upload model
Browse files- README.md +4 -4
- README_zh-CN.md +4 -4
- config.json +1 -1
- model.safetensors +1 -1
README.md
CHANGED
@@ -10,15 +10,15 @@ pipeline_tag: translation
|
|
10 |
tags:
|
11 |
- text-generation-inference
|
12 |
---
|
13 |
-
# NanoTranslator-
|
14 |
|
15 |
English | [简体中文](README_zh-CN.md)
|
16 |
|
17 |
## Introduction
|
18 |
|
19 |
-
NanoTranslator-
|
20 |
|
21 |
-
This model is trained following the Immersive Translate prompt format and can be deployed as an OpenAI format interface using tools like vllm and lmdeploy for utilization.
|
22 |
|
23 |
## How to use
|
24 |
|
@@ -29,7 +29,7 @@ import torch
|
|
29 |
from typing import Literal
|
30 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
31 |
|
32 |
-
model_path = 'Mxode/NanoTranslator-
|
33 |
|
34 |
model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
|
35 |
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
|
|
10 |
tags:
|
11 |
- text-generation-inference
|
12 |
---
|
13 |
+
# NanoTranslator-immersive_translate-365M
|
14 |
|
15 |
English | [简体中文](README_zh-CN.md)
|
16 |
|
17 |
## Introduction
|
18 |
|
19 |
+
NanoTranslator-immersive_translate-365M is a model specifically designed for **Chinese-English bilingual** translation, trained with 6M data from the [wmt-19](https://huggingface.co/datasets/wmt/wmt19) dataset, based on [NanoLM-365M-Base](https://huggingface.co/Mxode/NanoLM-365M-Base).
|
20 |
|
21 |
+
This model is trained following the [Immersive Translate](https://immersivetranslate.com/) prompt format and can be deployed as an OpenAI format interface using tools like vllm and lmdeploy for utilization.
|
22 |
|
23 |
## How to use
|
24 |
|
|
|
29 |
from typing import Literal
|
30 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
31 |
|
32 |
+
model_path = 'Mxode/NanoTranslator-immersive_translate-365M'
|
33 |
|
34 |
model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
|
35 |
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
README_zh-CN.md
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
-
# NanoTranslator-
|
2 |
|
3 |
[English](README.md) | 简体中文
|
4 |
|
5 |
## Introduction
|
6 |
|
7 |
-
NanoTranslator-
|
8 |
|
9 |
-
|
10 |
|
11 |
## How to use
|
12 |
|
@@ -17,7 +17,7 @@ import torch
|
|
17 |
from typing import Literal
|
18 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
19 |
|
20 |
-
model_path = 'Mxode/NanoTranslator-
|
21 |
|
22 |
model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
|
23 |
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
|
|
1 |
+
# NanoTranslator-immersive_translate-365M
|
2 |
|
3 |
[English](README.md) | 简体中文
|
4 |
|
5 |
## Introduction
|
6 |
|
7 |
+
NanoTranslator-immersive_translate-365M 是由 [NanoLM-365M-Base](https://huggingface.co/Mxode/NanoLM-365M-Base) 在 [wmt-19](https://huggingface.co/datasets/wmt/wmt19) 数据集上训练了 600 万数据得来的专门用于**中英双语**的翻译模型。
|
8 |
|
9 |
+
此模型遵循[沉浸式翻译](https://immersivetranslate.com/)(Immersive Translate)的 prompt 格式进行训练,可以通过 vllm、lmdeploy 等方式部署为 OpenAI 格式接口,从而完成调用。
|
10 |
|
11 |
## How to use
|
12 |
|
|
|
17 |
from typing import Literal
|
18 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
19 |
|
20 |
+
model_path = 'Mxode/NanoTranslator-immersive_translate-365M'
|
21 |
|
22 |
model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
|
23 |
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "Mxode/NanoTranslator-
|
3 |
"architectures": [
|
4 |
"Qwen2ForCausalLM"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "Mxode/NanoTranslator-immersive_translate-365M",
|
3 |
"architectures": [
|
4 |
"Qwen2ForCausalLM"
|
5 |
],
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 730164456
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b23a230bdafb3f95ec8640471f036bdd53118f85fc3d00c284c2cba4a41382e7
|
3 |
size 730164456
|