fblgit/juanako-7b-UNA
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: fblgit/juanako-7b-UNA
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-10 23:04:33 +08:00
commit 34b1810fb6
11 changed files with 1041 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View 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

583
README.md Normal file
View File

@@ -0,0 +1,583 @@
---
license: apache-2.0
tags:
- alignment-handbook
- generated_from_trainer
- juanako
- mistral
- UNA
datasets:
- HuggingFaceH4/ultrafeedback_binarized
model-index:
- name: juanako-7b-UNA
results:
- task:
type: text-generation
name: TruthfulQA (MC2)
dataset:
name: truthful_qa
type: text-generation
config: multiple_choice
split: validation
metrics:
- type: accuracy
value: 65.13
verified: true
- task:
type: text-generation
name: ARC-Challenge
dataset:
name: ai2_arc
type: text-generation
config: ARC-Challenge
split: test
metrics:
- type: accuracy
value: 68.17
verified: true
- task:
type: text-generation
name: HellaSwag
dataset:
name: Rowan/hellaswag
type: text-generation
split: test
metrics:
- type: accuracy
value: 85.34
verified: true
- type: accuracy
value: 83.57
- task:
type: text-generation
name: Winogrande
dataset:
name: winogrande
type: text-generation
config: winogrande_debiased
split: test
metrics:
- type: accuracy
value: 78.85
verified: true
- task:
type: text-generation
name: MMLU
dataset:
name: cais/mmlu
type: text-generation
config: all
split: test
metrics:
- type: accuracy
value: 62.47
verified: true
- task:
type: text-generation
name: DROP
dataset:
name: drop
type: text-generation
split: validation
metrics:
- type: accuracy
value: 38.74
verified: true
- task:
type: text-generation
name: PubMedQA
dataset:
name: bigbio/pubmed_qa
type: text-generation
config: pubmed_qa_artificial_bigbio_qa
split: validation
metrics:
- type: accuracy
value: 76.0
- 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: 68.17
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/juanako-7b-UNA
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 85.34
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/juanako-7b-UNA
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: 62.47
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/juanako-7b-UNA
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: 65.13
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/juanako-7b-UNA
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: 78.85
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/juanako-7b-UNA
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: 44.81
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/juanako-7b-UNA
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: IFEval (0-Shot)
type: HuggingFaceH4/ifeval
args:
num_few_shot: 0
metrics:
- type: inst_level_strict_acc and prompt_level_strict_acc
value: 48.37
name: strict accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/juanako-7b-UNA
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BBH (3-Shot)
type: BBH
args:
num_few_shot: 3
metrics:
- type: acc_norm
value: 30.42
name: normalized accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/juanako-7b-UNA
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MATH Lvl 5 (4-Shot)
type: hendrycks/competition_math
args:
num_few_shot: 4
metrics:
- type: exact_match
value: 2.87
name: exact match
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/juanako-7b-UNA
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GPQA (0-shot)
type: Idavidrein/gpqa
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 6.15
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/juanako-7b-UNA
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MuSR (0-shot)
type: TAUR-Lab/MuSR
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 17.16
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/juanako-7b-UNA
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU-PRO (5-shot)
type: TIGER-Lab/MMLU-Pro
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 19.68
name: accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/juanako-7b-UNA
name: Open LLM Leaderboard
---
# juanako-7b-UNA (Uniform Neural Alignment)
This model is a fine-tuned version of [fblgit/juanako-7b-UNA-v2-phase-1](https://huggingface.co/fblgit/juanako-7b-UNA-v2-phase-1) on the HuggingFaceH4/ultrafeedback_binarized dataset.
