初始化项目，由ModelHub XC社区提供模型
Model: AI-Sweden-Models/gpt-sw3-6.7b-v2-translator 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
|
||||
80
README.md
Normal file
80
README.md
Normal file
@@ -0,0 +1,80 @@
|
||||
---
|
||||
base_model: AI-Sweden-Models/gpt-sw3-6.7b-v2-instruct
|
||||
language:
|
||||
- sv
|
||||
- da
|
||||
- 'no'
|
||||
- en
|
||||
pipeline_tag: text-generation
|
||||
inference:
|
||||
parameters:
|
||||
temperature: 0.7
|
||||
tags:
|
||||
- translation
|
||||
---
|
||||
# Model Card for gpt-sw3-6.7b-v2-translator
|
||||
The `gpt-sw3-6.7b-v2-translator` is a finetuned version of `gpt-sw3-6.7b-v2-instruct` on a carefully selected translation pair dataset that was gathered by AI Sweden.
|
||||
|
||||
|
||||
## Intended usage:
|
||||
Translate text data from English to Swedish, or Swedish to English.
|
||||
|
||||
|
||||
## How to use:
|
||||
```python
|
||||
import torch
|
||||
from transformers import pipeline, StoppingCriteriaList, StoppingCriteria
|
||||
|
||||
device = "cuda" if torch.cuda.is_available() else "cpu"
|
||||
|
||||
|
||||
# (Optional) - define a stopping criteria
|
||||
# We ideally want the model to stop generate once the response from the Bot is generated
|
||||
class StopOnTokenCriteria(StoppingCriteria):
|
||||
def __init__(self, stop_token_id):
|
||||
self.stop_token_id = stop_token_id
|
||||
|
||||
def __call__(self, input_ids, scores, **kwargs):
|
||||
return input_ids[0, -1] == self.stop_token_id
|
||||
|
||||
|
||||
pipe = pipeline(
|
||||
task="text-generation",
|
||||
model="AI-Sweden-Models/gpt-sw3-6.7b-v2-translator",
|
||||
device=device
|
||||
)
|
||||
|
||||
stop_on_token_criteria = StopOnTokenCriteria(stop_token_id=pipe.tokenizer.bos_token_id)
|
||||
text = "I like to eat ice cream in the summer."
|
||||
|
||||
# This will translate English to Swedish
|
||||
# To translate from Swedish to English the prompt would be:
|
||||
# prompt = f"<|endoftext|><s>User: Översätt till Engelska från Svenska\n{text}<s>Bot:"
|
||||
|
||||
prompt = f"<|endoftext|><s>User: Översätt till Svenska från Engelska\n{text}<s>Bot:"
|
||||
|
||||
input_tokens = pipe.tokenizer(prompt, return_tensors="pt").input_ids.to(device)
|
||||
max_model_length = 2048
|
||||
dynamic_max_length = max_model_length - input_tokens.shape[1]
|
||||
|
||||
response = pipe(
|
||||
prompt,
|
||||
max_length=dynamic_max_length,
|
||||
truncation=True,
|
||||
stopping_criteria=StoppingCriteriaList([stop_on_token_criteria])
|
||||
)
|
||||
|
||||
print(response[0]["generated_text"].split("<s>Bot: ")[-1])
|
||||
```
|
||||
```python
|
||||
>>> "Jag tycker om att äta glass på sommaren."
|
||||
```
|
||||
|
||||
## Training & Data:
|
||||
The training was done on 1 NVIDIA DGX using DeepSpeed ZeRO 3 for three epochs on roughly 4GB of carefully selected translation data. It is a full finetune of all of the model parameters.
|
||||
|
||||
| Epoch | Training Loss | Evaluation Loss |
|
||||
|-------|---------------|-----------------|
|
||||
| 1 | 1.309 | 1.281 |
|
||||
| 2 | 1.161 | 1.242 |
|
||||
| 3 | 1.053 | 1.219 |
|
||||
38
config.json
Normal file
38
config.json
Normal file
@@ -0,0 +1,38 @@
|
||||
{
|
||||
"_name_or_path": "/data/models/gpt-sw3-translation-7b",
|
||||
"activation_function": "gelu",
|
||||
"apply_query_key_layer_scaling": true,
|
||||
"architectures": [
|
||||
"GPT2LMHeadModel"
|
||||
],
|
||||
"attn_pdrop": 0.1,
|
||||
"bos_token_id": 1,
|
||||
"embd_pdrop": 0.1,
|
||||
"eos_token_id": 1,
|
||||
"initializer_range": 0.01,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"max_length": 2048,
|
||||
"model_type": "gpt2",
|
||||
"n_ctx": 2048,
|
||||
"n_embd": 4096,
|
||||
"n_head": 32,
|
||||
"n_inner": 16384,
|
||||
"n_layer": 32,
|
||||
"n_positions": 2048,
|
||||
"normalize_attention_scores": true,
|
||||
"pad_token_id": 0,
|
||||
"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,
|
||||
"tokenizer_class": "GPTSw3Tokenizer",
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.40.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 64000
|
||||
}
|
||||
8
generation_config.json
Normal file
8
generation_config.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 1,
|
||||
"max_length": 2048,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.40.0.dev0"
|
||||
}
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:59fadb1cee8c2566dc4eba3b749da23508569ce8725c633d56347a12792bb4a2
|
||||
size 4971452464
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fa0638c1ddd676dd976774c16abf1d8e3f54be5b9f4af397ed27a1fdbf7743f9
|
||||
size 4967399072
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:be6e3549c8d4a262a058d196f40e1a04958ca3f955aad5f5d80226d5850c65de
|
||||
size 3490581120
|
||||
395
model.safetensors.index.json
Normal file
395
model.safetensors.index.json
Normal file
@@ -0,0 +1,395 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 13429391360
|
||||
},
|
||||
"weight_map": {
|
||||
"transformer.h.0.attn.c_attn.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.attn.c_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.ln_1.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.ln_1.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.ln_2.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.ln_2.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.attn.c_attn.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.attn.c_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.ln_1.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.ln_1.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.ln_2.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.ln_2.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.10.attn.c_attn.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.10.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.10.attn.c_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.10.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.10.ln_1.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.10.ln_1.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.10.ln_2.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.10.ln_2.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.10.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.10.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.10.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.10.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.11.attn.c_attn.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.11.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.11.attn.c_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.11.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.11.ln_1.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.11.ln_1.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.11.ln_2.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.11.ln_2.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.11.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.11.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.11.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.11.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.attn.c_attn.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.attn.c_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.ln_1.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.ln_1.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.ln_2.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.ln_2.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.attn.c_attn.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.attn.c_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.ln_1.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.ln_1.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.ln_2.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.ln_2.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.attn.c_attn.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.attn.c_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.ln_1.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.ln_1.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.ln_2.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.ln_2.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.attn.c_attn.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.attn.c_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.ln_1.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.ln_1.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.ln_2.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.ln_2.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.attn.c_attn.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.attn.c_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.ln_1.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.ln_1.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.ln_2.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.ln_2.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.attn.c_attn.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.attn.c_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.ln_1.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.ln_1.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.ln_2.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.ln_2.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.attn.c_attn.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.attn.c_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.ln_1.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.ln_1.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.ln_2.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.ln_2.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.attn.c_attn.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.attn.c_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.ln_1.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.ln_1.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.ln_2.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.ln_2.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.2.attn.c_attn.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.attn.c_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.ln_1.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.ln_1.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.ln_2.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.ln_2.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.20.attn.c_attn.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.20.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.20.attn.c_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.20.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.20.ln_1.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.20.ln_1.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.20.ln_2.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.20.ln_2.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.20.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.20.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.20.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.20.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.21.attn.c_attn.