初始化项目，由ModelHub XC社区提供模型
Model: Writer/InstructPalmyra-20b 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
|
||||
134
README.md
Normal file
134
README.md
Normal file
@@ -0,0 +1,134 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
tags:
|
||||
- InstructGPT
|
||||
- hf
|
||||
- palmyra
|
||||
datasets:
|
||||
- Writer/palmyra-data-index
|
||||
---
|
||||
|
||||
|
||||
|
||||
# InstructPalmyra-20b
|
||||
|
||||
- **Developed by:** [https://writer.com/](https://writer.com/);
|
||||
- **Model type:** Causal decoder-only;
|
||||
- **Language(s) (NLP):** English;
|
||||
- **License:** Apache 2.0;
|
||||
- **Finetuned from model:** [Palmyra-20B](https://huggingface.co/Writer/palmyra-large).
|
||||
|
||||
|
||||
<style>
|
||||
img {
|
||||
display: inline;
|
||||
}
|
||||
</style>
|
||||
|
||||
|
||||
## Model Description
|
||||
|
||||
Introducing InstructPalmyra-20b, a state-of-the-art instruction-following 20b language model designed to deliver exceptional performance and versatility. Derived from the foundational architecture of [Palmyra-20b](https://huggingface.co/Writer/palmyra-large), InstructPalmyra-20b is specifically tailored to address the growing demand for advanced natural language processing and comprehension capabilities.
|
||||
|
||||
The InstructPalmyra-20b model is meticulously trained on an extensive dataset of approximately 70,000 instruction-response records. These records are generated by our dedicated Writer Linguist team, who possess considerable expertise in language modeling and fine-tuning techniques. By leveraging their skills and knowledge, the InstructPalmyra-20b model is primed to offer unparalleled proficiency in understanding and executing language-based instructions.
|
||||
|
||||
One of the key differentiators of InstructPalmyra-20b lies in its ability to process complex instructions and generate accurate, contextually appropriate responses. This makes it an ideal choice for a wide range of applications, including virtual assistants, customer support, content generation, and more. Additionally, the model's comprehensive training enables it to adapt and perform well under varying conditions and contexts, further expanding its potential use cases.
|
||||
|
||||
|
||||
|
||||
## Usage :
|
||||
```python
|
||||
import torch
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
|
||||
model_name = "Writer/InstructPalmyra-20b"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_name,
|
||||
device_map="auto",
|
||||
torch_dtype=torch.float16
|
||||
)
|
||||
|
||||
instruction = "Describe a futuristic device that revolutionizes space travel."
|
||||
|
||||
|
||||
PROMPT_DICT = {
|
||||
"prompt_input": (
|
||||
"Below is an instruction that describes a task, paired with an input that provides further context. "
|
||||
"Write a response that appropriately completes the request\n\n"
|
||||
"### Instruction:\n{instruction}\n\n### Input:\n{input}\n\n### Response:"
|
||||
),
|
||||
"prompt_no_input": (
|
||||
"Below is an instruction that describes a task. "
|
||||
"Write a response that appropriately completes the request.\n\n"
|
||||
"### Instruction:\n{instruction}\n\n### Response:"
|
||||
),
|
||||
}
|
||||
|
||||
text = (
|
||||
PROMPT_DICT["prompt_no_input"].format(instruction=instruction)
|
||||
if not input
|
||||
else PROMPT_DICT["prompt_input"].format(instruction=instruction, input=input)
|
||||
)
|
||||
|
||||
model_inputs = tokenizer(text, return_tensors="pt").to("cuda")
|
||||
output_ids = model.generate(
|
||||
**model_inputs,
|
||||
max_length=256,
|
||||
)
|
||||
output_text = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0]
|
||||
clean_output = output_text.split("### Response:")[1].strip()
|
||||
|
||||
print(clean_output)
|
||||
```
|
||||
|
||||
It can also be used with text-generation-inference
|
||||
|
||||
```sh
|
||||
model=Writer/InstructPalmyra-20b
|
||||
volume=$PWD/data
|
||||
|
||||
docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference --model-id $model
|
||||
```
|
||||
|
||||
|
||||
### Limitations and Biases
|
||||
|
||||
InstructPalmyra's core functionality is to take a string of text and predict the next token. While language models are widely used for other tasks, there are many unknowns in this work. When prompting InstructPalmyra, keep in mind that the next statistically likely token is not always the token that produces the most "accurate" text. Never rely on InstructPalmyra to produce factually correct results.
|
||||
|
||||
InstructPalmyra was trained on Writer’s custom data. As with all language models, it is difficult to predict how InstructPalmyra will respond to specific prompts, and offensive content may appear unexpectedly. We recommend that the outputs be curated or filtered by humans before they are released, both to censor undesirable content and to improve the quality of the results.
|
||||
|
||||
## Uses
|
||||
|
||||
|
||||
### Out-of-Scope Use
|
||||
|
||||
Production use without adequate assessment of risks and mitigation; any use cases which may be considered irresponsible or harmful.