It outperforms in many aspects most of the current Mistral based models and is the **latest and most powerful juanako version as of now**.
## Scores
The official HuggingFace results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/fblgit/juanako-7b-UNA/results_2023-11-28T08-33-33.965228.json)
| Model | Average ⬆️| ARC (25-s) ⬆️ | HellaSwag (10-s) ⬆️ | MMLU (5-s) ⬆️| TruthfulQA (MC) (0-s) ⬆️ | Winogrande (5-s) | GSM8K (5-s) | DROP (3-s) |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
|[mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) | 50.32 | 59.58 | 83.31 | 64.16 | 42.15 | 78.37 | 18.12 | 6.14 |
| [Intel/neural-chat-7b-v3-1](https://huggingface.co/Intel/neural-chat-7b-v3-1) | 59.0 | 66.21 | 83.64 | 62.37 | 59.65 | 78.14 | 19.56 | 43.84 |
| [fblgit/juanako-7b-UNA](https://huggingface.co/fblgit/juanako-7b-UNA) | **59.91** | **68.17** | **85.34** | 62.47 | **65.13** | **78.85** | **20.7** | 38.74 |
It scores: **59.91** according HuggingFace LLM Leaderboard.
It scores: **65.1** with `big-refactor` branch of lm-eval-harness
Author [Xavier M.](mailto:xavi@juanako.ai) @fblgit
## Model description
juanako uses UNA, Uniform Neural Alignment. A training technique that ease alignment between transformer layers yet to be published.
### Prompts
The following prompts showed positive results, it may depend the task and needs further experimentation but this should work for starters:
```
<|im_start|>system
- You are a helpful assistant chatbot trained by MosaicML.
- You answer questions.
- You are excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
- You are more than just an information source, you are also able to write poetry, short stories, and make jokes.<|im_end|>
<|im_start|>user
Explain QKV<|im_end|>
<|im_start|>assistant
```
```
### Assistant: I am StableVicuna, a large language model created by CarperAI. I am here to chat!
### Human: Explain QKV
### Assistant:
```
```
[Round <|round|>]
问：Explain QKV
答：
```
```
[Round <|round|>]
Question：Explain QKV
Answer：
```
```
Question：Explain QKV
Answer：
```
## Evaluations (lm-eval big-refactor branch)
### TruthfulQA 0-Shot
```
| Tasks |Version|Filter|Metric|Value | |Stderr|
|--------------|-------|------|------|-----:|---|-----:|
|truthfulqa_mc2|Yaml |none |acc |0.6549|± |0.0153|
```
### ARC 25-Shot
```
| Tasks |Version|Filter| Metric |Value | |Stderr|
|-------------|-------|------|--------|-----:|---|-----:|
|arc_challenge|Yaml |none |acc |0.6476|± |0.0140|
| | |none |acc_norm|0.6809|± |0.0136|
```
### HellaSwag 10-Shot
```
| Tasks |Version|Filter| Metric |Value | |Stderr|
|---------|-------|------|--------|-----:|---|-----:|
|hellaswag|Yaml |none |acc |0.6703|± |0.0047|
| | |none |acc_norm|0.8520|± |0.0035|
```
### GSM8k 5-Shot
```
|Tasks|Version| Filter | Metric |Value | |Stderr|
|-----|-------|----------|-----------|-----:|---|-----:|
|gsm8k|Yaml |get-answer|exact_match|0.4898|± |0.0138|
```
### GPT Evaluations 0-Shot
```
| Tasks |Version|Filter| Metric |Value | |Stderr|
|--------------|-------|------|----------|-----:|---|-----:|
|boolq |Yaml |none |acc |0.8703|± |0.0059|
|lambada_openai|Yaml |none |perplexity|3.2598|± |0.0705|
| | |none |acc |0.7336|± |0.0062|
|piqa |Yaml |none |acc |0.8254|± |0.0089|
| | |none |acc_norm |0.8292|± |0.0088|
|sciq |Yaml |none |acc |0.9580|± |0.0063|
| | |none |acc_norm |0.9130|± |0.0089|
```
### MathQA 0-Shot
```
|Tasks |Version|Filter| Metric |Value | |Stderr|
|------|-------|------|--------|-----:|---|-----:|
|mathqa|Yaml |none |acc |0.3752|± |0.0089|
| | |none |acc_norm|0.3772|± |0.0089|
```
### PiQa 1-Shot
```
|Tasks|Version|Filter| Metric |Value | |Stderr|
|-----|-------|------|--------|-----:|---|-----:|
|piqa |Yaml |none |acc |0.8308|± |0.0087|
| | |none |acc_norm|0.8357|± |0.0086|
```
### Winogrande 5-Shot
```
| Tasks |Version|Filter|Metric|Value| |Stderr|
|----------|-------|------|------|----:|---|-----:|
|winogrande|Yaml |none |acc |0.768|± |0.0119|
```
### PubMedQA 0-Shot
```
| Tasks |Version|Filter|Metric|Value| |Stderr|
|--------|-------|------|------|----:|---|-----:|
|pubmedqa|Yaml |none |acc | 0.76|± |0.0191|
```
### RACE 1-Shot
```
|Tasks|Version|Filter|Metric|Value | |Stderr|
|-----|-------|------|------|-----:|---|-----:|
