初始化项目,由ModelHub XC社区提供模型
Model: Writer/palmyra-20b-chat Source: Original Platform
This commit is contained in:
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
|
||||
92
README.md
Normal file
92
README.md
Normal file
@@ -0,0 +1,92 @@
|
||||
---
|
||||
datasets:
|
||||
- WizardLM/WizardLM_evol_instruct_V2_196k
|
||||
- Open-Orca/OpenOrca
|
||||
language:
|
||||
- en
|
||||
tags:
|
||||
- chat
|
||||
- palmyra
|
||||
license: apache-2.0
|
||||
---
|
||||
|
||||
|
||||
**DEPRECATED MODEL NOTICE**
|
||||
==========================
|
||||
|
||||
Please note that this model is no longer maintained or supported by our team. We strongly advise against using it in production or for any critical applications.
|
||||
|
||||
Instead, we recommend using our latest and greatest models, which can be found at:
|
||||
|
||||
https://huggingface.co/collections/Writer/palmyra-writer-license-66476fa8156169f8720a2c89
|
||||
|
||||
==========================
|
||||
|
||||
|
||||
|
||||
|
||||
# Writer/palmyra-20b-chat
|
||||
---
|
||||
|
||||
# Usage
|
||||
|
||||
```py
|
||||
|
||||
import torch
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer
|
||||
|
||||
model_name = "Writer/palmyra-20b-chat"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_name,
|
||||
torch_dtype=torch.float16,
|
||||
device_map="auto",
|
||||
)
|
||||
|
||||
prompt = "What is the meaning of life?"
|
||||
|
||||
input_text = (
|
||||
"A chat between a curious user and an artificial intelligence assistant. "
|
||||
"The assistant gives helpful, detailed, and polite answers to the user's questions. "
|
||||
"USER: {prompt} "
|
||||
"ASSISTANT:"
|
||||
)
|
||||
|
||||
model_inputs = tokenizer(input_text.format(prompt=prompt), return_tensors="pt").to(
|
||||
"cuda"
|
||||
)
|
||||
|
||||
gen_conf = {
|
||||
"top_k": 20,
|
||||
"max_new_tokens": 2048,
|
||||
"temperature": 0.6,
|
||||
"do_sample": True,
|
||||
"eos_token_id": tokenizer.eos_token_id,
|
||||
}
|
||||
|
||||
streamer = TextStreamer(tokenizer)
|
||||
if "token_type_ids" in model_inputs:
|
||||
del model_inputs["token_type_ids"]
|
||||
|
||||
all_inputs = {**model_inputs, **gen_conf}
|
||||
output = model.generate(**all_inputs, streamer=streamer)
|
||||
|
||||
print("-"*20)
|
||||
print(output)
|
||||
|
||||
```
|
||||
# [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_Writer__palmyra-20b-chat)
|
||||
|
||||
| Metric | Value |
|
||||
|-----------------------|---------------------------|
|
||||
| Avg. | 38.97 |
|
||||
| ARC (25-shot) | 43.52 |
|
||||
| HellaSwag (10-shot) | 72.83 |
|
||||
| MMLU (5-shot) | 35.18 |
|
||||
| TruthfulQA (0-shot) | 43.17 |
|
||||
| Winogrande (5-shot) | 66.46 |
|
||||
| GSM8K (5-shot) | 3.94 |
|
||||
| DROP (3-shot) | 7.7 |
|
||||
3
added_tokens.json
Normal file
3
added_tokens.json
Normal file
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"[PAD]": 50257
|
||||
}
|
||||
33
config.json
Normal file
33
config.json
Normal file
@@ -0,0 +1,33 @@
|
||||
{
|
||||
"_name_or_path": "Writer/palmyra-20b-chat",
|
||||
"activation_function": "gelu",
|
||||
"architectures": [
|
||||
"GPT2LMHeadModel"
|
||||
],
|
||||
"attn_pdrop": 0.1,
|
||||
"bos_token_id": 50256,
|
||||
"embd_pdrop": 0.1,
|
||||
"eos_token_id": 50256,
|
||||
"initializer_range": 0.008165,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "gpt2",
|
||||
"n_embd": 6144,
|
||||
"n_head": 48,
|
||||
"n_inner": 24576,
|
||||
"n_layer": 44,
|
||||
"n_positions": 2048,
|
||||
"pad_token_id": 50257,
|
||||
"reorder_and_upcast_attn": false,
|
||||
"resid_pdrop": 0.1,
|
||||
"scale_attn_by_inverse_layer_idx": false,
|
||||
"scale_attn_weights": true,
|
||||
"summary_activation": null,
|
||||
"summary_first_dropout": 0.1,
|
||||
"summary_proj_to_labels": true,
|
||||
"summary_type": "cls_index",
|
||||
"summary_use_proj": true,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.32.0.dev0",
|
||||
"use_cache": false,
|
||||
"vocab_size": 50258
|
||||
}
|
||||
8
generation_config.json
Normal file
8
generation_config.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 50256,
|
||||
"eos_token_id": 50256,
|
||||
"pad_token_id": 50257,
|
||||
"transformers_version": "4.32.0.dev0",
|
||||
"use_cache": false
|
||||
}
|
||||
50001
merges.txt
Normal file
50001
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
pytorch_model-00001-of-00005.bin
Normal file
3
pytorch_model-00001-of-00005.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:63b83dd88774df2d6911af4e1b64059b5d2bd77bd664e802db65b413d28c5016
|
||||
size 9930627841
|
||||
3
pytorch_model-00002-of-00005.bin
Normal file
3
pytorch_model-00002-of-00005.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1fcdac70b950f9361dc6051dd0a4ba9885a993fcc1ecc8f154f90b15c21b2a10
|
||||
size 9967469263
|
||||
3
pytorch_model-00003-of-00005.bin
Normal file
3
pytorch_model-00003-of-00005.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b286c41e43b23382161da5132901cae9d02eb0b27306b3a18dbf5e3f659b71ec
|
||||
size 9967469263
|
||||
3
pytorch_model-00004-of-00005.bin
Normal file
3
pytorch_model-00004-of-00005.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1079abb02ea84e8e082eec4272a529529ed460cc0281b0a04273234582f43768
|
||||
size 9967469263
|
||||
3
pytorch_model-00005-of-00005.bin
Normal file
3
pytorch_model-00005-of-00005.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0e5b6dbcf92ecabc118e0de4389c0ca764ff506605db90e53be4d4d5683a14cd
|
||||
size 679603843
|
||||
540
pytorch_model.bin.index.json
Normal file
540
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,540 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 40512454656
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.0.attn.c_proj.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.1.attn.c_proj.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.1.mlp.c_proj.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.10.attn.c_attn.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.10.attn.c_attn.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.10.attn.c_proj.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.10.attn.c_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.10.ln_2.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.10.ln_2.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.10.mlp.c_fc.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.10.mlp.c_fc.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.10.mlp.c_proj.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.10.mlp.c_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.11.attn.c_attn.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.11.attn.c_attn.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.11.attn.c_proj.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.11.attn.c_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.11.ln_1.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.11.ln_1.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.11.ln_2.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.11.ln_2.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.11.mlp.c_fc.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.11.mlp.c_fc.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.11.mlp.c_proj.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.11.mlp.c_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.12.attn.c_attn.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.12.attn.c_attn.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.12.attn.c_proj.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.12.attn.c_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.12.ln_1.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.12.ln_1.