初始化项目，由ModelHub XC社区提供模型
Model: Wanfq/FuseLLM-7B Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
||||
*.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
|
||||
assets/fig_2.png filter=lfs diff=lfs merge=lfs -text
|
||||
assets/fig_5.png filter=lfs diff=lfs merge=lfs -text
|
||||
494
README.md
Normal file
494
README.md
Normal file
@@ -0,0 +1,494 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
license: apache-2.0
|
||||
library_name: transformers
|
||||
tags:
|
||||
- llama
|
||||
- open-llama
|
||||
- mpt
|
||||
- model-fusion
|
||||
- fusellm
|
||||
pipeline_tag: text-generation
|
||||
model-index:
|
||||
- name: FuseLLM-7B
|
||||
results:
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: AI2 Reasoning Challenge (25-Shot)
|
||||
type: ai2_arc
|
||||
config: ARC-Challenge
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 25
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 53.24
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Wanfq/FuseLLM-7B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: HellaSwag (10-Shot)
|
||||
type: hellaswag
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 10
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 78.72
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Wanfq/FuseLLM-7B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: MMLU (5-Shot)
|
||||
type: cais/mmlu
|
||||
config: all
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 47.93
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Wanfq/FuseLLM-7B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: TruthfulQA (0-shot)
|
||||
type: truthful_qa
|
||||
config: multiple_choice
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 0
|
||||
metrics:
|
||||
- type: mc2
|
||||
value: 38.17
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Wanfq/FuseLLM-7B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: Winogrande (5-shot)
|
||||
type: winogrande
|
||||
config: winogrande_xl
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 74.03
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Wanfq/FuseLLM-7B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: GSM8k (5-shot)
|
||||
type: gsm8k
|
||||
config: main
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 14.33
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Wanfq/FuseLLM-7B
|
||||
name: Open LLM Leaderboard
|
||||
---
|
||||
<p align="center" width="100%">
|
||||
</p>
|
||||
|
||||
<div id="top" align="center">
|
||||
|
||||
<p style="font-size: 32px; font-weight: bold;">Knowledge Fusion of Large Language Models</p>
|
||||
|
||||
|
||||
<h4> |<a href="https://arxiv.org/abs/2401.10491"> 📑 Paper </a> |
|
||||
<a href="https://huggingface.co/FuseAI"> 🤗 Huggingface Repo </a> |
|
||||
<a href="https://github.com/fanqiwan/FuseLLM"> 🐱 Github Repo </a> |
|
||||
</h4>
|
||||
|
||||
<!-- **Authors:** -->
|
||||
|
||||
_**Fanqi Wan<sup>†</sup>, Xinting Huang<sup>‡</sup>, Deng Cai<sup>‡</sup>, Xiaojun Quan<sup>†</sup>, Wei Bi<sup>‡</sup>, Shuming Shi<sup>‡</sup>**_
|
||||
|
||||
|
||||
<!-- **Affiliations:** -->
|
||||
|
||||
|
||||
_<sup>†</sup> Sun Yat-sen University,
|
||||
<sup>‡</sup> Tencent AI Lab_
|
||||
|
||||
| Model | BBH | ARC-easy | ARC-challenge | BoolQ | HellaSwag | OpenBookQA |
|
||||
|----------------------------------------------------------|-------|----------|---------------|-------|-----------|------------|
|
||||
| OpenLLaMA-7B | 33.87 | 69.70 | 41.38 | 72.29 | 74.53 | 41.00 |
|
||||
| MPT-7B | 33.38 | 70.12 | 42.15 | 74.74 | 76.25 | 42.40 |
|
||||
| Llama-2-7B | 39.70 | 74.58 | 46.33 | 77.71 | 76.00 | 44.20 |
|
||||
| Llama-2-CLM-7B | 40.44 | 74.54 | 46.50 | 76.88 | 76.57 | 44.80 |
|
||||
| 🤗 [FuseLLM-7B](https://huggingface.co/Wanfq/FuseLLM-7B) | 41.75 | 75.04 | 47.44 | 78.13 | 76.78 | 45.40 |
|
||||
|
||||
|
||||
| Model | MultiPL-E | TrivialQA | DROP | LAMBADA | IWSLT2017 | SciBench |
|
||||
|----------------------------------------------------------|-----------|-----------|-------|---------|-----------|----------|
|
||||
| OpenLLaMA-7B | 18.11 | 39.96 | 22.31 | 70.31 | 5.51 | 0.68 |
|
||||
| MPT-7B | 17.26 | 28.89 | 23.54 | 70.08 | 5.49 | 0.88 |
|
||||
| Llama-2-7B | 14.63 | 52.46 | 27.25 | 73.28 | 6.48 | 0.14 |
|
||||
| Llama-2-CLM-7B | 14.83 | 53.14 | 28.51 | 73.45 | 6.91 | 0.94 |
|
||||
| 🤗 [FuseLLM-7B](https://huggingface.co/Wanfq/FuseLLM-7B) | 15.56 | 54.49 | 28.97 | 73.72 | 6.75 | 1.65 |
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
## News
|
||||
- **Jan 22, 2024:** 🔥 We release [FuseLLM-7B](https://huggingface.co/Wanfq/FuseLLM-7B), which is the fusion of three open-source foundation LLMs with distinct architectures, including [Llama-2-7B](https://huggingface.co/meta-llama/Llama-2-7b-hf), [OpenLLaMA-7B](https://huggingface.co/openlm-research/open_llama_7b_v2), and [MPT-7B](https://huggingface.co/mosaicml/mpt-7b).