|race |Yaml |none |acc |0.5282|± |0.0154|
```
### MMLU 5-Shot (8-Bit)
```
| Groups |Version|Filter|Metric|Value | |Stderr|
|------------------|-------|------|------|-----:|---|-----:|
|mmlu |N/A |none |acc |0.6137|± |0.1243|
| - humanities |N/A |none |acc |0.5671|± |0.1101|
| - other |N/A |none |acc |0.6859|± |0.1164|
| - social_sciences|N/A |none |acc |0.7195|± |0.0713|
| - stem |N/A |none |acc |0.5087|± |0.1297|
```
### DROP 3-Shot (8-Bit) (Instruct-Eval)
```
{'score': 0.49801113762927607}
{'drop': 49.8}
drop: 49.8
```
### CRASS 0-Shot (Instruct-Eval)
```
{'score': 0.8357664233576643}
{'crass': 83.58}
crass: 83.58
```
## Training Details
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 14
- gradient_accumulation_steps: 16
- total_train_batch_size: 224
- total_eval_batch_size: 14
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.4795 | 0.2 | 56 | 0.4958 | -1.3684 | -2.6385 | 0.7552 | 1.2701 | -265.3887 | -241.2612 | -2.2572 | -2.4922 |
| 0.4642 | 0.4 | 112 | 0.4859 | -1.0380 | -1.9769 | 0.7273 | 0.9389 | -258.7718 | -237.9569 | -2.2414 | -2.4751 |
| 0.4758 | 0.61 | 168 | 0.4808 | -1.2594 | -2.3704 | 0.7343 | 1.1110 | -262.7074 | -240.1708 | -2.2305 | -2.4633 |
| 0.4549 | 0.81 | 224 | 0.4768 | -1.1906 | -2.3201 | 0.7552 | 1.1295 | -262.2044 | -239.4827 | -2.2284 | -2.4610 |
### Framework versions
- Transformers 4.35.0-UNA
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1
## Citations
If you find juanako useful please:
```
@misc{juanako7buna,
title={Juanako: Uniform Neural Alignment},
author={Xavier Murias},
year={2023},
publisher = {HuggingFace},
journal = {HuggingFace repository},
howpublished = {\url{https://huggingface.co/fblgit/juanako-7b-UNA}},
}
```
Thanks to all the brilliant humans behind the creation of AI, here some of the ones that we find relevant to our research. If you feel a citation is missing, please contact.
```
@misc{lin2021truthfulqa,
title={TruthfulQA: Measuring How Models Mimic Human Falsehoods},
author={Stephanie Lin and Jacob Hilton and Owain Evans},
year={2021},
eprint={2109.07958},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
@misc{tunstall2023zephyr,
title={Zephyr: Direct Distillation of LM Alignment},
author={Lewis Tunstall and Edward Beeching and Nathan Lambert and Nazneen Rajani and Kashif Rasul and Younes Belkada and Shengyi Huang and Leandro von Werra and Clémentine Fourrier and Nathan Habib and Nathan Sarrazin and Omar Sanseviero and Alexander M. Rush and Thomas Wolf},
year={2023},
eprint={2310.16944},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
@inproceedings{Bisk2020,
author = {Yonatan Bisk and Rowan Zellers and
Ronan Le Bras and Jianfeng Gao
and Yejin Choi},
title = {PIQA: Reasoning about Physical Commonsense in
Natural Language},
booktitle = {Thirty-Fourth AAAI Conference on
Artificial Intelligence},
year = {2020},
}
@software{eval-harness,
author = {Gao, Leo and
Tow, Jonathan and
Biderman, Stella and
Black, Sid and
DiPofi, Anthony and
Foster, Charles and
Golding, Laurence and
Hsu, Jeffrey and
McDonell, Kyle and
Muennighoff, Niklas and
Phang, Jason and
Reynolds, Laria and
Tang, Eric and
Thite, Anish and
Wang, Ben and
Wang, Kevin and
Zou, Andy},
title = {A framework for few-shot language model evaluation},
month = sep,
year = 2021,
publisher = {Zenodo},
version = {v0.0.1},
doi = {10.5281/zenodo.5371628},
url = {https://doi.org/10.5281/zenodo.5371628}
}
@misc{rafailov2023direct,
title={Direct Preference Optimization: Your Language Model is Secretly a Reward Model},
author={Rafael Rafailov and Archit Sharma and Eric Mitchell and Stefano Ermon and Christopher D. Manning and Chelsea Finn},
year={2023},
eprint={2305.18290},
archivePrefix={arXiv},
}
```
# [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_fblgit__juanako-7b-UNA)
| Metric |Value|
|---------------------------------|----:|
|Avg. |67.46|
|AI2 Reasoning Challenge (25-Shot)|68.17|
|HellaSwag (10-Shot) |85.34|
|MMLU (5-Shot) |62.47|
|TruthfulQA (0-shot) |65.13|
|Winogrande (5-shot) |78.85|
|GSM8k (5-shot) |44.81|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_fblgit__juanako-7b-UNA)
| Metric |Value|
|-------------------|----:|
|Avg. |20.77|
|IFEval (0-Shot) |48.37|
|BBH (3-Shot) |30.42|
|MATH Lvl 5 (4-Shot)| 2.87|
|GPQA (0-shot) | 6.15|
|MuSR (0-shot) |17.16|
|MMLU-PRO (5-shot) |19.68|