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.12.ln_2.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.12.ln_2.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.12.mlp.c_fc.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.12.mlp.c_fc.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.12.mlp.c_proj.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.12.mlp.c_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.13.attn.c_attn.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.13.attn.c_attn.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.13.attn.c_proj.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.13.attn.c_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.13.ln_1.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.13.ln_1.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.13.ln_2.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.13.ln_2.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.13.mlp.c_fc.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.13.mlp.c_fc.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.13.mlp.c_proj.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.13.mlp.c_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.14.attn.c_attn.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.14.attn.c_attn.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.14.attn.c_proj.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.14.attn.c_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.14.ln_1.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.14.ln_1.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.14.ln_2.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.14.ln_2.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.14.mlp.c_fc.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.14.mlp.c_fc.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.14.mlp.c_proj.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.14.mlp.c_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.15.attn.c_attn.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.15.attn.c_attn.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.15.attn.c_proj.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.15.attn.c_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.15.ln_1.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.15.ln_1.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.15.ln_2.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.15.ln_2.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.15.mlp.c_fc.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.15.mlp.c_fc.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.15.mlp.c_proj.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.15.mlp.c_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.16.attn.c_attn.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.16.attn.c_attn.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.16.attn.c_proj.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.16.attn.c_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.16.ln_1.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.16.ln_1.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.16.ln_2.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.16.ln_2.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.16.mlp.c_fc.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.16.mlp.c_fc.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.16.mlp.c_proj.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.16.mlp.c_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.17.attn.c_attn.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.17.attn.c_attn.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.17.attn.c_proj.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.17.attn.c_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.17.ln_1.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.17.ln_1.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.17.ln_2.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.17.ln_2.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.17.mlp.c_fc.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.17.mlp.c_fc.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.17.mlp.c_proj.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.17.mlp.c_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.18.attn.c_attn.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.18.attn.c_attn.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.18.attn.c_proj.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.18.attn.c_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.18.ln_1.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.18.ln_1.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.18.ln_2.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.18.ln_2.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.18.mlp.c_fc.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.18.mlp.c_fc.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.18.mlp.c_proj.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.18.mlp.c_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.19.attn.c_attn.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.19.attn.c_attn.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.19.attn.c_proj.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.19.attn.c_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.19.ln_1.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.19.ln_1.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.19.ln_2.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.19.ln_2.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.19.mlp.c_fc.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.19.mlp.c_fc.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.19.mlp.c_proj.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.19.mlp.c_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.2.attn.c_attn.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.2.attn.c_attn.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.2.attn.c_proj.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.2.attn.c_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.2.ln_2.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.2.mlp.c_fc.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.2.mlp.c_fc.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.2.mlp.c_proj.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.20.attn.c_attn.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.20.attn.c_attn.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.20.attn.c_proj.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.20.attn.c_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.20.ln_1.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.20.ln_1.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.20.ln_2.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.20.ln_2.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.20.mlp.c_fc.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.20.mlp.c_fc.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.20.mlp.c_proj.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.20.mlp.c_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.21.attn.c_attn.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.21.attn.c_attn.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.21.attn.c_proj.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.21.attn.c_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.21.ln_1.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.21.ln_1.