初始化项目，由ModelHub XC社区提供模型

Model: xiaomi-research/MiLMMT-46-1B-v0.1
Source: Original Platform

.gitattributes

@@ -0,0 +1,37 @@
+*.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+main.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,87 @@
+---
+license: gemma
+base_model:
+- xiaomi-research/MiMT-46-1B-Pretrain
+pipeline_tag: translation
+library_name: transformers
+---
+
+
+## Model Description
+
+MiLMMT-46-1B-v0.1 is an LLM-based translation model. It has been fintuned on MiLMMT-46-1B-Pretrain, which is a language model developed through continual pretraining of Gemma3-1B using a mix of 143 billion tokens from both monolingual and parallel data across 46 different languages. Please find more details in our paper: [Scaling Model and Data for Multilingual Machine Translation with Open Large Language Models](https://arxiv.org/abs/2602.11961).
+
+
+- **Supported Languages**: Arabic, Azerbaijani, Bulgarian, Bengali, Catalan, Czech, Danish, German, Greek, English, Spanish, Persian, Finnish, French, Hebrew, Hindi, Croatian, Hungarian, Indonesian, Italian, Japanese, Kazakh, Khmer, Korean, Lao, Malay, Burmese, Norwegian, Dutch, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Swedish, Tamil, Thai, Tagalog, Turkish, Urdu, Uzbek, Vietnamese, Cantonese, Chinese (Simplified), Chinese (Traditional).
+- **GitHub**: Please find more details in our [GitHub repository](https://github.com/xiaomi-research/gemmax).
+- **Developed by**: Xiaomi Inc.
+
+
+## Model Performance
+
+![Experimental Result](main.png)
+
+## Translation Prompt
+
+```text
+Translate this from <source language name> to <target language name>:
+<source language name>: <source language sentence>
+<target language name>:
+```
+Please use the language name specified above in the translation prompt.
+
+
+## Run the model
+
+#### Using on vLLM:
+```python
+from vllm import LLM, SamplingParams
+
+
+model_id = "xiaomi-research/MiLMMT-46-1B-v0.1"
+
+model = LLM(model=model_id)
+sampling_params = SamplingParams(top_k=1, temperature=0, max_tokens=2048)
+
+text = "Translate this from Chinese (Simplified) to English:\nChinese (Simplified): 我爱机器翻译\nEnglish:"
+
+outputs = model.generate(text, sampling_params)
+print(outputs[0].outputs[0].text)
+```
+
+#### Using on Transformers:
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+
+model_id = "xiaomi-research/MiLMMT-46-1B-v0.1"
+
+model = AutoModelForCausalLM.from_pretrained(model_id)
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+text = "Translate this from Chinese (Simplified) to English:\nChinese (Simplified): 我爱机器翻译\nEnglish:"
+inputs = tokenizer(text, add_special_tokens=False, return_tensors="pt")
+
+outputs = model.generate(**inputs, max_new_tokens=1024)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+
+## Citation
+
+```bibtex
+@misc{shang2026scalingmodeldatamultilingual,
+      title={Scaling Model and Data for Multilingual Machine Translation with Open Large Language Models}, 
+      author={Yuzhe Shang and Pengzhi Gao and Wei Liu and Jian Luan and Jinsong Su},
+      year={2026},
+      eprint={2602.11961},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2602.11961}, 
+}
+```
+
+
+## Limitations
+
+MiLMMT-46 currently supports only the 46 languages listed above, and strong translation performance is not guaranteed for other languages. We will continue to improve the translation quality of MiLMMT-46, and future model releases will follow in due course.

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

config.json

@@ -0,0 +1,62 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 1152,
+  "initializer_range": 0.02,
+  "intermediate_size": 6912,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": 512,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.2",
+  "use_cache": false,
+  "vocab_size": 262144
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.55.2"
+}

main.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:824a4427b98127b266c2a4992f64d71d61cdae211859215be0b54f153379d516
+size 310340

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:118ceb72904a25d3760df3abc1cac684ffae0c2c633cce2f65e111d7ff12d47e
+size 2603791264

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074