|
||||
|
||||
|
||||
## WIP
|
||||
|
||||
| Source LLMs | Target LLM |
|
||||
|------------------------------------------------------|-------------------|
|
||||
| Mixtral-8x7B-v0.1, SOLAR-10.7B-v1.0, Mistral-7B-v0.1 | Mistral-7B-v0.1 |
|
||||
| Mixtral-8x7B-v0.1, SOLAR-10.7B-v1.0, Mistral-7B-v0.1 | SOLAR-10.7B-v1.0 |
|
||||
| Mixtral-8x7B-v0.1, SOLAR-10.7B-v1.0, Mistral-7B-v0.1 | Mixtral-8x7B-v0.1 |
|
||||
|
||||
## Contents
|
||||
|
||||
- [Overview](#overview)
|
||||
- [Model Release](#model-release)
|
||||
- [Quick Start](#quick-start)
|
||||
- [Data Construction](#data-construction)
|
||||
- [Training](#training)
|
||||
- [Evaluation](#evaluation)
|
||||
- [Citation](#citation)
|
||||
|
||||
## Overview
|
||||
|
||||
In this study, we explore the realm of knowledge fusion for LLMs to create a unified model that combines the capabilities and distinctive strengths of multiple structurally diverse LLMs. To achieve this, we introduce FuseLLM, which first leverages the generative distributions of these source LLMs to externalize both their collective knowledge and individual strengths, and subsequently transfer them to the target LLM through lightweight continual training.
|
||||
|
||||
Unlike model ensemble approaches that require the **parallel deployment of multiple LLMs**, or weight merging techniques that are typically **limited to LLMs with identical architectures**, FuseLLM is designed to support **the fusion of multiple LLMs with diverse architectures into a more potent LLM**. By explicitly transferring their knowledge and capabilities to a single target LLM, FuseLLM offers a powerful and flexible solution for the knowledge fusion of LLMs.
|
||||
|
||||
<p align="center">
|
||||
<img src="./assets/fig_1.png" width="95%"> <br>
|
||||
</p>
|
||||
|
||||
|
||||
## Model Release
|
||||
|
||||
We release the FuseLLM-7B on 🤗 [Huggingface Models](https://huggingface.co/models?sort=trending&search=FuseLLM), which is the fusion of three popular open-source LLMs that possess distinct architectures and functionalities: [Llama-2-7B](https://huggingface.co/meta-llama/Llama-2-7b-hf), [OpenLLaMA-7B](https://huggingface.co/openlm-research/open_llama_7b_v2), and [MPT-7B](https://huggingface.co/mosaicml/mpt-7b).
|
||||
|
||||
Here are the evaluation results of FuseLLM.
|
||||
|
||||
### General Reasoning & Commonsense Reasoning
|
||||
|
||||
We first show the performance of FuseLLM on Big-Bench Hard and CommonSense benchmarks, which evaluate the general reasoning and commonsense reasoning abilities respectively.
|
||||
|
||||
<p align="center">
|
||||
<img src="./assets/fig_4.png" width="95%"> <br>
|
||||
</p>
|
||||
|
||||
### Code Generation & Text Generation
|
||||
|
||||
We then evaluate FuseLLM on MultiPL-E, which is a multilingual programming benchmark to assess the code generation performance. We also conduct experiments on several text generation benchmarks, including TrivialQA (question-answering), DROP (reading comprehension), LAMBADA (content analysis), IWSLT2017 (machine translation), and SCIBench (theorem application).
