初始化项目，由ModelHub XC社区提供模型
Model: mrm8488/falcoder-7b Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
114
README.md
Normal file
114
README.md
Normal file
@@ -0,0 +1,114 @@
|
||||
---
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
- code
|
||||
- coding
|
||||
model-index:
|
||||
- name: FalCoder
|
||||
results: []
|
||||
license: apache-2.0
|
||||
language:
|
||||
- code
|
||||
thumbnail: https://huggingface.co/mrm8488/falcoder-7b/resolve/main/falcoder.png
|
||||
datasets:
|
||||
- HuggingFaceH4/CodeAlpaca_20K
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
<div style="text-align:center;width:250px;height:250px;">
|
||||
<img src="https://huggingface.co/mrm8488/falcoder-7b/resolve/main/falcoder.png" alt="falcoder logo"">
|
||||
</div>
|
||||
|
||||
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
||||
should probably proofread and complete it, then remove this comment. -->
|
||||
|
||||
# FalCoder 🦅👩💻
|
||||
**Falcon-7b** fine-tuned on the **CodeAlpaca 20k instructions dataset** by using the method **QLoRA** with [PEFT](https://github.com/huggingface/peft) library.
|
||||
|
||||
## Model description 🧠
|
||||
|
||||
[Falcon 7B](https://huggingface.co/tiiuae/falcon-7b)
|
||||
|
||||
|
||||
## Training and evaluation data 📚
|
||||
|
||||
[CodeAlpaca_20K](https://huggingface.co/datasets/HuggingFaceH4/CodeAlpaca_20K): contains 20K instruction-following data used for fine-tuning the Code Alpaca model.
|
||||
|
||||
|
||||
### Training hyperparameters ⚙
|
||||
|
||||
TBA
|
||||
|
||||
### Training results 🗒️
|
||||
|
||||
| Step | Training Loss | Validation Loss |
|
||||
|------|---------------|-----------------|
|
||||
| 100 | 0.798500 | 0.767996 |
|
||||
| 200 | 0.725900 | 0.749880 |
|
||||
| 300 | 0.669100 | 0.748029 |
|
||||
| 400 | 0.687300 | 0.742342 |
|
||||
| 500 | 0.579900 | 0.736735 |
|
||||
|
||||
|
||||
|
||||
### Example of usage 👩💻
|
||||
```py
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer, AutoTokenizer
|
||||
|
||||
model_id = "mrm8488/falcoder-7b"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained(model_id).to("cuda")
|
||||
|
||||
def generate(
|
||||
instruction,
|
||||
max_new_tokens=128,
|
||||
temperature=0.1,
|
||||
top_p=0.75,
|
||||
top_k=40,
|
||||
num_beams=4,
|
||||
**kwargs
|
||||
):
|
||||
prompt = instruction + "\n### Solution:\n"
|
||||
print(prompt)
|
||||
inputs = tokenizer(prompt, return_tensors="pt")
|
||||
input_ids = inputs["input_ids"].to("cuda")
|
||||
attention_mask = inputs["attention_mask"].to("cuda")
|
||||
generation_config = GenerationConfig(
|
||||
temperature=temperature,
|
||||
top_p=top_p,
|
||||
top_k=top_k,
|
||||
num_beams=num_beams,
|
||||
**kwargs,
|
||||
)
|
||||
with torch.no_grad():
|
||||
generation_output = model.generate(
|
||||
input_ids=input_ids,
|
||||
attention_mask=attention_mask,
|
||||
generation_config=generation_config,
|
||||
return_dict_in_generate=True,
|
||||
output_scores=True,
|
||||
max_new_tokens=max_new_tokens,
|
||||
early_stopping=True
|
||||
)
|
||||
s = generation_output.sequences[0]
|
||||
output = tokenizer.decode(s)
|
||||
return output.split("### Solution:")[1].lstrip("\n")
|
||||
|
||||
instruction = "Design a class for representing a person in Python."
