初始化项目，由ModelHub XC社区提供模型
Model: bavest/fin-llama-33b-merged Source: Original Platform
This commit is contained in:
ModelHub XC
34
.gitattributes
vendored
Normal file
34
.gitattributes
vendored
Normal file
@@ -0,0 +1,34 @@
|
||||
*.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
|
||||
*.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
|
||||
160
README.md
Normal file
160
README.md
Normal file
@@ -0,0 +1,160 @@
|
||||
---
|
||||
license: gpl
|
||||
datasets:
|
||||
- bavest/fin-llama-dataset
|
||||
tags:
|
||||
- finance
|
||||
- llm
|
||||
- llama
|
||||
- trading
|
||||
---
|
||||
|
||||
|
||||
# FIN-LLAMA
|
||||
|
||||
> Efficient Finetuning of Quantized LLMs for Finance
|
||||
|
||||
[Adapter Weights](https://huggingface.co/bavest/fin-llama-33b-merged)
|
||||
| [Dataset](https://huggingface.co/datasets/bavest/fin-llama-dataset)
|
||||
|
||||
## Installation
|
||||
|
||||
To load models in 4bits with transformers and bitsandbytes, you have to install accelerate and transformers from source
|
||||
and make sure you have the latest version of the bitsandbytes library (0.39.0).
|
||||
|
||||
```bash
|
||||
pip3 install -r requirements.txt
|
||||
```
|
||||
|
||||
### Other dependencies
|
||||
|
||||
If you want to finetune the model on a new instance. You could run
|
||||
the `setup.sh` to install the python and cuda package.
|
||||
|
||||
```bash
|
||||
bash scripts/setup.sh
|
||||
```
|
||||
|
||||
## Finetuning
|
||||
|
||||
```bash
|
||||
bash script/finetune.sh
|
||||
```
|
||||
|
||||
## Usage
|
||||
|
||||
Quantization parameters are controlled from the `BitsandbytesConfig`
|
||||
|
||||
- Loading in 4 bits is activated through `load_in_4bit`
|
||||
- The datatype used for the linear layer computations with `bnb_4bit_compute_dtype`
|
||||
- Nested quantization is activated through `bnb_4bit_use_double_quant`
|
||||
- The datatype used for qunatization is specified with `bnb_4bit_quant_type`. Note that there are two supported
|
||||
quantization datatypes `fp4` (four bit float) and `nf4` (normal four bit float). The latter is theoretically optimal
|
||||
for normally distributed weights and we recommend using `nf4`.
|
||||
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
|
||||
|
||||
pretrained_model_name_or_path = "bavest/fin-llama-33b-merge"
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
pretrained_model_name_or_path=pretrained_model_name_or_path,
|
||||
load_in_4bit=True,
|
||||
device_map='auto',
|
||||
torch_dtype=torch.bfloat16,
|
||||
quantization_config=BitsAndBytesConfig(
|
||||
load_in_4bit=True,
|
||||
bnb_4bit_compute_dtype=torch.bfloat16,
|
||||
bnb_4bit_use_double_quant=True,
|
||||
bnb_4bit_quant_type='nf4'
|
||||
),
|
||||
)
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(pretrained_model_name_or_path)
|
||||
|
||||
question = "What is the market cap of apple?"
|
||||
input = "" # context if needed
|
||||
|
||||
prompt = f"""
|
||||
A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's question.
|
||||
'### Instruction:\n{question}\n\n### Input:{input}\n""\n\n### Response:
|
||||
"""
|
||||
|
||||
input_ids = tokenizer.encode(prompt, return_tensors="pt").to('cuda:0')
|
||||
|
||||
with torch.no_grad():
|
||||
generated_ids = model.generate(
|
||||
input_ids,
|
||||
do_sample=True,
|
||||
top_p=0.9,
|
||||
temperature=0.8,
|
||||
max_length=128
|
||||
)
|
||||
|
||||
generated_text = tokenizer.decode(
|
||||
[el.item() for el in generated_ids[0]], skip_special_tokens=True
|
||||
)
|
||||
```
|
||||
|
||||
|
||||
## Dataset for FIN-LLAMA
|
||||
|
||||
The dataset is released under bigscience-openrail-m.