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"transformer.h.21.ln_2.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.21.ln_2.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.21.mlp.c_fc.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.21.mlp.c_fc.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.21.mlp.c_proj.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.21.mlp.c_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.22.attn.c_attn.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.22.attn.c_attn.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.22.attn.c_proj.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.22.attn.c_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.22.ln_1.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.22.ln_1.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.22.ln_2.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.22.ln_2.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.22.mlp.c_fc.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.22.mlp.c_fc.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.22.mlp.c_proj.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.22.mlp.c_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.23.attn.c_attn.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.23.attn.c_attn.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.23.attn.c_proj.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.23.attn.c_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.23.ln_1.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.23.ln_1.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.23.ln_2.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.23.ln_2.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.23.mlp.c_fc.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.23.mlp.c_fc.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.23.mlp.c_proj.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.23.mlp.c_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.24.attn.c_attn.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.24.attn.c_attn.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.24.attn.c_proj.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.24.attn.c_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.24.ln_1.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.24.ln_1.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.24.ln_2.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.24.ln_2.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.24.mlp.c_fc.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.24.mlp.c_fc.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.24.mlp.c_proj.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.24.mlp.c_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.25.attn.c_attn.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.25.attn.c_attn.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.25.attn.c_proj.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.25.attn.c_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.25.ln_1.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.25.ln_1.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.25.ln_2.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.25.ln_2.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.25.mlp.c_fc.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.25.mlp.c_fc.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.25.mlp.c_proj.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.25.mlp.c_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.26.attn.c_attn.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.26.attn.c_attn.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.26.attn.c_proj.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.26.attn.c_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.26.ln_1.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.26.ln_1.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.26.ln_2.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.26.ln_2.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.26.mlp.c_fc.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.26.mlp.c_fc.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.26.mlp.c_proj.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.26.mlp.c_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.27.attn.c_attn.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.27.attn.c_attn.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.27.attn.c_proj.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.27.attn.c_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.27.ln_1.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.27.ln_1.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.27.ln_2.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.27.ln_2.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.27.mlp.c_fc.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.27.mlp.c_fc.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.27.mlp.c_proj.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.27.mlp.c_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.28.attn.c_attn.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.28.attn.c_attn.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.28.attn.c_proj.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.28.attn.c_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.28.ln_1.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.28.ln_1.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.28.ln_2.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.28.ln_2.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.28.mlp.c_fc.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.28.mlp.c_fc.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.28.mlp.c_proj.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.28.mlp.c_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.29.attn.c_attn.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.29.attn.c_attn.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.29.attn.c_proj.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.29.attn.c_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.29.ln_1.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.29.ln_1.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.29.ln_2.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.29.ln_2.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.29.mlp.c_fc.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.29.mlp.c_fc.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.29.mlp.c_proj.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.29.mlp.c_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.3.attn.c_attn.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.3.attn.c_attn.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.3.attn.c_proj.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.3.attn.c_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.3.ln_2.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.3.mlp.c_fc.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.30.attn.c_attn.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.30.attn.c_attn.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.30.attn.c_proj.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.30.attn.c_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.30.ln_1.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.30.ln_1.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.30.ln_2.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.30.ln_2.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.30.mlp.c_fc.