初始化项目，由ModelHub XC社区提供模型
Model: Writer/palmyra-med-20b Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
184
README.md
Normal file
184
README.md
Normal file
@@ -0,0 +1,184 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
tags:
|
||||
- medical
|
||||
- palmyra
|
||||
---
|
||||
|
||||
**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Please note that this model is no longer maintained or supported by our team.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
|
||||
|
||||
==========================
|
||||
|
||||
# Palmyra-med-20b
|
||||
|
||||
## Model description
|
||||
**Palmyra-Med-20b** is a 20 billion parameter Large Language Model that has been uptrained on
|
||||
**Palmyra-Large** with a specialized custom-curated medical dataset.
|
||||
The main objective of this model is to enhance performance in tasks related to medical dialogue
|
||||
and question-answering.
|
||||
|
||||
- **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-Large](https://huggingface.co/Writer/palmyra-large).
|
||||
|
||||
### Model Source
|
||||
|
||||
[Palmyra-Med: Instruction-Based Fine-Tuning of LLMs Enhancing Medical Domain Performance](https://dev.writer.com/docs/palmyra-med-instruction-based-fine-tuning-of-llms-enhancing-medical-domain-performance)
|
||||
|
||||
|
||||
## 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
|
||||
|
||||
Palmyra-Med-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 Palmyra-Med-20B to develop guardrails and to take appropriate precautions for any production use.
|
||||
|
||||
|
||||
## Usage
|
||||
The model is compatible with the huggingface `AutoModelForCausalLM` and can be easily run on a single 40GB A100.
|
||||
|
||||
```py
|
||||
import torch
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
|
||||
model_name = "Writer/palmyra-med-20b"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=False)
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_name,
|
||||
device_map="auto",
|
||||
torch_dtype=torch.float16,
|
||||
)
|
||||
|
||||
prompt = "Can you explain in simple terms how vaccines help our body fight diseases?"
|
||||
|
||||
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 = {
|
||||
"temperature": 0.7,
|
||||
"repetition_penalty": 1.0,
|
||||
"max_new_tokens": 512,
|
||||
"do_sample": True,
|
||||
}
|
||||
|
||||
out_tokens = model.generate(**model_inputs, **gen_conf)
|
||||
|
||||
response_ids = out_tokens[0][len(model_inputs.input_ids[0]) :]
|
||||
output = tokenizer.decode(response_ids, skip_special_tokens=True)
|
||||
|
||||
print(output)
|
||||
## output ##
|
||||
# Vaccines stimulate the production of antibodies by the body's immune system.
|
||||
# Antibodies are proteins produced by B lymphocytes in response to foreign substances,such as viruses and bacteria.
|
||||
# The antibodies produced by the immune system can bind to and neutralize the pathogens, preventing them from invading and damaging the host cells.
|
||||
# Vaccines work by introducing antigens, which are components of the pathogen, into the body.
|
||||
# The immune system then produces antibodies against the antigens, which can recognize and neutralize the pathogen if it enters the body in the future.
|
||||
# The use of vaccines has led to a significant reduction in the incidence and severity of many diseases, including measles, mumps, rubella, and polio.
|
||||
```
|
||||
|
||||
It can also be used with text-generation-inference
|
||||
|
||||
```sh
|
||||
model=Writer/palmyra-med-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
|
||||
```
|
||||
|
||||
## Dataset
|
||||
For the fine-tuning of our LLMs, we used a custom-curated medical dataset that combines data from
|
||||
two publicly available sources: PubMedQA (Jin et al. 2019) and MedQA (Zhang et al. 2018).The
|
||||
PubMedQA dataset, which originated from the PubMed abstract database, consists of biomedical
|
||||
articles accompanied by corresponding question-answer pairs. In contrast, the MedQA dataset
|
||||
features medical questions and answers that are designed to assess the reasoning capabilities of
|
||||
medical question-answering systems.
|
||||
We prepared our custom dataset by merging and processing data from the aforementioned sources,
|
||||
maintaining the dataset mixture ratios detailed in Table 1. These ratios were consistent for finetuning
|
||||
both Palmyra-20b and Palmyra-40b models. Upon fine-tuning the models with this dataset, we refer
|
||||
to the resulting models as Palmyra-Med-20b and Palmyra-Med-40b, respectively.