|
||||
|
||||
<p align="center">
|
||||
<img src="./assets/fig_5.png" width="95%"> <br>
|
||||
</p>
|
||||
|
||||
### Instruction Following
|
||||
|
||||
FuseLLM is also applicable to the fusion of instruction-tuned LLMs. We further evaluate the Vicuna Benchmark, which assesses the instruction following ability.
|
||||
|
||||
<p align="center">
|
||||
<img src="./assets/fig_6.png" width="50%"> <br>
|
||||
</p>
|
||||
|
||||
### FuseLLM vs. Knowledge Distillation
|
||||
|
||||
As knowledge distillation is also a method for enhancing the performance of LLMs by utilizing representations, we compare FuseLLM with Llama-2 KD, which is distilled from Llama-2 13B.
|
||||
|
||||
<p align="center">
|
||||
<img src="./assets/fig_7.png" width="50%"> <br>
|
||||
</p>
|
||||
|
||||
### FuseLLM vs. Model Ensemble & Weight Merging
|
||||
|
||||
To compare FuseLLM with existing fusion methods (such as model ensemble and weight merging), we simulate scenarios to ensure model fusion with an identical structure where multiple source LLMs are derived from the same base model but are continually trained on different corpus. We then test the perplexity of these fusion methods on different benchmarks.
|
||||
|
||||
|
||||
<p align="center">
|
||||
<img src="./assets/fig_8.png" width="50%"> <br>
|
||||
</p>
|
||||
|
||||
## Quick Start
|
||||
|
||||
### Setup
|
||||
|
||||
We use `python 3.9` in this project.
|
||||
|
||||
Then, we have to install all the libraries listed in `requirements.txt`.
|
||||
|
||||
```bash
|
||||
pip install -r requirements.txt
|
||||
```
|
||||
|
||||
### Usage
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
tokenizer = AutoTokenizer.from_pretrained("Wanfq/FuseLLM-7B", use_fast=False)
|
||||
model = AutoModelForCausalLM.from_pretrained("Wanfq/FuseLLM-7B", torch_dtype="auto")
|
||||
model.cuda()
|
||||
inputs = tokenizer("<your text here>", return_tensors="pt").to(model.device)
|
||||
tokens = model.generate(
|
||||
**inputs,
|
||||
max_new_tokens=512,
|
||||
temperature=0.6,
|
||||
top_p=0.9,
|
||||
do_sample=True,
|
||||
)
|
||||
print(tokenizer.decode(tokens[0], skip_special_tokens=True))
|
||||
```
|
||||
|
||||
We also find `Exllama v2 Quantizations` version on [FuseLLM-7B-exl2](https://huggingface.co/bartowski/FuseLLM-7B-exl2), it uses [ExLlamaV2 v0.0.11](https://github.com/turboderp/exllamav2/releases/tag/v0.0.11) for quantization.
|
||||
|
||||
## Data Construction
|
||||
|
||||
We use the [MiniPile](https://huggingface.co/datasets/JeanKaddour/minipile) dataset for continual training.
|
||||
|
||||
Here we show the scripts to obtain representations from multiple LLMs for model fusion.