|
||||
print(generate(instruction))
|
||||
```
|
||||
|
||||
### Citation
|
||||
```
|
||||
@misc {manuel_romero_2023,
|
||||
author = { {Manuel Romero} },
|
||||
title = { falcoder-7b (Revision e061237) },
|
||||
year = 2023,
|
||||
url = { https://huggingface.co/mrm8488/falcoder-7b },
|
||||
doi = { 10.57967/hf/0789 },
|
||||
publisher = { Hugging Face }
|
||||
}
|
||||
```
|
||||
33
config.json
Normal file
33
config.json
Normal file
@@ -0,0 +1,33 @@
|
||||
{
|
||||
"_name_or_path": "ybelkada/falcon-7b-sharded-bf16",
|
||||
"alibi": false,
|
||||
"apply_residual_connection_post_layernorm": false,
|
||||
"architectures": [
|
||||
"RWForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"auto_map": {
|
||||
"AutoConfig": "tiiuae/falcon-7b--configuration_RW.RWConfig",
|
||||
"AutoModel": "tiiuae/falcon-7b--modelling_RW.RWModel",
|
||||
"AutoModelForCausalLM": "tiiuae/falcon-7b--modelling_RW.RWForCausalLM",
|
||||
"AutoModelForQuestionAnswering": "tiiuae/falcon-7b--modelling_RW.RWForQuestionAnswering",
|
||||
"AutoModelForSequenceClassification": "tiiuae/falcon-7b--modelling_RW.RWForSequenceClassification",
|
||||
"AutoModelForTokenClassification": "tiiuae/falcon-7b--modelling_RW.RWForTokenClassification"
|
||||
},
|
||||
"bias": false,
|
||||
"bos_token_id": 11,
|
||||
"eos_token_id": 11,
|
||||
"hidden_dropout": 0.0,
|
||||
"hidden_size": 4544,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "RefinedWebModel",
|
||||
"multi_query": true,
|
||||
"n_head": 71,
|
||||
"n_layer": 32,
|
||||
"parallel_attn": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.31.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 65024
|
||||
}
|
||||
BIN
falcoder.png
Normal file
BIN
falcoder.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 46 KiB |
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.31.0.dev0"
|
||||
}
|
||||
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:c6059bf3588550fbc95da0f0e199d8c7f5372766b3e4a76c45dc807a754e4754
|
||||
size 9951026337
|
||||
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 sha256:68ed0f5da1c34158beb14ff7f0104ca33a697fc3a05435549c63d20831833aba
|
||||
size 3892482385
|
||||
203
pytorch_model.bin.index.json
Normal file
203
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,203 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 13843441408
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.10.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.11.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.12.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.13.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.14.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.15.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.16.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.17.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.18.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.19.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.20.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.20.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.21.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.21.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.22.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.22.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.23.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.23.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.24.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.24.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.25.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.25.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.26.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.26.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.27.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.27.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.28.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.28.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.29.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.29.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.30.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.30.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.31.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.31.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.4.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.5.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.6.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.7.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.8.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.9.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.word_embeddings.weight": "pytorch_model-00001-of-00002.bin"
|
||||
}
|
||||
}
|
||||
17
special_tokens_map.json
Normal file
17
special_tokens_map.json
Normal file
@@ -0,0 +1,17 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
">>TITLE<<",
|
||||
">>ABSTRACT<<",
|
||||
">>INTRODUCTION<<",
|
||||
">>SUMMARY<<",
|
||||
">>COMMENT<<",
|
||||
">>ANSWER<<",
|
||||
">>QUESTION<<",
|
||||
">>DOMAIN<<",
|
||||
">>PREFIX<<",
|
||||
">>SUFFIX<<",
|
||||
">>MIDDLE<<"
|
||||
],
|
||||
"eos_token": "<|endoftext|>",
|
||||
"pad_token": "<|endoftext|>"
|
||||
}
|
||||
129983
tokenizer.json
Normal file
129983
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
7
tokenizer_config.json
Normal file
7
tokenizer_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"model_max_length": 2048,
|
||||
"tokenizer_class": "PreTrainedTokenizerFast"
|
||||
}
|
||||
Reference in New Issue
Block a user