|
||||
|
||||
|
||||
| Dataset | Ratio | Count |
|
||||
| -----------|----------- | ----------- |
|
||||
| PubMedQA | 75% | 150,000 |
|
||||
| MedQA | 25% | 10,178 |
|
||||
|
||||
|
||||
## Evaluation
|
||||
we present the findings of our experiments, beginning with the evaluation outcomes of
|
||||
the fine-tuned models and followed by a discussion of the base models’ performance on each of the
|
||||
evaluation datasets. Additionally, we report the progressive improvement of the Palmyra-Med-40b
|
||||
model throughout the training process on the PubMedQA dataset.
|
||||
|
||||
| Model | PubMedQA | MedQA |
|
||||
| -----------|----------- | ----------- |
|
||||
| Palmyra-20b | 49.8 | 31.2 |
|
||||
| Palmyra-40b | 64.8 | 43.1|
|
||||
| Palmyra-Med-20b| 75.6 | 44.6|
|
||||
| Palmyra-Med-40b| 81.1 | 72.4|
|
||||
|
||||
|
||||
|
||||
## Limitation
|
||||
The model may not operate efficiently beyond the confines of the healthcare field.
|
||||
Since it has not been subjected to practical scenarios, its real-time efficacy and precision remain undetermined.
|
||||
Under no circumstances should it replace the advice of a medical professional, and it must be regarded solely as a tool for research purposes.
|
||||
|
||||
## Citation and Related Information
|
||||
|
||||
|
||||
To cite this model:
|
||||
```
|
||||
@misc{Palmyra-Med-20B,
|
||||
author = {Writer Engineering team},
|
||||
title = {{Palmyra-Large Parameter Autoregressive Language Model}},
|
||||
howpublished = {\url{https://dev.writer.com}},
|
||||
year = 2023,
|
||||
month = March
|
||||
}
|
||||
```
|
||||
|
||||
## Contact
|
||||
Hello@writer.com
|
||||
# [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-med-20b)
|
||||
|
||||
| Metric | Value |
|
||||
|-----------------------|---------------------------|
|
||||
| Avg. | 40.02 |
|
||||
| ARC (25-shot) | 46.93 |
|
||||
| HellaSwag (10-shot) | 73.51 |
|
||||
| MMLU (5-shot) | 44.34 |
|
||||
| TruthfulQA (0-shot) | 35.47 |
|
||||
| Winogrande (5-shot) | 65.35 |
|
||||
| GSM8K (5-shot) | 2.65 |
|
||||
| DROP (3-shot) | 11.88 |
|
||||
4
added_tokens.json
Normal file
4
added_tokens.json
Normal file
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"<s>": 50258,
|
||||
"[PAD]": 50257
|
||||
}
|
||||
32
config.json
Normal file
32
config.json
Normal file
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"_name_or_path": "palmyra-med-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": "4.30.0.dev0",
|
||||
"use_cache": false,
|
||||
"vocab_size": 50259
|
||||
}
|
||||
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": "4.30.0.dev0"
|
||||
}
|
||||
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:bd9c141fb89248be2fcfd895873a97008e0329468117237cf2243dce9c4484f0
|
||||
size 9930640129
|
||||
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 sha256:804c94e524af7927aae4c222670cdbedda9fb4077f53f14440f6c319d0f74b06
|
||||
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 sha256:650f860fa5d24ec87ef17394e82735350c1563f8b18ff3521955c8d4990ad21a
|
||||
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 sha256:4e07108b56d29d59adf796cb0e12b15af3de0138e318adf6ac3f6a8207d8861f
|
||||
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:a4f32273b9d70dbd6a61f3fb9bb32d41c73c26b9e1a524fa2e5cf508223b27c7
|
||||
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": 40512466944
|
||||
},
|
||||
"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"
|
||||
}
|
||||
}
|
||||
7
special_tokens_map.json
Normal file
7
special_tokens_map.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"bos_token": "<|endoftext|>",
|
||||
"eos_token": "<|endoftext|>",
|
||||
"pad_token": "[PAD]",
|
||||
"sep_token": "<s>",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
100323
tokenizer.json
Normal file
100323
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