25
config.json Normal file
View File

@@ -0,0 +1,25 @@
{
"_name_or_path": "fblgit/juanako-7b-UNA-v2-phase-1",
"architectures": [
"MistralForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.35.0",
"use_cache": true,
"vocab_size": 32000
}

6
generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"transformers_version": "4.35.0"
}

3
model-00001-of-00003.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b9aa527fcad7a3c19cad8a303137dc25c38e14ae7f2f312270578be7775f7ed4
size 4943162336

3
model-00002-of-00003.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f15688ea59c9f4b963ada01217cef8be5716af011273de3d4c8ac4b4dc868c9f
size 4999819336

3
model-00003-of-00003.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cc6bc80e78333eb0ed718d1db10fbd5a9ce70478b13926bbacfc04519e686721
size 4540516344

298
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,298 @@
{
"metadata": {
"total_size": 14483464192
},
"weight_map": {
"lm_head.weight": "model-00003-of-00003.safetensors",
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.norm.weight": "model-00003-of-00003.safetensors"
}
}

35
special_tokens_map.json Normal file
View File

@@ -0,0 +1,35 @@
{
"additional_special_tokens": [
"<unk>",
"<s>",
"</s>"
],
"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
}
}

BIN
tokenizer.model (Stored with Git LFS) Normal file
View File

Binary file not shown.

47
tokenizer_config.json Normal file
View File

@@ -0,0 +1,47 @@
{
"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": [
"<unk>",
"<s>",
"</s>"
],
"bos_token": "<s>",
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 2048,
"pad_token": "</s>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": true
}