AdaptLLM/finance-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/finance-LLM
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-21 07:15:06 +08:00
commit 9ff525ccd3
77 changed files with 807 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

142
README.md Normal file
View File

@@ -0,0 +1,142 @@
---
language:
- en
datasets:
- Open-Orca/OpenOrca
- GAIR/lima
- WizardLM/WizardLM_evol_instruct_V2_196k
metrics:
- accuracy
pipeline_tag: text-generation
tags:
- finance
---
# 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 finance base model (🤗we highly recommend switching to the [chat model](https://huggingface.co/AdaptLLM/finance-chat) for better response quality):
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("AdaptLLM/finance-LLM")
tokenizer = AutoTokenizer.from_pretrained("AdaptLLM/finance-LLM", use_fast=False)
# Put your input here:
user_input = '''Use this fact to answer the question: Title of each class Trading Symbol(s) Name of each exchange on which registered
Common Stock, Par Value $.01 Per Share MMM New York Stock Exchange
MMM Chicago Stock Exchange, Inc.
1.500% Notes due 2026 MMM26 New York Stock Exchange
1.750% Notes due 2030 MMM30 New York Stock Exchange
1.500% Notes due 2031 MMM31 New York Stock Exchange
Which debt securities are registered to trade on a national securities exchange under 3M's name as of Q2 of 2023?'''
# 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='finance'
# Specify any Huggingface model name (Not applicable to chat models)
MODEL='AdaptLLM/finance-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 sha256:4846c5fb7c4d3a4ffb2bf62b7a464df7ffe1fd8f97e06303cd38e74010ed4777
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 sha256:793a8ac9ac69535c038024abf4a72d0d3b392b7b575054ac9e0b04955db8e206
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:b6c7175cdc5fe3985d8811b2478173c598210cd176c3a426920b7c111d0900eb
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 sha256:1a23ccadc650a76ace47c012c2aa713765795e6bca851729edc3aabe1e7f5d40
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 sha256:31f41cf772cfe36cb9b02754c778fd72a797a1e945c5bf97921ee73ef921713f
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 sha256:5e65b6d3a5dcae8193bc9ff44670d86718ba580003007821f06f14d3fdf6d012
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 sha256:4a3548c0153c6130b86718852c286b2a9c233cef036ed1b2308e6db733c66a8b
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 sha256:6117bd51a6a457149037bc60499aa2a4ba210e77d53184d435a01449f18ab71e
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 sha256:96cc3eb7ea582e1971c9d93c79691744131da9bec906b99ca2454965f5854bc5
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:da46b9355b050711a3aae27b5f1345bb04e81892929df7a8f7e7befc48763386
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 sha256:5a5d286817a20456345f3b87ea8e590e1f07cc01b5e1d6f6f0ab7d65d3ac861e
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:ca2a80f06960db38eccff43b30f1485168de16d7e9e1d7a9bf6bfac0f186bcb6
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 sha256:9fa0f0ee3de505cad0d18a09cbde1f40eb715865b8fe40f6a0e97be5f8f017dc
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 sha256:55fbd2492141ed4eeb77b51564d77b623c45ca02759495879bf21881b6ce7b21
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 sha256:92e5e41ef3ab8696071729bb7b5bcb46969536562d4f31685850f4c6dd044180
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 sha256:5589ba606a5a7673d35cb6f49a2af692985bfe2cd0c756badc8912bd81f75e66
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:e09b82793af7905d86d3ac993538b480743c265603068fa875b2fb3e4b8bd1c9
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 sha256:4570a7b3fa8c6f6e1f1161f6caca00ced6be16bc86cf0f1d39a36d63c5a59ddd
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 sha256:95e73fd1c3f3704a0e1de51432984763ea3e0554207d5905fddebcb73a154149
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 sha256:20e90f4df4bb37effc1b0456c97169bdf1438c1276b13075425838d5a9de1716
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:a7536a86297238971b3ba628e9b75b0b4f988e92e00c5f80d8c4f2c15e762207
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 sha256:09a64e23a7241605deca8811529b1ed17bdefd4e2d221eee9beae128ad3f9908
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:d47fcaaabfd5d901f1ff025d9563e8348edc7fa22001c1100d4dfced506f3057
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 sha256:3de725f90522d10e426641755914aa5d53ceeb5edf7183a086a4745b9b48c161
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:f5da5f605b26ec6fa35d473d4d245d8097e8eebab8c6cdae218146398fc77bd6
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 sha256:7b0d937d747005d1833616c6d2a12bde211b1947fa75d83c1abcca9b77253e63
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:d580f4f3956ce21fe14557b8e354593685caf696122e0f7d6a5186de86d4da6a