|
||||
|
||||
1. Split long text
|
||||
|
||||
```bash
|
||||
python ./src/utils/split_long_text.py \
|
||||
--base_model_name_or_path "<path_to_llama_2_7b>" \
|
||||
--blending_model_name_or_path "<path_to_open_llama_7b_v2>" \
|
||||
--another_blending_model_name_or_path "<path_to_mpt_7b>" \
|
||||
--dataset "<path_to_minipile>" \
|
||||
--dataset_save_dir "<path_to_minipile_split>" \
|
||||
--cache_dir "<path_to_cache_dir>" \
|
||||
--block_size 2048 \
|
||||
--preprocessing_num_workers 80
|
||||
```
|
||||
|
||||
2. Get representations for each LLM
|
||||
|
||||
```bash
|
||||
# We split the dataset into 8 splits, then process each split on a GPU.
|
||||
# Please run this script for llama_2_7b, open_llama_7b_v2, and mpt_7b.
|
||||
for i in {0..7}; do
|
||||
export CUDA_VISIBLE_DEVICES=${i}
|
||||
python ./src/utils/forward_for_logits.py \
|
||||
--model_name_or_path "<path_to_each_model>" \
|
||||
--dataset "<path_to_minipile_split>" \
|
||||
--dataset_save_dir "${i}_8_<path_to_minipile_split_each_model_representation>" \
|
||||
--dataset_split_num 8 \
|
||||
--dataset_index ${i} \
|
||||
--cache_dir "<path_to_cache_dir>" \
|
||||
--model_max_length 2048 \
|
||||
--training_mode full \
|
||||
--load_in_half bf16 \
|
||||
--batch_size 8 \
|
||||
--preprocessing_num_workers 80 \
|
||||
--top_k_logits 10 \
|
||||
--save_per_token_metric 2>&1 > "${i}_8_<path_to_log_file>" 2>&1 &
|
||||
unset CUDA_VISIBLE_DEVICES
|
||||
sleep 30
|
||||
done
|
||||
|
||||
wait
|
||||
```
|
||||
|
||||
3. Align representations from different LLMs
|
||||
|
||||
```bash
|
||||
# Get vocab mapping from different LLMs.
|
||||
|
||||
# llama_2_7b <-> open_llama_7b_v2
|
||||
python ./src/utils/vocab_mapping.py \
|
||||
--base_model_name_or_path "<path_to_llama_2_7b>" \
|
||||
--blending_model_name_or_path "<path_to_open_llama_7b_v2>" \
|
||||
--dataset_dir "<path_to_minipile_split>" \
|
||||
--vocab_mapping_save_dir "<path_to_llama_2_7b_open_llama_7b_v2_vocab_mapping>" \
|
||||
--cache_dir "<path_to_cache_dir>" \
|
||||
--model_max_length 2048 \
|
||||
--vocab_mapping_type "default" \
|
||||
--num_process 1
|
||||
|
||||
# llama_2_7b <-> mpt_7b
|
||||
python ./src/utils/vocab_mapping.py \
|
||||
--base_model_name_or_path "<path_to_llama_2_7b>" \
|
||||
--blending_model_name_or_path "<path_to_mpt_7b>" \
|
||||
--dataset_dir "<path_to_minipile_split>" \
|
||||
--vocab_mapping_save_dir "<path_to_llama_2_7b_mpt_7b_vocab_mapping>" \
|
||||
--cache_dir "<path_to_cache_dir>" \
|
||||
--model_max_length 2048 \
|
||||
--vocab_mapping_type "default" \
|
||||
--num_process 1
|
||||
```
|
||||
|
||||
```bash
|
||||
# Align representations from different LLMs.
|
||||
|
||||
# llama_2_7b <-> open_llama_7b_v2
|
||||
for i in {0..7}; do
|
||||
python ./src/utils/token_alignment.py \
|
||||
--base_model_name_or_path "<path_to_llama_2_7b>" \
|
||||
--blending_model_name_or_path "<path_to_open_llama_7b_v2>" \
|
||||
--base_dataset_dir "${i}_8_<path_to_minipile_split_llama_2_7b_representation>" \
|
||||
--blending_dataset_dir "${i}_8_<path_to_minipile_split_open_llama_7b_v2_representation>" \
|
||||
--dataset_save_dir "${i}_8_<path_to_minipile_split_llama_2_7b_open_llama_7b_v2_aligned_representation>" \
|
||||
--cache_dir "<path_to_cache_dir>" \
|
||||
--model_max_length 2048 \
|
||||
--preprocessing_num_workers 80 \
|
||||
--batch_size 100 \
|
||||
--blending_model_index 0 \
|
||||
--vocab_align_type "soft" \
|
||||
--vocab_mapping_save_dir "<path_to_llama_2_7b_open_llama_7b_v2_vocab_mapping>" \
|
||||
--metric_level "sequence"
|
||||
done
|
||||
|
||||
# llama_2_7b <-> mpt_7b
|
||||
for i in {0..7}; do
|
||||
python ./src/utils/token_alignment.py \
|
||||
--base_model_name_or_path "<path_to_llama_2_7b>" \
|
||||
--blending_model_name_or_path "<path_to_mpt_7b>" \
|
||||
--base_dataset_dir "${i}_8_<path_to_minipile_split_llama_2_7b_open_llama_7b_v2_aligned_representation>" \
|
||||
--blending_dataset_dir "${i}_8_<path_to_minipile_split_mpt_7b_representation>" \
|
||||
--dataset_save_dir "${i}_8_<path_to_minipile_split_llama_2_7b_open_llama_7b_v2_mpt_7b_aligned_representation>" \
|
||||
--cache_dir "<path_to_cache_dir>" \
|
||||
--model_max_length 2048 \
|
||||
--preprocessing_num_workers 80 \
|
||||
--batch_size 100 \
|
||||
--blending_model_index 1 \
|
||||
--vocab_align_type "soft" \
|
||||
--vocab_mapping_save_dir "<path_to_llama_2_7b_mpt_7b_vocab_mapping>" \
|
||||
--metric_level "sequence"
