AdaptLLM/medicine-LLM
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: AdaptLLM/medicine-LLM
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-04 08:10:12 +08:00
commit 3ca151e9b5
77 changed files with 810 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

101
.gitattributes vendored Normal file
View File

@@ -0,0 +1,101 @@
*.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
model-00001-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00002-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00003-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00004-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00005-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00006-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00007-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00008-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00009-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00010-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00011-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00012-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00013-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00014-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00015-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00016-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00017-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00018-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00019-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00020-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00021-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00022-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00023-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00024-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00025-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00026-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00027-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00028-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00029-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00030-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00031-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00032-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
model-00033-of-00033.safetensors filter=lfs diff=lfs merge=lfs -text
pytorch_model-00001-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00002-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00003-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00004-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00005-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00006-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00007-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00008-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00009-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00010-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00011-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00012-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00013-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00014-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00015-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00016-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00017-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00018-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00019-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00020-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00021-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00022-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00023-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00024-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00025-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00026-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00027-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00028-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00029-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00030-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00031-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00032-of-00033.bin filter=lfs diff=lfs merge=lfs -text
pytorch_model-00033-of-00033.bin filter=lfs diff=lfs merge=lfs -text

145
README.md Normal file
View File

@@ -0,0 +1,145 @@
---
language:
- en
datasets:
- Open-Orca/OpenOrca
- GAIR/lima
- WizardLM/WizardLM_evol_instruct_V2_196k
- EleutherAI/pile
metrics:
- accuracy
pipeline_tag: text-generation
tags:
- biology
- medical
---
# Adapting LLMs to Domains via Continual Pre-Training (ICLR 2024)
This repo contains the domain-specific base model developed from **LLaMA-1-7B**, using the method in our paper [Adapting Large Language Models via Reading Comprehension](https://huggingface.co/papers/2309.09530).
We explore **continued pre-training on domain-specific corpora** for large language models. While this approach enriches LLMs with domain knowledge, it significantly hurts their prompting ability for question answering. Inspired by human learning via reading comprehension, we propose a simple method to **transform large-scale pre-training corpora into reading comprehension texts**, consistently improving prompting performance across tasks in biomedicine, finance, and law domains. **Our 7B model competes with much larger domain-specific models like BloombergGPT-50B**.
### [2024/11/29] 🤗 Introduce the multimodal version of AdaptLLM at [AdaMLLM](https://huggingface.co/papers/2411.19930), for adapting MLLMs to domains 🤗
**************************** **Updates** ****************************
* 2024/11/29: Released [AdaMLLM](https://huggingface.co/AdaptLLM/Adapt-MLLM-to-Domains) for adapting MLLMs to domains
* 2024/9/20: Our [research paper for Instruction-Pretrain](https://huggingface.co/papers/2406.14491) has been accepted by EMNLP 2024
* 2024/8/29: Updated [guidelines](https://huggingface.co/datasets/AdaptLLM/finance-tasks) on evaluating any 🤗Huggingface models on the domain-specific tasks
* 2024/6/22: Released the [benchmarking code](https://github.com/microsoft/LMOps/tree/main/adaptllm)
* 2024/6/21: Released the general version of AdaptLLM at [Instruction-Pretrain](https://huggingface.co/instruction-pretrain)
* 2024/4/2: Released the [raw data splits (train and test)](https://huggingface.co/datasets/AdaptLLM/ConvFinQA) of all the evaluation datasets
* 2024/1/16: Our [research paper for AdaptLLM](https://huggingface.co/papers/2309.09530) has been accepted by ICLR 2024
* 2023/12/19: Released our [13B base models](https://huggingface.co/AdaptLLM/law-LLM-13B) developed from LLaMA-1-13B
* 2023/12/8: Released our [chat models](https://huggingface.co/AdaptLLM/law-chat) developed from LLaMA-2-Chat-7B
* 2023/9/18: Released our [paper](https://huggingface.co/papers/2309.09530), [code](https://github.com/microsoft/LMOps), [data](https://huggingface.co/datasets/AdaptLLM/law-tasks), and [base models](https://huggingface.co/AdaptLLM/law-LLM) developed from LLaMA-1-7B
## 1. Domain-Specific Models
### LLaMA-1-7B
In our paper, we develop three domain-specific models from LLaMA-1-7B, which are also available in Huggingface: [Biomedicine-LLM](https://huggingface.co/AdaptLLM/medicine-LLM), [Finance-LLM](https://huggingface.co/AdaptLLM/finance-LLM) and [Law-LLM](https://huggingface.co/AdaptLLM/law-LLM), the performances of our AdaptLLM compared to other domain-specific LLMs are:
<p align='center'>
<img src="https://cdn-uploads.huggingface.co/production/uploads/650801ced5578ef7e20b33d4/6efPwitFgy-pLTzvccdcP.png" width="700">
</p>
### LLaMA-1-13B
Moreover, we scale up our base model to LLaMA-1-13B to see if **our method is similarly effective for larger-scale models**, and the results are consistently positive too: [Biomedicine-LLM-13B](https://huggingface.co/AdaptLLM/medicine-LLM-13B), [Finance-LLM-13B](https://huggingface.co/AdaptLLM/finance-LLM-13B) and [Law-LLM-13B](https://huggingface.co/AdaptLLM/law-LLM-13B).