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.30.mlp.c_fc.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.30.mlp.c_proj.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.30.mlp.c_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.31.attn.c_attn.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.31.attn.c_attn.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.31.attn.c_proj.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.31.attn.c_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.31.ln_1.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.31.ln_1.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.31.ln_2.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.31.ln_2.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.31.mlp.c_fc.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.31.mlp.c_fc.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.31.mlp.c_proj.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.31.mlp.c_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.32.attn.c_attn.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.32.attn.c_attn.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.32.attn.c_proj.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.32.attn.c_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.32.ln_1.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.32.ln_1.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"transformer.h.32.ln_2.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.32.ln_2.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.32.mlp.c_fc.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.32.mlp.c_fc.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.32.mlp.c_proj.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.32.mlp.c_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.33.attn.c_attn.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.33.attn.c_attn.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.33.attn.c_proj.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.33.attn.c_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.33.ln_1.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.33.ln_1.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.33.ln_2.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.33.ln_2.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.33.mlp.c_fc.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.33.mlp.c_fc.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.33.mlp.c_proj.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.33.mlp.c_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.34.attn.c_attn.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.34.attn.c_attn.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.34.attn.c_proj.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.34.attn.c_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.34.ln_1.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.34.ln_1.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.34.ln_2.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.34.ln_2.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.34.mlp.c_fc.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.34.mlp.c_fc.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.34.mlp.c_proj.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.34.mlp.c_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.35.attn.c_attn.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.35.attn.c_attn.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.35.attn.c_proj.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.35.attn.c_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.35.ln_1.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.35.ln_1.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.35.ln_2.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.35.ln_2.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.35.mlp.c_fc.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.35.mlp.c_fc.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.35.mlp.c_proj.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.35.mlp.c_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.36.attn.c_attn.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.36.attn.c_attn.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.36.attn.c_proj.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.36.attn.c_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.36.ln_1.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.36.ln_1.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.36.ln_2.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.36.ln_2.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.36.mlp.c_fc.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.36.mlp.c_fc.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.36.mlp.c_proj.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.36.mlp.c_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.37.attn.c_attn.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.37.attn.c_attn.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.37.attn.c_proj.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.37.attn.c_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.37.ln_1.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.37.ln_1.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.37.ln_2.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.37.ln_2.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.37.mlp.c_fc.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.37.mlp.c_fc.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.37.mlp.c_proj.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.37.mlp.c_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.38.attn.c_attn.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.38.attn.c_attn.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.38.attn.c_proj.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.38.attn.c_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.38.ln_1.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.38.ln_1.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.38.ln_2.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.38.ln_2.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.38.mlp.c_fc.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.38.mlp.c_fc.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.38.mlp.c_proj.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.38.mlp.c_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.39.attn.c_attn.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.39.attn.c_attn.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.39.attn.c_proj.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.39.attn.c_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.39.ln_1.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.39.ln_1.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.39.ln_2.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.39.ln_2.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.39.mlp.c_fc.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.39.mlp.c_fc.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.39.mlp.c_proj.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.39.mlp.c_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.4.attn.c_attn.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.4.attn.c_attn.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.4.attn.c_proj.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.4.attn.c_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.4.ln_2.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.4.mlp.c_fc.