|
||||
done
|
||||
```
|
||||
|
||||
4. Packing all features to speed up training.
|
||||
|
||||
```bash
|
||||
for i in {0..7}; do
|
||||
python3 ./src/utils/packing.py \
|
||||
--dataset_dir "${i}_8_<path_to_minipile_split_llama_2_7b_open_llama_7b_v2_mpt_7b_aligned_representation>" \
|
||||
--dataset_save_dir "${i}_8_<path_to_miniplie_fusellm_processed>" \
|
||||
--cache_dir "<path_to_cache_dir>" \
|
||||
--model_max_length 2048 \
|
||||
--preprocessing_num_workers 80 \
|
||||
--batch_size 1000 \
|
||||
--metric_level "sequence"
|
||||
```
|
||||
|
||||
The final processed data is at `${i}_8_<path_to_miniplie_fusellm_processed>`, where `i in {0..7}`.
|
||||
|
||||
## Training
|
||||
|
||||
Here, we show the script for FuseLLM training.
|
||||
|
||||
```bash
|
||||
export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
|
||||
|
||||
deepspeed --master_port=20001 ./src/train.py \
|
||||
--training_mode full \
|
||||
--deepspeed ./config/zero_stage2_config.json \
|
||||
--model_name_or_path "<path_to_llama_2_7b>" \
|
||||
--output_dir "<path_to_save_fusellm_7b>" \
|
||||
--model_max_length 2048 \
|
||||
--logging_steps 1 \
|
||||
--save_strategy steps \
|
||||
--save_steps 500 \
|
||||
--save_total_limit 1 \
|
||||
--evaluation_strategy steps \
|
||||
--per_device_eval_batch_size 1 \
|
||||
--logging_strategy steps \
|
||||
--do_train \
|
||||
--do_eval \
|
||||
--bf16 True \
|
||||
--tf32 True \
|
||||
--warmup_ratio 0.008 \
|
||||
--lr_scheduler_type cosine \
|
||||
--dataset_name "0_8_<path_to_miniplie_fusellm_processed>,1_8_<path_to_miniplie_fusellm_processed>,2_8_<path_to_miniplie_fusellm_processed>,3_8_<path_to_miniplie_fusellm_processed>,4_8_<path_to_miniplie_fusellm_processed>,5_8_<path_to_miniplie_fusellm_processed>,6_8_<path_to_miniplie_fusellm_processed>,7_8_<path_to_miniplie_fusellm_processed>" \
|
||||
--per_device_train_batch_size 1 \
|
||||
--gradient_accumulation_steps 16 \
|
||||
--num_train_epochs 1 \
|
||||
--eval_steps 500 \
|
||||
--optim adamw_torch \
|
||||
--adam_beta1 0.9 \
|
||||
--adam_beta2 0.95 \
|
||||
--learning_rate 1e-5 \
|
||||
--weight_decay 0.1 \
|
||||
--max_grad_norm 1.0 \
|
||||
--seed 42 \
|
||||
--gradient_checkpointing True \
|
||||
--use_flash_attn True \
|
||||
--report_to tensorboard \
|
||||
--do_distill \
|
||||
--distill_with_ref_model True \
|
||||
--distill_with_aligned_model_0 True \
|
||||
--distill_with_aligned_model_1 True \
|
||||
--distill_loss_type "ce" \
|
||||
--distill_teacher_temperature 1.0 \
|
||||
--lm_loss_weight 0.9 \
|
||||
--distill_greater_as_gt True \
|
||||
--distill_greater_as_gt_type "hard" \
|
||||
--dataloader_num_workers 10 \
|
||||
--remove_unused_columns False 2>&1 | tee "<path_to_log_file>"
|
||||
```
|
||||
|
||||
## Evaluation
|
||||
|
||||
The evaluation code we used in our evaluation are list as follows:
|
||||
|
||||
- [Big-Bench Hard](https://github.com/allenai/open-instruct/tree/main/eval)
|
||||
- [CommonSense: ARC-easy, ARC-challenge, BoolQ, HellaSwag, OpenBookQA](https://github.com/EleutherAI/lm-evaluation-harness/releases/tag/v0.3.0)
|
||||
- [MultiPL-E](https://github.com/bigcode-project/bigcode-evaluation-harness)
|
||||
- [Text Generation: TrivialQA, DROP, LAMBADA, IWSLT2017, SciBench](https://github.com/open-compass/opencompass)
|
||||
- [Vicuna Bench](https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge)
|
||||
|
||||
## Citation
|
||||
|
||||
If you find this work is relevant with your research or applications, please feel free to cite our work!