### LLaMA-2-Chat
Our method is also effective for aligned models! LLaMA-2-Chat requires a [specific data format](https://huggingface.co/blog/llama2#how-to-prompt-llama-2), and our **reading comprehension can perfectly fit the data format** by transforming the reading comprehension into a multi-turn conversation. We have also open-sourced chat models in different domains: [Biomedicine-Chat](https://huggingface.co/AdaptLLM/medicine-chat), [Finance-Chat](https://huggingface.co/AdaptLLM/finance-chat) and [Law-Chat](https://huggingface.co/AdaptLLM/law-chat).
For example, to chat with the biomedicine base model (🤗we highly recommend switching to the [chat model](https://huggingface.co/AdaptLLM/medicine-chat) for better response quality):
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("AdaptLLM/medicine-LLM")
tokenizer = AutoTokenizer.from_pretrained("AdaptLLM/medicine-LLM", use_fast=False)
# Put your input here:
user_input = '''Question: Which of the following is an example of monosomy?
Options:
- 46,XX
- 47,XXX
- 69,XYY
- 45,X
Please provide your choice first and then provide explanations if possible.'''
# Simply use your input as the prompt for base models
prompt = user_input
inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).input_ids.to(model.device)
outputs = model.generate(input_ids=inputs, max_length=2048)[0]
answer_start = int(inputs.shape[-1])
pred = tokenizer.decode(outputs[answer_start:], skip_special_tokens=True)
print(pred)
```
### LLaMA-3-8B (💡New!)
In our recent research on [Instruction-Pretrain](https://huggingface.co/papers/2406.14491), we developed a context-based instruction synthesizer to augment the raw corpora with instruction-response pairs, **enabling Llama3-8B to be comparable to or even outperform Llama3-70B**: [Finance-Llama3-8B](https://huggingface.co/instruction-pretrain/finance-Llama3-8B), [Biomedicine-Llama3-8B](https://huggingface.co/instruction-pretrain/medicine-Llama3-8B).
## 2. Domain-Specific Tasks
### Pre-templatized Testing Splits
To easily reproduce our prompting results, we have uploaded the filled-in zero/few-shot input instructions and output completions of the test each domain-specific task: [biomedicine-tasks](https://huggingface.co/datasets/AdaptLLM/medicine-tasks), [finance-tasks](https://huggingface.co/datasets/AdaptLLM/finance-tasks), and [law-tasks](https://huggingface.co/datasets/AdaptLLM/law-tasks).
Note: those filled-in instructions are specifically tailored for models before alignment and do NOT fit for the specific data format required for chat models.
### Evaluating Any Huggingface LMs on Domain-Specific Tasks (💡New!)
You can use the following script to reproduce our results and evaluate any other Huggingface models on domain-specific tasks. Note that the script is NOT applicable to models that require specific prompt templates (e.g., Llama2-chat, Llama3-Instruct).