|
||||
You can find the dataset used to train FIN-LLAMA models on HF
|
||||
at [bavest/fin-llama-dataset](https://huggingface.co/datasets/bavest/fin-llama-dataset).
|
||||
|
||||
## Known Issues and Limitations
|
||||
|
||||
Here a list of known issues and bugs. If your issue is not reported here, please open a new issue and describe the
|
||||
problem.
|
||||
See [QLORA](https://github.com/artidoro/qlora) for any other limitations.
|
||||
|
||||
1. 4-bit inference is slow. Currently, our 4-bit inference implementation is not yet integrated with the 4-bit matrix
|
||||
multiplication
|
||||
2. Currently, using `bnb_4bit_compute_type='fp16'` can lead to instabilities.
|
||||
3. Make sure that `tokenizer.bos_token_id = 1` to avoid generation issues.
|
||||
|
||||
## Acknowledgements
|
||||
|
||||
We also thank Meta for releasing the LLaMA models without which this work would not have been possible.
|
||||
|
||||
This repo builds on the [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca)
|
||||
, [QLORA](https://github.com/artidoro/qlora), [Chinese-Guanaco](https://github.com/jianzhnie/Chinese-Guanaco/tree/main)
|
||||
and [LMSYS FastChat](https://github.com/lm-sys/FastChat) repos.
|
||||
|
||||
## License and Intended Use
|
||||
We release the resources associated with QLoRA finetuning in this repository under GLP3 license. In addition, we release the FIN-LLAMA model family for base LLaMA model sizes of 7B, 13B, 33B, and 65B. These models are intended for purposes in line with the LLaMA license and require access to the LLaMA models.
|
||||
|
||||
## Prompts
|
||||
### Act as an Accountant
|
||||
> I want you to act as an accountant and come up with creative ways to manage finances. You'll need to consider budgeting, investment strategies and risk management when creating a financial plan for your client. In some cases, you may also need to provide advice on taxation laws and regulations in order to help them maximize their profits. My first suggestion request is “Create a financial plan for a small business that focuses on cost savings and long-term investments".
|
||||
|
||||
## Paged Optimizer
|
||||
You can access the paged optimizer with the argument --optim paged_adamw_32bit
|
||||
|
||||
## Cite
|
||||
|
||||
```tex
|
||||
@misc{Fin-LLAMA,
|
||||
author = {William Todt, Ramtin Babaei, Pedram Babaei},
|
||||
title = {Fin-LLAMA: Efficient Finetuning of Quantized LLMs for Finance},
|
||||
year = {2023},
|
||||
publisher = {GitHub},
|
||||
journal = {GitHub repository},
|
||||
howpublished = {\url{https://github.com/Bavest/fin-llama}},
|
||||
}
|
||||
```
|
||||
# [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_bavest__fin-llama-33b-merged)
|
||||
|
||||
| Metric | Value |
|
||||
|-----------------------|---------------------------|
|
||||
| Avg. | 51.76 |
|
||||
| ARC (25-shot) | 65.02 |
|
||||
| HellaSwag (10-shot) | 86.2 |
|
||||
| MMLU (5-shot) | 58.73 |
|
||||
| TruthfulQA (0-shot) | 49.75 |
|
||||
| Winogrande (5-shot) | 80.03 |
|
||||
| GSM8K (5-shot) | 16.22 |
|
||||
| DROP (3-shot) | 6.36 |
|
||||
24
config.json
Normal file
24
config.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"_name_or_path": "huggyllama/llama-30b",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 6656,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 17920,
|
||||
"max_position_embeddings": 2048,
|
||||
"max_sequence_length": 2048,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 52,
|
||||
"num_hidden_layers": 60,
|
||||
"pad_token_id": 0,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.29.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.29.2"
|
||||
}
|
||||
3
pytorch_model-00001-of-00007.bin
Normal file
3
pytorch_model-00001-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:66de0175d26e03577bc0cf6ba2d95b0ae5419dd2c9844fdffe665bb442c04583
|
||||
size 9818324627
|
||||
3
pytorch_model-00002-of-00007.bin
Normal file
3
pytorch_model-00002-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0f31cd96e3b5dbccc3ddd6f09589ff00665be421083a1e7222e7d777285ae370
|
||||
size 9958102743
|
||||
3
pytorch_model-00003-of-00007.bin
Normal file
3
pytorch_model-00003-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8a7fecb7969fe8247f6e004035e583c2950f9237a7cfe93b66574454cd147746
|
||||
size 9896734715
|
||||
3
pytorch_model-00004-of-00007.bin
Normal file
3
pytorch_model-00004-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:540022be38820930e843d83d9ab7b8deb8f7b6b1956ceac8683c8cb42f94d8ed
|
||||
size 9869470481
|
||||
3
pytorch_model-00005-of-00007.bin
Normal file
3
pytorch_model-00005-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2cd9aacf54b1ceae630c45376b023926c686433573f1ea7965cbd7fb0d94e26b
|
||||
size 9869470445
|
||||
3
pytorch_model-00006-of-00007.bin
Normal file
3
pytorch_model-00006-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fe339e10b8ad78299472cbc857c51714283422959359b3d88c7c9a7ea577fddf
|
||||
size 9958102743
|
||||
3
pytorch_model-00007-of-00007.bin
Normal file
3
pytorch_model-00007-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2b32b0d7c85738a330addce5b7d5a1e8a99399006dfb5e7a01e27a8f3b3b08a8
|
||||
size 5687903281
|
||||
610
pytorch_model.bin.index.json
Normal file
610
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,610 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 65057902592
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.32.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.33.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.34.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.35.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.38.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.39.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.40.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.40.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.40.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.40.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.40.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.40.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.40.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.40.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.40.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.40.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.41.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.41.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.41.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.41.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.41.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.41.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.41.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.41.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.41.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.41.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.42.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.42.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.42.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.42.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.42.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.42.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.42.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.42.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.42.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.42.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.43.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.43.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.43.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.43.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.43.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.43.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.43.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.43.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.43.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.43.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.44.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.44.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.44.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.44.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.44.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.44.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.44.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.44.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.44.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.44.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.45.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.45.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.45.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.45.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.45.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.45.