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.21.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.21.attn.c_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.21.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.21.ln_1.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.21.ln_1.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.21.ln_2.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.21.ln_2.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.21.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.21.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.21.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.21.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.22.attn.c_attn.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.22.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.22.attn.c_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.22.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.22.ln_1.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.22.ln_1.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.22.ln_2.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.22.ln_2.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.22.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.22.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.22.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.22.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.23.attn.c_attn.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.23.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.23.attn.c_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.23.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.23.ln_1.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.23.ln_1.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.23.ln_2.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.23.ln_2.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.23.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.23.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.23.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.23.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.attn.c_attn.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.attn.c_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.ln_1.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.ln_1.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.ln_2.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.ln_2.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.attn.c_attn.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.attn.c_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.ln_1.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.ln_1.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.ln_2.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.ln_2.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.attn.c_attn.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.attn.c_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.ln_1.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.ln_1.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.ln_2.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.ln_2.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.attn.c_attn.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.attn.c_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.ln_1.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.ln_1.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.ln_2.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.ln_2.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.28.attn.c_attn.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.28.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.28.attn.c_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.28.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.28.ln_1.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.28.ln_1.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.28.ln_2.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.28.ln_2.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.28.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.28.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.28.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.28.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.29.attn.c_attn.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.29.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.29.attn.c_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.29.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.29.ln_1.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.29.ln_1.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.29.ln_2.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.29.ln_2.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.29.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.29.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.29.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.29.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.3.attn.c_attn.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.attn.c_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.ln_1.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.ln_1.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.ln_2.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.ln_2.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.30.attn.c_attn.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.30.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.30.attn.c_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.30.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.30.ln_1.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.30.ln_1.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.30.ln_2.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.30.ln_2.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.30.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.30.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.30.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.30.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.31.attn.c_attn.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.31.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.31.attn.c_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.31.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.31.ln_1.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.31.ln_1.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.31.ln_2.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.31.ln_2.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.31.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.31.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.31.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.31.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.4.attn.c_attn.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.attn.c_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.ln_1.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.ln_1.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.ln_2.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.ln_2.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.attn.c_attn.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.attn.c_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.ln_1.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.ln_1.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.ln_2.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.ln_2.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.attn.c_attn.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.attn.c_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.ln_1.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.ln_1.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.ln_2.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.ln_2.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.7.attn.c_attn.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.7.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.7.attn.c_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.7.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.7.ln_1.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.7.ln_1.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.7.ln_2.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.7.ln_2.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.7.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.7.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.7.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.7.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.8.attn.c_attn.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.8.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.8.attn.c_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.8.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.8.ln_1.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.8.ln_1.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.8.ln_2.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.8.ln_2.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.8.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.8.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.8.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.8.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.9.attn.c_attn.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.9.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.9.attn.c_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.9.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.9.ln_1.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.9.ln_1.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.9.ln_2.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.9.ln_2.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.9.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.9.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.9.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.9.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.ln_f.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.ln_f.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.wpe.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.wte.weight": "model-00001-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
spiece.model
Normal file
3
spiece.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f4bda2cd84ff0ac659cda40e746c55f47ee3e57cf18471670ad26998c28be52d
|
||||
size 1071955
|
||||
49
tokenizer_config.json
Normal file
49
tokenizer_config.json
Normal file
@@ -0,0 +1,49 @@
|
||||
{
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"3": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"do_lower_case": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"keep_accents": false,
|
||||
"model_max_length": 2048,
|
||||
"pad_token": "<pad>",
|
||||
"padding_side": "left",
|
||||
"remove_space": false,
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "GPTSw3Tokenizer",
|
||||
"truncation_side": "left",
|
||||
"unk_token": "<unk>"
|
||||
}
|
||||
Reference in New Issue
Block a user