1). **Set Up Dependencies**
```bash
git clone https://github.com/microsoft/LMOps
cd LMOps/adaptllm
pip install -r requirements.txt
```
2). **Evaluate the Model**
```bash
# Select the domain from ['biomedicine', 'finance', 'law']
DOMAIN='biomedicine'
# Specify any Huggingface model name (Not applicable to chat models)
MODEL='AdaptLLM/medicine-LLM'
# Model parallelization:
# - Set MODEL_PARALLEL=False if the model fits on a single GPU.
# We observe that LMs smaller than 10B always meet this requirement.
# - Set MODEL_PARALLEL=True if the model is too large and encounters OOM on a single GPU.
MODEL_PARALLEL=False
# Choose the number of GPUs from [1, 2, 4, 8]
N_GPU=1
# Whether to add a BOS token at the beginning of the prompt input:
# - Set to False for AdaptLLM.
# - Set to True for instruction-pretrain models.
# If unsure, we recommend setting it to False, as this is suitable for most LMs.
add_bos_token=False
# Run the evaluation script
bash scripts/inference.sh ${DOMAIN} ${MODEL} ${add_bos_token} ${MODEL_PARALLEL} ${N_GPU}
```
### Raw Datasets
We have also uploaded the raw training and testing splits, for facilitating fine-tuning or other usages: [ChemProt](https://huggingface.co/datasets/AdaptLLM/ChemProt), [RCT](https://huggingface.co/datasets/AdaptLLM/RCT), [ConvFinQA](https://huggingface.co/datasets/AdaptLLM/ConvFinQA), [FiQA_SA](https://huggingface.co/datasets/AdaptLLM/FiQA_SA), [Headline](https://huggingface.co/datasets/AdaptLLM/Headline), [NER](https://huggingface.co/datasets/AdaptLLM/NER), [FPB](https://huggingface.co/datasets/AdaptLLM/FPB)
### Domain Knowledge Probing
Our pre-processed knowledge probing datasets are available at: [med_knowledge_prob](https://huggingface.co/datasets/AdaptLLM/med_knowledge_prob) and [law_knowledge_prob](https://huggingface.co/datasets/AdaptLLM/law_knowledge_prob)
## Citation
If you find our work helpful, please cite us:
```bibtex
@inproceedings{
cheng2024adapting,
title={Adapting Large Language Models via Reading Comprehension},
author={Daixuan Cheng and Shaohan Huang and Furu Wei},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=y886UXPEZ0}
}
```

BIN
comparison.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 160 KiB

21
config.json Normal file
View File

@@ -0,0 +1,21 @@
{
"architectures": [
"LLaMAForCausalLM"
],
"bos_token_id": 0,
"eos_token_id": 1,
"hidden_act": "silu",
"hidden_size": 4096,
"intermediate_size": 11008,
"initializer_range": 0.02,
"max_sequence_length": 2048,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"pad_token_id": 32000,
"rms_norm_eps": 1e-06,
"torch_dtype": "float16",
"transformers_version": "4.27.0.dev0",
"use_cache": true,
"vocab_size": 32001
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

1
generation_config.json Normal file
View File

@@ -0,0 +1 @@
{"_from_model_config": true, "bos_token_id": 0, "eos_token_id": 1, "pad_token_id": 0, "transformers_version": "4.27.0.dev0"}

3
model-00001-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3368f7f09ff68b909d2265770608b60f382a51ca870038d579e68c5568f904a3
size 809518344

3
model-00002-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d25c149e00ead151f65e47da4dc4fcc305185699b0b8d22dd1f8061caa9018ba
size 809518344

3
model-00003-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7e90e7891f12db3e506e1fbf3a081397cb71b57b27c2ec2806b17094963eb091
size 809518344

3
model-00004-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2d4680a4e21b175f0e68876282432be55418606ccdf3cba62f8f27805866d18c
size 809518344

3
model-00005-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0ce67fa6be13e1b6a2ea61fe0ad4fcb34a7df8980f56c392b384d6baa0b8412e
size 809518344

3
model-00006-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1c065d000c773f12505f9663e882137dd9d49aa805f96f454c047b1c294fa59f
size 809518344

3
model-00007-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7485da707edcbb04d4afd460438a9da32cb5e51ce8009ec34ebd12fc0cd9a505
size 809518344

3
model-00008-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ced6459cd077fc3e2ea4368f095125a03ec461a539ada116842eb601abd2ef60
size 809518344

3
model-00009-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:24ee78b88f5a45b4b6ef2fb8c83b2d6dbcbf3b1f9cea0bddb05b630163503838
size 809518344

3
model-00010-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e25c52ae8e0382d3e848051bde57fa8a6f02a85689bb84a5454e4fbe9a5df516
size 809518344

3
model-00011-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a687e8ccada567b214903fec73fb65978e4f34ce2387436c5244969b5792d96e
size 809518360

3
model-00012-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9cc8dc34437d6a1a6d050f6353370506c2934effd5997a3194a61f7eb25ac784
size 809518360

3
model-00013-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2098361e29d762d7047c17c1f1bd4daf4b4f9b12cab66068373b0ba09b09363c
size 809518360

3
model-00014-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c4834cecbcbf46f8909c11340bea11f7bb050d7821655049d71e97e0359e00d2
size 809518360

3
model-00015-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:98f79244b3a866cf3589e40f06399d163b45e9fce6086196c79b5aba84ffe43a
size 809518360

3
model-00016-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:722f0eec23d5504a97012b69d4219c39ca04b426a6c93826e1b61d2e176762df
size 809518360

3
model-00017-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:72377618093d4b345c3718946e6f3cfd70b97d07f9dab6a5630b87ee8d8aeeea
size 809518360

3
model-00018-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d7191458ea542493664559526fb4c3578e86c8b0ed67b6729e96ae9c07f593bc
size 809518360

3
model-00019-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bfbbe7d9ee49c6cb5ab69ecf55b12d4e96c9d3477de24b77b9dc0845c81f7080
size 809518360

3
model-00020-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:873aee0c28c8a076197196e6aab8c34145a0939045237ed1e76ed8dd713d5ffa
size 809518360

3
model-00021-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:234e8d85a237b237de48689e8f2bd230da0a99a6d01e5735c5562863fb252487
size 809518360

3