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
|
||||
InstructPalmyra-20b is mostly trained on English data, and will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online.
|
||||
|
||||
### Recommendations
|
||||
|
||||
We recommend users of InstructPalmyra-20b to develop guardrails and to take appropriate precautions for any production use.
|
||||
|
||||
|
||||
|
||||
## Citation and Related Information
|
||||
|
||||
|
||||
To cite this model:
|
||||
```
|
||||
@misc{InstructPalmyra,
|
||||
author = {Writer Engineering team},
|
||||
title = {{InstructPalmyra-20b : Instruct tuned Palmyra-Large model}},
|
||||
howpublished = {\url{https://dev.writer.com}},
|
||||
year = 2023,
|
||||
month = Augest
|
||||
}
|
||||
```
|
||||
[](#model-architecture)|[](#model-architecture)|[](#datasets)|
|
||||
3
added_tokens.json
Normal file
3
added_tokens.json
Normal file
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"[PAD]": 50257
|
||||
}
|
||||
32
config.json
Normal file
32
config.json
Normal file
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"_name_or_path": "/home/ubuntu/server/InstructPalmyra-20b",
|
||||
"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,
|
||||
"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": true,
|
||||
"vocab_size": 50258
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 50256,
|
||||
"eos_token_id": 50256,
|
||||
"transformers_version": "4.32.0.dev0"
|
||||
}
|
||||
52
handler.py
Normal file
52
handler.py
Normal file
@@ -0,0 +1,52 @@
|
||||
import torch
|
||||
from typing import Dict, List, Any
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
|
||||
|
||||
# check for GPU
|
||||
device = 0 if torch.cuda.is_available() else -1
|
||||
|
||||
|
||||
format_input = (
|
||||
"Below is an instruction that describes a task. "
|
||||
"Write a response that appropriately completes the request.\n\n"
|
||||
"### Instruction:\n{instruction}\n\n### Response:"
|
||||
)
|
||||
|
||||
|
||||
class EndpointHandler:
|
||||
def __init__(self, path=""):
|
||||
# load the model
|
||||
tokenizer = AutoTokenizer.from_pretrained(path)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
path,
|
||||
device_map="auto",
|
||||
torch_dtype=torch.float16,
|
||||
)
|
||||
# create inference pipeline
|
||||
self.pipeline = pipeline(
|
||||
"text-generation",
|
||||
model=model,
|
||||
tokenizer=tokenizer,
|
||||
device=device,
|
||||
max_length=256,
|
||||
)
|
||||
|
||||
def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
|
||||
inputs = data.pop("inputs", data)
|
||||
parameters = data.pop("parameters", None)
|
||||
|
||||
text_input = format_input.format(instruction=inputs)
|
||||
|
||||
# pass inputs with all kwargs in data
|
||||
if parameters is not None:
|
||||
prediction = self.pipeline(text_input, **parameters)
|
||||
else:
|
||||
prediction = self.pipeline(text_input)
|
||||
|
||||
# postprocess the prediction
|
||||
output = [
|
||||
{"generated_text": pred["generated_text"].split("### Response:")[1].strip()}
|
||||
for pred in prediction
|
||||
]
|
||||
|
||||
return output
|
||||
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 sha256:016eb83728cc4f3ea3ad677700c287bf584d0011411efcb216caea4ddccfda31
|
||||
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 sha256:9be3e150665aa6b28567d6141258fa9fc148d5a54e820330673c5b5ad51a72eb
|
||||
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:a20b7b36a1e686f76ae5f3a98421d2ee9d6299ba8d0686181a34817fc1a60edd
|
||||
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 sha256:77278e4e765edd31cc085e4ef699443f610950a3668d9c51e1055bd063238f12
|
||||
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 sha256:9f72cd3d8a5fc5b20d4b6dffb2288671a854c8dae19a5c57de227ab6871ae7c3
|
||||
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|>"
|
||||
}
|
||||
100313
tokenizer.json
Normal file
100313
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