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.45.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.45.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.45.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.45.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.46.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.46.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.46.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.46.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.46.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.46.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.46.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.46.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.46.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.46.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.47.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.47.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.47.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.47.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.47.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.47.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.47.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.47.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.47.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.47.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.48.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.48.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.48.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.48.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.48.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.48.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.48.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.48.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.48.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.48.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.49.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.49.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.49.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.49.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.49.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.49.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.49.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.49.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.49.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.49.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.50.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.50.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.50.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.50.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.50.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.50.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.50.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.50.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.50.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.50.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.51.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.51.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.51.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.51.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.51.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.51.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.51.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.51.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.51.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.51.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.52.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.52.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.52.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.52.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.52.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.52.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.52.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.52.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.52.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.52.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.53.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.53.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.53.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.53.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.53.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.53.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.53.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.53.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.53.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.53.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.54.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.54.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.54.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.54.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.54.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.54.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.54.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.54.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.54.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.54.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.55.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.55.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.55.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.55.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.55.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.55.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.55.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.55.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.55.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.55.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.56.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.56.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.56.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.56.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.56.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.56.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.56.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.56.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.56.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.56.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.57.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.57.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.57.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.57.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.57.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.57.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.57.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.57.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.57.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.57.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.58.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.58.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.58.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.58.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.58.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.58.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.58.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.58.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.58.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.58.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.59.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.59.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.59.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.59.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.59.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.59.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.59.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.59.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.59.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.59.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.norm.weight": "pytorch_model-00007-of-00007.bin"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"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
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
93385
tokenizer.json
Normal file
93385
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
33
tokenizer_config.json
Normal file
33
tokenizer_config.json
Normal file
@@ -0,0 +1,33 @@
|
||||
{
|
||||
"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
|
||||
},
|
||||
"model_max_length": 2048,
|
||||
"pad_token": null,
|
||||
"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