model-00022-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:504ec89c61675f979719e17bf79667bdd1bbdb68ea08f88295251260a31636d3
size 809518360

3
model-00023-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b9439c133bdd811bf7e17a2b6d15093c58876c0b0f22ac4b2c2db3e74a9b3d2a
size 809518360

3
model-00024-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9b984390dadb12e1e9f673d710a41e40c38359a26fddb41ab15193b6e8e99bd1
size 809518360

3
model-00025-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:08d11ebd3ce7f9050263151fb39d1258048a476743175551fec6e4707e3c5967
size 809518360

3
model-00026-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cdd3d29a6fa02d9dfe135773f82687a05c0bd454b8abdc8a50fea9b4833023f0
size 809518360

3
model-00027-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e8656eec0fa5f0ff33e17defc0afe886f3156f8ad0a0acd62839bea4f18a2dba
size 809518360

3
model-00028-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b8786e86bbcf2772418c0b8a4f5506aa50e893ee7b45bc5b2b67bd8897567c9a
size 809518360

3
model-00029-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f70588976fd2556f2b3a3adaef8c27b5fa306e65739b745fdfd3ae0ae0a1bfd9
size 809518360

3
model-00030-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:208e45872abac3b783b07a56f4a53e56997bfd546cd16940d5f5763ab4f5e8fb
size 809518360

3
model-00031-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:61d7a54c94e5771ce0b7d8c3bbe1f42aa928a9e2eea6ff6cb1289e8b275ca64d
size 809518360

3
model-00032-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c00a57dfe67b1ec177147e75dba0b9f4b12307d3ffa23ca7d050a80cf8ee5165
size 809518360

3
model-00033-of-00033.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f5b6759bcb4138d4805e5bd861acc510fb5afc7aa70d6bcf6d70339c26abcc9c
size 524312896

330
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,330 @@
{
"weight_map": {
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00033.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00033.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00033.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00033.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00033.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00033.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00033.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00033.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00033.safetensors",
"model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00033.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00002-of-00033.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00002-of-00033.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00002-of-00033.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00002-of-00033.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00002-of-00033.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00033.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00033.safetensors",
"model.layers.1.input_layernorm.weight": "model-00002-of-00033.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00033.safetensors",
"model.layers.1.self_attn.rotary_emb.inv_freq": "model-00002-of-00033.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00003-of-00033.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00003-of-00033.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00003-of-00033.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00003-of-00033.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00003-of-00033.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00003-of-00033.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00003-of-00033.safetensors",
"model.layers.2.input_layernorm.weight": "model-00003-of-00033.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00003-of-00033.safetensors",
"model.layers.2.self_attn.rotary_emb.inv_freq": "model-00003-of-00033.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00004-of-00033.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00004-of-00033.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00004-of-00033.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00004-of-00033.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00004-of-00033.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00004-of-00033.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00004-of-00033.safetensors",
"model.layers.3.input_layernorm.weight": "model-00004-of-00033.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00004-of-00033.safetensors",
"model.layers.3.self_attn.rotary_emb.inv_freq": "model-00004-of-00033.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00005-of-00033.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00005-of-00033.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00005-of-00033.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00005-of-00033.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00005-of-00033.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00005-of-00033.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00005-of-00033.safetensors",
"model.layers.4.input_layernorm.weight": "model-00005-of-00033.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00005-of-00033.safetensors",
"model.layers.4.self_attn.rotary_emb.inv_freq": "model-00005-of-00033.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00006-of-00033.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00006-of-00033.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00006-of-00033.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00006-of-00033.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00006-of-00033.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00006-of-00033.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00006-of-00033.safetensors",
"model.layers.5.input_layernorm.weight": "model-00006-of-00033.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00006-of-00033.safetensors",
