |
|
||||
| meta-llama/Llama-2-70b-hf | 67.87 | ~ 70B |
|
||||
| tiiuae/falcon-180B | 67.85 | ~ 180B |
|
||||
| **SOLAR-10.7B-v1.0** | **66.04** | **~11B** |
|
||||
| mistralai/Mistral-7B-Instruct-v0.2 | 65.71 | ~ 7B |
|
||||
| Qwen/Qwen-14B | 65.86 | ~ 14B |
|
||||
| 01-ai/Yi-34B-Chat | 65.32 | ~34B |
|
||||
| meta-llama/Llama-2-70b-chat-hf | 62.4 | ~ 70B |
|
||||
| mistralai/Mistral-7B-v0.1 | 60.97 | ~ 7B |
|
||||
| mistralai/Mistral-7B-Instruct-v0.1 | 54.96 | ~ 7B |
|
||||
|
||||
# **Usage Instructions**
|
||||
|
||||
This model has been fine-tuned primarily for single-turn conversation, making it less suitable for multi-turn conversations such as chat.
|
||||
|
||||
### **Version**
|
||||
|
||||
Make sure you have the correct version of the transformers library installed:
|
||||
|
||||
```sh
|
||||
pip install transformers==4.35.2
|
||||
```
|
||||
|
||||
### **Loading the Model**
|
||||
|
||||
Use the following Python code to load the model:
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained("Upstage/SOLAR-10.7B-Instruct-v1.0")
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
"Upstage/SOLAR-10.7B-Instruct-v1.0",
|
||||
device_map="auto",
|
||||
torch_dtype=torch.float16,
|
||||
)
|
||||
```
|
||||
|
||||
### **Conducting Single-Turn Conversation**
|
||||
|
||||
```python
|
||||
conversation = [ {'role': 'user', 'content': 'Hello?'} ]
|
||||
|
||||
prompt = tokenizer.apply_chat_template(conversation, tokenize=False, add_generation_prompt=True)
|
||||
|
||||
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
|
||||
outputs = model.generate(**inputs, use_cache=True, max_length=4096)
|
||||
output_text = tokenizer.decode(outputs[0])
|
||||
print(output_text)
|
||||
```
|
||||
|
||||
Below is an example of the output.
|
||||
```
|
||||
<s> ### User:
|
||||
Hello?
|
||||
|
||||
### Assistant:
|
||||
Hello, how can I assist you today? Please feel free to ask any questions or request help with a specific task.</s>
|
||||
```
|
||||
|
||||
### **License**
|
||||
- [upstage/SOLAR-10.7B-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-v1.0): apache-2.0
|
||||
- [upstage/SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0): cc-by-nc-4.0
|
||||
- Since some non-commercial datasets such as Alpaca are used for fine-tuning, we release this model as cc-by-nc-4.0.
|
||||
|
||||
### **How to Cite**
|
||||
|
||||
Please cite this model using this format.
|
||||
|
||||
```bibtex
|
||||
@misc{kim2023solar,
|
||||
title={SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling},
|
||||
author={Dahyun Kim and Chanjun Park and Sanghoon Kim and Wonsung Lee and Wonho Song and Yunsu Kim and Hyeonwoo Kim and Yungi Kim and Hyeonju Lee and Jihoo Kim and Changbae Ahn and Seonghoon Yang and Sukyung Lee and Hyunbyung Park and Gyoungjin Gim and Mikyoung Cha and Hwalsuk Lee and Sunghun Kim},
|
||||
year={2023},
|
||||
eprint={2312.15166},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.CL}
|
||||
}
|
||||
```
|
||||
|
||||
### **The Upstage AI Team** ###
|
||||
Upstage is creating the best LLM and DocAI. Please find more information at https://upstage.ai
|
||||
|
||||
### **Contact Us** ###
|
||||
Any questions and suggestions, please use the discussion tab. If you want to contact us directly, drop an email to [contact@upstage.ai](mailto:contact@upstage.ai)
|
||||
# [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_CallComply__SOLAR-10.7B-Instruct-v1.0-128k)
|
||||
|
||||
| Metric |Value|
|
||||
|---------------------------------|----:|
|
||||
|Avg. |60.16|
|
||||
|AI2 Reasoning Challenge (25-Shot)|65.96|
|
||||
|HellaSwag (10-Shot) |84.35|
|
||||
|MMLU (5-Shot) |57.63|
|
||||
|TruthfulQA (0-shot) |65.42|
|
||||
|Winogrande (5-shot) |80.51|
|
||||
|GSM8k (5-shot) | 7.13|
|
||||
|
||||
34
config.json
Normal file
34
config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"_name_or_path": "CallComply/SOLAR-10.7B-Instruct-v1.0-128k",
|
||||
"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": 131072,
|
||||
"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": {
|
||||
"factor": 16.0,
|
||||
"finetuned": true,
|
||||
"original_max_position_embeddings": 8192,
|
||||
"type": "yarn"
|
||||
},
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.37.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
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 sha256:2c63ead1f2c68d6511ff3154d5549f811b0e71682fe0bc10899db5d1b32afcab
|
||||
size 4943162240
|
||||
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:c3d933e7524c54f9c3c982ec698e8499ccabe4c9c531e61b8e62443adea3903c
|
||||
size 4999819232
|
||||
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 sha256:4aadc5a5ff2f9187cacb49e55c9e1687cd78a20c25a5ba46ff58cbe20804118a
|
||||
size 4915916080
|
||||
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 sha256:29fea960b5463bda37ce29dbf2914dec55a6ef5e8a783bb4f4811f1ce3f7ebd1
|
||||
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 sha256:46e67ee561f241973fcebca4e911c8515bcabda67e1f30fe2136ea95d400d22a
|
||||
size 1688284744
|
||||
442
model.safetensors.index.json
Normal file
442
model.safetensors.index.json
Normal file
@@ -0,0 +1,442 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 21463048192
|
||||
},
|
||||
"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-00001-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-00002-of-00005.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-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-00002-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-00002-of-00005.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-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-00003-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-00004-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
|
||||
}
|
||||
}
|
||||
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.
46
tokenizer_config.json
Normal file
46
tokenizer_config.json
Normal file
@@ -0,0 +1,46 @@
|
||||
{
|
||||
"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": "{% 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']}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% endif %}{% endfor %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"device_map": {
|
||||
"": "cuda"
|
||||
},
|
||||
"eos_token": "</s>",
|
||||
"legacy": true,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "</s>",
|
||||
"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