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.4.mlp.c_fc.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.4.mlp.c_proj.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.40.attn.c_attn.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.40.attn.c_attn.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.40.attn.c_proj.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.40.attn.c_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.40.ln_1.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.40.ln_1.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.40.ln_2.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.40.ln_2.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.40.mlp.c_fc.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.40.mlp.c_fc.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.40.mlp.c_proj.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.40.mlp.c_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.41.attn.c_attn.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.41.attn.c_attn.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.41.attn.c_proj.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.41.attn.c_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.41.ln_1.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.41.ln_1.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.41.ln_2.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.41.ln_2.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.41.mlp.c_fc.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.41.mlp.c_fc.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.41.mlp.c_proj.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.41.mlp.c_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.42.attn.c_attn.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.42.attn.c_attn.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.42.attn.c_proj.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.42.attn.c_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.42.ln_1.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.42.ln_1.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.42.ln_2.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.42.ln_2.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.42.mlp.c_fc.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.42.mlp.c_fc.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.42.mlp.c_proj.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.42.mlp.c_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.43.attn.c_attn.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.43.attn.c_attn.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.43.attn.c_proj.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"transformer.h.43.attn.c_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"transformer.h.43.ln_1.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.43.ln_1.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"transformer.h.43.ln_2.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"transformer.h.43.ln_2.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"transformer.h.43.mlp.c_fc.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"transformer.h.43.mlp.c_fc.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"transformer.h.43.mlp.c_proj.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"transformer.h.43.mlp.c_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"transformer.h.5.attn.c_attn.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.5.attn.c_attn.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.5.attn.c_proj.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.5.attn.c_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.5.ln_2.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.5.mlp.c_fc.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.5.mlp.c_fc.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.5.mlp.c_proj.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.5.mlp.c_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.6.attn.c_attn.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.6.attn.c_attn.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.6.attn.c_proj.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.6.attn.c_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.6.ln_2.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.6.ln_2.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.6.mlp.c_fc.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.6.mlp.c_fc.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.6.mlp.c_proj.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.6.mlp.c_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.7.attn.c_attn.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.7.attn.c_attn.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.7.attn.c_proj.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.7.attn.c_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.7.ln_2.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.7.ln_2.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.7.mlp.c_fc.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.7.mlp.c_fc.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.7.mlp.c_proj.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.7.mlp.c_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.8.attn.c_attn.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.8.attn.c_attn.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.8.attn.c_proj.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.8.attn.c_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.8.ln_2.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.8.ln_2.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.8.mlp.c_fc.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.8.mlp.c_fc.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.8.mlp.c_proj.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.8.mlp.c_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.9.attn.c_attn.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.9.attn.c_attn.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.9.attn.c_proj.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.9.attn.c_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.9.ln_2.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.9.ln_2.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.9.mlp.c_fc.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.9.mlp.c_fc.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.9.mlp.c_proj.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.h.9.mlp.c_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.ln_f.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"transformer.ln_f.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"transformer.wpe.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"transformer.wte.weight": "pytorch_model-00001-of-00005.bin"
|
||||
}
|
||||
}
|
||||
6
special_tokens_map.json
Normal file
6
special_tokens_map.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"bos_token": "<|endoftext|>",
|
||||
"eos_token": "<|endoftext|>",
|
||||
"pad_token": "[PAD]",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
100314
tokenizer.json
Normal file
100314
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
34
tokenizer_config.json
Normal file
34
tokenizer_config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"bos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"errors": "replace",
|
||||
"model_max_length": 2048,
|
||||
"pad_token": null,
|
||||
"padding_side": "right",
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user