"model.layers.5.self_attn.rotary_emb.inv_freq": "model-00006-of-00033.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00007-of-00033.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00007-of-00033.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00007-of-00033.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00007-of-00033.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00007-of-00033.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00007-of-00033.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00007-of-00033.safetensors",
"model.layers.6.input_layernorm.weight": "model-00007-of-00033.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00007-of-00033.safetensors",
"model.layers.6.self_attn.rotary_emb.inv_freq": "model-00007-of-00033.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00008-of-00033.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00008-of-00033.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00008-of-00033.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00008-of-00033.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00008-of-00033.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00008-of-00033.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00008-of-00033.safetensors",
"model.layers.7.input_layernorm.weight": "model-00008-of-00033.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00008-of-00033.safetensors",
"model.layers.7.self_attn.rotary_emb.inv_freq": "model-00008-of-00033.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00009-of-00033.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00009-of-00033.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00009-of-00033.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00009-of-00033.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00009-of-00033.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00009-of-00033.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00009-of-00033.safetensors",
"model.layers.8.input_layernorm.weight": "model-00009-of-00033.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00009-of-00033.safetensors",
"model.layers.8.self_attn.rotary_emb.inv_freq": "model-00009-of-00033.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00010-of-00033.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00010-of-00033.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00010-of-00033.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00010-of-00033.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00010-of-00033.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00010-of-00033.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00010-of-00033.safetensors",
"model.layers.9.input_layernorm.weight": "model-00010-of-00033.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00010-of-00033.safetensors",
"model.layers.9.self_attn.rotary_emb.inv_freq": "model-00010-of-00033.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00011-of-00033.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00011-of-00033.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00011-of-00033.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00011-of-00033.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00011-of-00033.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00011-of-00033.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00011-of-00033.safetensors",
"model.layers.10.input_layernorm.weight": "model-00011-of-00033.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00011-of-00033.safetensors",
"model.layers.10.self_attn.rotary_emb.inv_freq": "model-00011-of-00033.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00012-of-00033.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00012-of-00033.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00012-of-00033.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00012-of-00033.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00012-of-00033.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00012-of-00033.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00012-of-00033.safetensors",
"model.layers.11.input_layernorm.weight": "model-00012-of-00033.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00012-of-00033.safetensors",
"model.layers.11.self_attn.rotary_emb.inv_freq": "model-00012-of-00033.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00013-of-00033.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00013-of-00033.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00013-of-00033.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00013-of-00033.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00013-of-00033.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00013-of-00033.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00013-of-00033.safetensors",
"model.layers.12.input_layernorm.weight": "model-00013-of-00033.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00013-of-00033.safetensors",
"model.layers.12.self_attn.rotary_emb.inv_freq": "model-00013-of-00033.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00014-of-00033.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00014-of-00033.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00014-of-00033.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00014-of-00033.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00014-of-00033.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00014-of-00033.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00014-of-00033.safetensors",
"model.layers.13.input_layernorm.weight": "model-00014-of-00033.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00014-of-00033.safetensors",
"model.layers.13.self_attn.rotary_emb.inv_freq": "model-00014-of-00033.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00015-of-00033.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00015-of-00033.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00015-of-00033.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00015-of-00033.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00015-of-00033.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00015-of-00033.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00015-of-00033.safetensors",