|
||||
```
|
||||
@inproceedings{wan2024knowledge,
|
||||
title={Knowledge Fusion of Large Language Models},
|
||||
author={Fanqi Wan and Xinting Huang and Deng Cai and Xiaojun Quan and Wei Bi and Shuming Shi},
|
||||
booktitle={The Twelfth International Conference on Learning Representations},
|
||||
year={2024},
|
||||
url={https://openreview.net/pdf?id=jiDsk12qcz}
|
||||
}
|
||||
```
|
||||
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
||||
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Wanfq__FuseLLM-7B)
|
||||
|
||||
| Metric |Value|
|
||||
|---------------------------------|----:|
|
||||
|Avg. |51.07|
|
||||
|AI2 Reasoning Challenge (25-Shot)|53.24|
|
||||
|HellaSwag (10-Shot) |78.72|
|
||||
|MMLU (5-Shot) |47.93|
|
||||
|TruthfulQA (0-shot) |38.17|
|
||||
|Winogrande (5-shot) |74.03|
|
||||
|GSM8k (5-shot) |14.33|
|
||||
|
||||
BIN
assets/fig_1.png
Normal file
BIN
assets/fig_1.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 486 KiB |
3
assets/fig_2.png
Normal file
3
assets/fig_2.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d94ee154bcabd793828e903d932105643831fa2cc2becfb7cc531ada059c0be3
|
||||
size 1042342
|
||||
BIN
assets/fig_3.png
Normal file
BIN
assets/fig_3.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 161 KiB |
BIN
assets/fig_4.png
Normal file
BIN
assets/fig_4.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 572 KiB |
3
assets/fig_5.png
Normal file
3
assets/fig_5.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:986cff79cfc12f1443c014fcd0227f58b67013b19f55da4e75f79cdcf0cfcc4a
|
||||
size 1100285
|
||||
BIN
assets/fig_6.png
Normal file
BIN
assets/fig_6.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 90 KiB |
BIN
assets/fig_7.png
Normal file
BIN
assets/fig_7.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 204 KiB |
BIN
assets/fig_8.png
Normal file
BIN
assets/fig_8.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 158 KiB |
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"_name_or_path": "meta-llama/Llama-2-7b-hf",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 32,
|
||||
"pad_token_id": 0,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.31.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
10
generation_config.json
Normal file
10
generation_config.json
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"bos_token_id": 1,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 0,
|
||||
"temperature": 0.6,
|
||||
"max_length": 4096,
|
||||
"top_p": 0.9,
|
||||
"transformers_version": "4.31.0.dev0"
|
||||
}
|
||||
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:67765c21add84368c269448c2c7ebad188289846e49ef092161eb790bc677315
|
||||
size 9976576392
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6dc58b22cff243ff0d4f9bd73478efaf0702d2579ee05f66bdbf6cce3218e129
|
||||
size 3500296504
|
||||
330
model.safetensors.index.json
Normal file
330
model.safetensors.index.json
Normal file
@@ -0,0 +1,330 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 13476835328
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00002-of-00002.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.norm.weight": "model-00002-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
3
pytorch_model-00001-of-00002.bin
Normal file
3
pytorch_model-00001-of-00002.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a3516a9628fe1392925c2a9ba7a687c05f0f9d9594464c53c3a15068b8fbdfb1
|
||||
size 9976631486
|
||||
3
pytorch_model-00002-of-00002.bin
Normal file
3
pytorch_model-00002-of-00002.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ace81e96aec0f43969699f1002868fcbea84a61de346dbf31b17dab1418e1bb6
|
||||
size 3500314451
|
||||
330
pytorch_model.bin.index.json
Normal file
330
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,330 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 13476835328
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.norm.weight": "pytorch_model-00002-of-00002.bin"
|
||||
}
|
||||
}
|
||||
24
special_tokens_map.json
Normal file
24
special_tokens_map.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<unk>",
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
35
tokenizer_config.json
Normal file
35
tokenizer_config.json
Normal file
@@ -0,0 +1,35 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"bos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"legacy": false,
|
||||
"model_max_length": 2048,
|
||||
"pad_token": null,
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user