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 sha256:1dfdfd9e7d76fd7a25a4011cd945a9d91af5ae80881defefd2c0981d92c90796
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 sha256:1cbe550ccf36e1b80f84f2b2570e911d36a8a24f4c3a0011127dc7d68fe2256b
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 sha256:1d93f4c24324d5a92d70527ded6ad368ac0cb862353c145b1c225944a61240f1
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:ebcedb4c10a89208f17fdbe3eeff86ab5961154bd9e192646440198324d2f34b
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 sha256:306d2f25a7a07d1e15855f3c4f71572f91dd0ffed915f6bfe7c35523b77ef5bf
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 sha256:65575a55c4f2669694e7a05fb44e275e42725e713181324e9a30ca59015271c9
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 sha256:1f497287f6d431d1c72c5a5e3d1f3d1b82182a8b8d561e4f43463af5ed8802aa
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 sha256:53aabd332380d30623bae7bc9089d35d252cce61ce55b6f98ca833045959058f
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 sha256:8e5602a29de104aff5b4c7adf77af212ee22c00abaa89fc1e46b62182f374f66
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:cb7eb657bffb1b1f8a598143dbbe9e805e787f5bf95e1bf2b6b136346c880d4d
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 sha256:13a06dfbb61c8b157f81cfb5dc82236342969d1b44de53133a258e6f7e2ada78
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:c2c7c2d0a137fa9f8b73d370af959ae1ff02683b142ec97f74dacba0eeb4bf46
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 sha256:93630213b38a35fd418a248e7a3ff93e09b7d64eaa455b6796d80b130e1f3e0f
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:a6fb4b9a03a5fd266571ab04de70a990931fcb2aedfd6e22bf8012b529774a07
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 sha256:5468c3de55161346f83b1d8a4e63764520f167a036d99f99acd998d3a4aa1a0d
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 sha256:76b094949c8d581b7f7cd2c6cd430a479ca3a2b6fb07ca1f9348cd9e45eaec5b
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 sha256:310f296ad260bd01ce5124430a7edd73002a313729d15f95cfd2bf64290b003e
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 sha256:1a4792ed0c72509c15d333022b83be14589f0cb8b41f2a6e3730a3ac5246ce7b
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 sha256:90821af788fea488ab2af37f4a7608f4a4daf12615169919955353d612ae9721
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:a4132626256e328619132b2f6228748ba4d33fa7a30c0bb0b4ba9b85eb3250af
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:aa0d079951f5684179147af0141d44880f1ead168593b8081b83b0cb94cf4b25
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 sha256:45ee7a48b4193bb2d1379076daf5901da1e8f27edeb008b2c3c310da4d68d0a3
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 sha256:03ecb710daf7a1d4fe57dd7e2db5cc7bc153c38b7c2c06fba9e24a32ff18502a
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 sha256:97d6eddecd48e542fd5a0c13b4249fda6ffcc1fd3ed6ac5709ad676ddf0f81a8
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 sha256:59a6846610a343e97cf7cb35310d40f015ceeff8f758be989ef0c6bddcef4678
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 sha256:16610b735ad1487465331c2fb59df272ba54f648edf6b15e767b09c2d5f62d06
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 sha256:5777cfd2fe8474ba80b1990250adf7d051437df18d15fc4e588d696578e30b34
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 sha256:358afb41d4fe2d38a70b7f635815e29a4fea49331ba53c18d9fdf5d416ac24b5
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:bc563420e8b1b6ec97cb09991a6586bd014158f6a67bd1ea7088a5ba0456c712
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 sha256:762d7cc907c0c72a82f477468e6a23bd498c7363b9a5aa3bfb52c51d4913472a
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:ff9a57224ef95e3764b6b8c9108aaa84080838eca338228065ab29ea3ba9c7fd
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 sha256:8116bfccc6972fd390993a9230c689d6274310b75536fd2a2d3f7be01c63c074
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 sha256:1db59894aa7ee782f06043998a00389f3dba6c163c91be8e877b5c07749016c7
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 sha256:983be7ab1625b1d6f65b3fa2d2911a2da9f30527e2f17c4a12c575393aefa8c8
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 sha256:135d40ca39798c4f84c7bd0ebeb9f4da36eca4f5f71987c6632985198de21897
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:d7b7b252d87399647a0e5b96355a1453157d6feda4e54b33d108383f52f3cd85
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 sha256:9309b218cc2fcbdc3d31979c597b44320efa1f8f95b9b6e8b162bb3674d96a37
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 sha256:2013662b1238417895d1a32023a207c7fb72ff92918072590cf8fc0157b5f6c1
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:a4b50941e07161050d7c8c090d0ec91f939010af3b5f1b446821c6297a111493
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>"
}