"model.layers.14.input_layernorm.weight": "model-00015-of-00033.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00015-of-00033.safetensors",
"model.layers.14.self_attn.rotary_emb.inv_freq": "model-00015-of-00033.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00016-of-00033.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00016-of-00033.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00016-of-00033.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00016-of-00033.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00016-of-00033.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00016-of-00033.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00016-of-00033.safetensors",
"model.layers.15.input_layernorm.weight": "model-00016-of-00033.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00016-of-00033.safetensors",
"model.layers.15.self_attn.rotary_emb.inv_freq": "model-00016-of-00033.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00017-of-00033.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00017-of-00033.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00017-of-00033.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00017-of-00033.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00017-of-00033.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00017-of-00033.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00017-of-00033.safetensors",
"model.layers.16.input_layernorm.weight": "model-00017-of-00033.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00017-of-00033.safetensors",
"model.layers.16.self_attn.rotary_emb.inv_freq": "model-00017-of-00033.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00018-of-00033.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00018-of-00033.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00018-of-00033.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00018-of-00033.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00018-of-00033.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00018-of-00033.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00018-of-00033.safetensors",
"model.layers.17.input_layernorm.weight": "model-00018-of-00033.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00018-of-00033.safetensors",
"model.layers.17.self_attn.rotary_emb.inv_freq": "model-00018-of-00033.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00019-of-00033.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00019-of-00033.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00019-of-00033.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00019-of-00033.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00019-of-00033.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00019-of-00033.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00019-of-00033.safetensors",
"model.layers.18.input_layernorm.weight": "model-00019-of-00033.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00019-of-00033.safetensors",
"model.layers.18.self_attn.rotary_emb.inv_freq": "model-00019-of-00033.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00020-of-00033.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00020-of-00033.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00020-of-00033.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00020-of-00033.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00020-of-00033.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00020-of-00033.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00020-of-00033.safetensors",
"model.layers.19.input_layernorm.weight": "model-00020-of-00033.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00020-of-00033.safetensors",
"model.layers.19.self_attn.rotary_emb.inv_freq": "model-00020-of-00033.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00021-of-00033.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00021-of-00033.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00021-of-00033.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00021-of-00033.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00021-of-00033.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00021-of-00033.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00021-of-00033.safetensors",
"model.layers.20.input_layernorm.weight": "model-00021-of-00033.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00021-of-00033.safetensors",
"model.layers.20.self_attn.rotary_emb.inv_freq": "model-00021-of-00033.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00022-of-00033.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00022-of-00033.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00022-of-00033.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00022-of-00033.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00022-of-00033.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00022-of-00033.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00022-of-00033.safetensors",
"model.layers.21.input_layernorm.weight": "model-00022-of-00033.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00022-of-00033.safetensors",
"model.layers.21.self_attn.rotary_emb.inv_freq": "model-00022-of-00033.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00023-of-00033.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00023-of-00033.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00023-of-00033.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00023-of-00033.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00023-of-00033.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00023-of-00033.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00023-of-00033.safetensors",
"model.layers.22.input_layernorm.weight": "model-00023-of-00033.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00023-of-00033.safetensors",
