upload model

README.md

@@ -1,3 +1,71 @@
 ---
 license: gpl-3.0
 ---
+# NanoTranslator-365M-immersive_translate-v1
+
+## 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).
+
+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.
+
+## How to use
+
+Below is a method to call the model using transformers. The prompt follows the immersive translation format to ensure optimal results.
+
+```python
+import torch
+from typing import Literal
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_path = 'Mxode/NanoTranslator-365M-immersive_translate-v1'
+
+model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+
+def translate(
+    text: str,
+    to: Literal["chinese", "english"] = "chinese",
+    **kwargs
+):
+    generation_args = dict(
+        max_new_tokens = kwargs.pop("max_new_tokens", 512),
+        do_sample = kwargs.pop("do_sample", True),
+        temperature = kwargs.pop("temperature", 0.35),
+        top_p = kwargs.pop("top_p", 0.8),
+        top_k = kwargs.pop("top_k", 40),
+        **kwargs
+    )
+
+    prompt = """Translate the following source text to {to}. Output translation directly without any additional text.
+    Source Text: {text}
+
+    Translated Text:"""
+
+    messages = [
+        {"role": "system", "content": "You are a professional, authentic machine translation engine."},
+        {"role": "user", "content": prompt.format(to=to, text=text)}
+    ]
+    inputs = tokenizer.apply_chat_template(
+        messages,
+        tokenize=False,
+        add_generation_prompt=True
+    )
+    model_inputs = tokenizer([inputs], return_tensors="pt").to(model.device)
+
+    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
+    generated_ids = [
+        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+    ]
+
+    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+    return response
+
+text = "After a long day at work, I love to unwind by cooking a nice dinner and watching my favorite TV series. It really helps me relax and recharge for the next day."
+response = translate(text=text, to='chinese')
+print(f'Translation: {response}')
+
+"""
+Translation: 工作了一天，我喜欢吃一顿美味的晚餐，看我最喜欢的电视剧，这样做有助于我放松，补充能量。
+"""
+```

README_zh-CN.md

@@ -0,0 +1,68 @@
+# NanoTranslator-365M-immersive_translate-v1
+
+## 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。
+
+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。
+
+## How to use
+
+下面是一个用 transformers 调用的方式，prompt 遵循沉浸式翻译以保持最佳效果。
+
+```python
+import torch
+from typing import Literal
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_path = 'Mxode/NanoTranslator-365M-immersive_translate-v1'
+
+model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+
+def translate(
+    text: str,
+    to: Literal["chinese", "english"] = "chinese",
+    **kwargs
+):
+    generation_args = dict(
+        max_new_tokens = kwargs.pop("max_new_tokens", 512),
+        do_sample = kwargs.pop("do_sample", True),
+        temperature = kwargs.pop("temperature", 0.35),
+        top_p = kwargs.pop("top_p", 0.8),
+        top_k = kwargs.pop("top_k", 40),
+        **kwargs
+    )
+
+    prompt = """Translate the following source text to {to}. Output translation directly without any additional text.
+    Source Text: {text}
+
+    Translated Text:"""
+
+    messages = [
+        {"role": "system", "content": "You are a professional, authentic machine translation engine."},
+        {"role": "user", "content": prompt.format(to=to, text=text)}
+    ]
+    inputs = tokenizer.apply_chat_template(
+        messages,
+        tokenize=False,
+        add_generation_prompt=True
+    )
+    model_inputs = tokenizer([inputs], return_tensors="pt").to(model.device)
+
+    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
+    generated_ids = [
+        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+    ]
+
+    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+    return response
+
+text = "After a long day at work, I love to unwind by cooking a nice dinner and watching my favorite TV series. It really helps me relax and recharge for the next day."
+response = translate(text=text, to='chinese')
+print(f'Translation: {response}')
+
+"""
+Translation: 工作了一天，我喜欢吃一顿美味的晚餐，看我最喜欢的电视剧，这样做有助于我放松，补充能量。
+"""
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Mxode/NanoTranslator-365M-immersive_translate-v1",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 8000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 2,
+  "max_new_tokens": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.42.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6c1c82e6983f99f0540a667bd98c8336a2fb4e2284fcde51a5b055dea8dc97d
+size 730164456

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,37 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}