upload model

README.md

@@ -10,15 +10,15 @@ pipeline_tag: translation
 tags:
 - text-generation-inference
 ---
-# NanoTranslator-365M-immersive_translate-v1
+# NanoTranslator-immersive_translate-365M
 
 English | [简体中文](README_zh-CN.md)
 
 ## Introduction
 
-NanoTranslator-365M-immersive_translate-v1 is a translation model specifically designed for **Chinese-English bilingual** translation, trained with 200M data from the [wmt-19](https://huggingface.co/datasets/wmt/wmt19) dataset, based on [NanoLM-365M-Base](https://huggingface.co/Mxode/NanoLM-365M-Base).
+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).
 
-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.
+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.
 
 ## How to use
 
@@ -29,7 +29,7 @@ import torch
 from typing import Literal
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_path = 'Mxode/NanoTranslator-365M-immersive_translate-v1'
+model_path = 'Mxode/NanoTranslator-immersive_translate-365M'
 
 model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
 tokenizer = AutoTokenizer.from_pretrained(model_path)

README_zh-CN.md

@@ -1,12 +1,12 @@
-# NanoTranslator-365M-immersive_translate-v1
+# NanoTranslator-immersive_translate-365M
 
 [English](README.md) | 简体中文
 
 ## Introduction
 
-NanoTranslator-365M-immersive_translate-v1 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 200M 数据得来的专门用于**中英双语**的翻译模型。
+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。
 
-此模型遵循沉浸式翻译（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。
+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。
 
 ## How to use
 
@@ -17,7 +17,7 @@ import torch
 from typing import Literal
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_path = 'Mxode/NanoTranslator-365M-immersive_translate-v1'
+model_path = 'Mxode/NanoTranslator-immersive_translate-365M'
 
 model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
 tokenizer = AutoTokenizer.from_pretrained(model_path)

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Mxode/NanoTranslator-365M-immersive_translate-v1",
+  "_name_or_path": "Mxode/NanoTranslator-immersive_translate-365M",
   "architectures": [
     "Qwen2ForCausalLM"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6c1c82e6983f99f0540a667bd98c8336a2fb4e2284fcde51a5b055dea8dc97d
+oid sha256:b23a230bdafb3f95ec8640471f036bdd53118f85fc3d00c284c2cba4a41382e7
 size 730164456