"model.layers.22.self_attn.rotary_emb.inv_freq": "model-00023-of-00033.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00024-of-00033.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00024-of-00033.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00024-of-00033.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00024-of-00033.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00024-of-00033.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00024-of-00033.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00024-of-00033.safetensors",
"model.layers.23.input_layernorm.weight": "model-00024-of-00033.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00024-of-00033.safetensors",
"model.layers.23.self_attn.rotary_emb.inv_freq": "model-00024-of-00033.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00025-of-00033.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00025-of-00033.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00025-of-00033.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00025-of-00033.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00025-of-00033.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00025-of-00033.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00025-of-00033.safetensors",
"model.layers.24.input_layernorm.weight": "model-00025-of-00033.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00025-of-00033.safetensors",
"model.layers.24.self_attn.rotary_emb.inv_freq": "model-00025-of-00033.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00026-of-00033.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00026-of-00033.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00026-of-00033.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00026-of-00033.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00026-of-00033.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00026-of-00033.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00026-of-00033.safetensors",
"model.layers.25.input_layernorm.weight": "model-00026-of-00033.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00026-of-00033.safetensors",
"model.layers.25.self_attn.rotary_emb.inv_freq": "model-00026-of-00033.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00027-of-00033.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00027-of-00033.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00027-of-00033.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00027-of-00033.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00027-of-00033.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00027-of-00033.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00027-of-00033.safetensors",
"model.layers.26.input_layernorm.weight": "model-00027-of-00033.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00027-of-00033.safetensors",
"model.layers.26.self_attn.rotary_emb.inv_freq": "model-00027-of-00033.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00028-of-00033.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00028-of-00033.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00028-of-00033.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00028-of-00033.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00028-of-00033.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00028-of-00033.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00028-of-00033.safetensors",
"model.layers.27.input_layernorm.weight": "model-00028-of-00033.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00028-of-00033.safetensors",
"model.layers.27.self_attn.rotary_emb.inv_freq": "model-00028-of-00033.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00029-of-00033.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00029-of-00033.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00029-of-00033.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00029-of-00033.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00029-of-00033.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00029-of-00033.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00029-of-00033.safetensors",
"model.layers.28.input_layernorm.weight": "model-00029-of-00033.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00029-of-00033.safetensors",
"model.layers.28.self_attn.rotary_emb.inv_freq": "model-00029-of-00033.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00030-of-00033.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00030-of-00033.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00030-of-00033.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00030-of-00033.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00030-of-00033.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00030-of-00033.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00030-of-00033.safetensors",
"model.layers.29.input_layernorm.weight": "model-00030-of-00033.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00030-of-00033.safetensors",
"model.layers.29.self_attn.rotary_emb.inv_freq": "model-00030-of-00033.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00031-of-00033.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00031-of-00033.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00031-of-00033.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00031-of-00033.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00031-of-00033.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00031-of-00033.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00031-of-00033.safetensors",
"model.layers.30.input_layernorm.weight": "model-00031-of-00033.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00031-of-00033.safetensors",
"model.layers.30.self_attn.rotary_emb.inv_freq": "model-00031-of-00033.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00032-of-00033.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00032-of-00033.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00032-of-00033.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00032-of-00033.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00032-of-00033.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00032-of-00033.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00032-of-00033.safetensors",
"model.layers.31.input_layernorm.weight": "model-00032-of-00033.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00032-of-00033.safetensors",
"model.layers.31.self_attn.rotary_emb.inv_freq": "model-00032-of-00033.safetensors",
"model.embed_tokens.weight": "model-00033-of-00033.safetensors",
"model.norm.weight": "model-00033-of-00033.safetensors",
"lm_head.weight": "model-00033-of-00033.safetensors"
},
"metadata": {
"total_size": 13476835328
}
}

3
pytorch_model-00001-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cfa3fc237bbecb8982e67a92d410e1daa48c720a9d566e1c4c18b3e3890c71bd
size 809520963

3
pytorch_model-00002-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:24146cba79a478ecea5d900870c75b248aee39afd5995e123cdb31be12a754aa
size 809520963

3
pytorch_model-00003-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:43a4ab801023b1acacb638877c74aed27bd9e12898571fce97af0f264d05f7de
size 809520963

3
pytorch_model-00004-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3b2d6973e059cd01ca44a7a19c87b1a3eb8c1b2f4e82c6dc009abdf9d2f3b755
size 809520963

3
pytorch_model-00005-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d12b9adb06870196c9c33c6bc53b90faf767d4a34f0eca34910667431c3b1c4c
size 809520963

3
pytorch_model-00006-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ee4188d6fcd05385e65a5137e00fdff80fb43df7f23e14db1990517a8a881932
size 809520963

3
pytorch_model-00007-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0eeb9db5cb455aa3c30ace5182ea655131a10d21e8621efd091771d9dd5ec3ac
size 809520963

3
pytorch_model-00008-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:84afeffda180a5a5f893178e290c12a69aa86a6b8cf306e7152b8ad68ef8e07a
size 809520963

3
pytorch_model-00009-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f0c48999b6911c0e2531e6c52fd100761bb97c8c903b0e46f0310346878bc099
size 809520963

3
pytorch_model-00010-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1dbc33e2ee3e5399a99d8e6456cb226914df88bc0ca9a70c8dc816fab026421c
size 809520963

3
pytorch_model-00011-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6a01412018382124a7cef1363771dd3c9e2371b02fd2291c19b82caf8de8b180
size 809520963

3
pytorch_model-00012-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:548ba11c335a6b8193ad1a64baf9ac6537af66a971763fff2928e50eac7f59c4
size 809520963

3
pytorch_model-00013-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c4af705eb4be81c0cc700be69ccc2c30f64f4dca5da97edfd3adfd2164c34f1f
size 809520963

3
pytorch_model-00014-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:84f6d4d1e17f34524de3fa901642e048ce9434ed8ac62dd0339d6957e7c590dc
size 809520963

3
pytorch_model-00015-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6b051151d1a160c0e5a506bbeb499f2596f8a43a9c78d83bbdf2628b7a2dcf41
size 809520963

3
pytorch_model-00016-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:79c0d5f3bf78378cf0fee2d31277b7658cf7691a992c3079435003db7e795735
size 809520963

3
pytorch_model-00017-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1d8a2dd3e8a495f2f154bfa2388f6ebc52de27dfcbd075c264846f02db98c6ce
size 809520963

3
pytorch_model-00018-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:85d1792e4ffe493d73f204b26d8e95c96a91cbcca081cc7c8d7702c16b3f8988
size 809520963

3
pytorch_model-00019-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5df54ebad10b28bd0d865e214e8c1b6a860fdf1c144cbff635604b7e0e535420
size 809520963

3
pytorch_model-00020-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:da1aa4c2f6c0fcc651af7e0a1328e3813d8f6fc6e3ad01fb68afee8d357e6d6e
size 809520963

3
pytorch_model-00021-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0690ce2c8e0fb80e267c7964adfbb14ea60fc38a9b75ad1e575658160bb5af50
size 809520963

3
pytorch_model-00022-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9a9a2286a812fd3dae3138c616aa8f340725a6d2b4e0ea4097d18dc1464af561
size 809520963

3
pytorch_model-00023-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1104557819a42e487d5ee4051339d28f80aacc518644ecbdee8abb4a7d01d328
size 809520963

3
pytorch_model-00024-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:041135a90bf937d0d3c00dd536160569e53f921d8d941e981c531b21bdad47a1
size 809520963

3
pytorch_model-00025-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f1f6674f85d535eb2d80d370c991fbcdd1ae8fe8a79947a16d898aba1cc0c1a0
size 809520963

3
pytorch_model-00026-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7cb846aedb10220d05979eee91be214cde6d6c59441be65edf90a7036827ba9b
size 809520963

3
pytorch_model-00027-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ab91db96ed9bb22fe4afbc76750608d71eec6a1ec28d65e562dc5e82f058cf9f
size 809520963

3
pytorch_model-00028-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7ec4a1561691311072407da847d933e7ac826f7b7d471b7384d876aa3dd5d6cb
size 809520963

3
pytorch_model-00029-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f769ff6cca6fc7892e6c78e5938694f1908346800bb724bb338bb54020b95a07
size 809520963

3
pytorch_model-00030-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:157fd26afac79204fcf0964270b4bc54d2a0655a9b008eeede2c85b5caa6f703
size 809520963

3
pytorch_model-00031-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8c94c0f7d851aa4b3479459cbf760cb7b1740508d422d0f4ce0efec9361729b4
size 809520963

3
pytorch_model-00032-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cc45d3e8518655ed9b78dfe5766dd5ace7048f8959621b4e5c51e609bd772570
size 809520963

3
pytorch_model-00033-of-00033.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5fe79967f185823af08d57640c33cb55464d86895b514435cc2ebaf61d73a9d1
size 524314060

1
pytorch_model.bin.index.json Normal file
View File

File diff suppressed because one or more lines are too long

1
special_tokens_map.json Normal file
View File

@@ -0,0 +1 @@
{}

3
tokenizer.model Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fa299a0662fc3bf7ada4d816b1cb9fdeb472e9edf6c2ffbc7f00e1b5ff5ff968
size 499739

8
tokenizer_config.json Normal file
View File

@@ -0,0 +1,8 @@
{
"bos_token": "<s>",
"eos_token": "</s>",
"model_max_length": 2048,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"pad_token": "<pad>"
}