commit cc4204b24c1d83fcc4da15a644a081392d4433e8 Author: ModelHub XC Date: Sun May 10 20:14:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: GeneZC/MiniMA-3B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7bc225d --- /dev/null +++ b/.gitattributes @@ -0,0 +1,34 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..f1cda24 --- /dev/null +++ b/README.md @@ -0,0 +1,57 @@ +--- +frameworks: +- Pytorch +license: Apache License 2.0 +tasks: +- fill-mask +--- + +## MiniMA-3B + +📑 [arXiv](https://arxiv.org/abs/2311.07052) | 👻 [GitHub](https://github.com/GeneZC/MiniMA) | 🤗 [HuggingFace-MiniMA](https://huggingface.co/GeneZC/MiniMA-3B) | 🤗 [HuggingFace-MiniChat](https://huggingface.co/GeneZC/MiniChat-3B) | 🤖 [ModelScope-MiniMA](https://modelscope.cn/models/GeneZC/MiniMA-3B) | 🤖 [ModelScope-MiniChat](https://modelscope.cn/models/GeneZC/MiniChat-3B) + +❗ Must comply with LICENSE of LLaMA2 since it is derived from LLaMA2. + +A language model distilled from an adapted version of LLaMA2-7B following "Towards the Law of Capacity Gap in Distilling Language Models". + +Establishing a new compute-performance pareto frontier. + +teaser_a + +The following is an example code snippet to use MiniMA-3B: + +```python +import torch + +from transformers import AutoModelForCausalLM, AutoTokenizer + +# MiniMA +tokenizer = AutoTokenizer.from_pretrained("GeneZC/MiniMA-3B", use_fast=False) +# GPU. +model = AutoModelForCausalLM.from_pretrained("GeneZC/MiniMA-3B", use_cache=True, device_map="auto", torch_dtype=torch.float16).eval() +# CPU. +# model = AutoModelForCausalLM.from_pretrained("GeneZC/MiniMA-3B", use_cache=True, device_map="cpu", torch_dtype=torch.float16).eval() + +prompt = "Question: Sherrie tells the truth. Vernell says Sherrie tells the truth. Alexis says Vernell lies. Michaela says Alexis tells the truth. Elanor says Michaela tells the truth. Does Elanor tell the truth?\nAnswer: No\n\nQuestion: Kristian lies. Sherrie says Kristian lies. Delbert says Sherrie lies. Jerry says Delbert tells the truth. Shalonda says Jerry tells the truth. Does Shalonda tell the truth?\nAnswer: No\n\nQuestion: Vina tells the truth. Helene says Vina lies. Kandi says Helene tells the truth. Jamey says Kandi lies. Ka says Jamey lies. Does Ka tell the truth?\nAnswer: No\n\nQuestion: Christie tells the truth. Ka says Christie tells the truth. Delbert says Ka lies. Leda says Delbert tells the truth. Lorine says Leda tells the truth. Does Lorine tell the truth?\nAnswer:" +input_ids = tokenizer([prompt]).input_ids +output_ids = model.generate( + torch.as_tensor(input_ids).cuda(), + do_sample=True, + temperature=0.7, + max_new_tokens=1024, +) +output_ids = output_ids[0][len(input_ids[0]):] +output = tokenizer.decode(output_ids, skip_special_tokens=True).strip() +# output: "No" +``` + +## Bibtex + +```bibtex +@article{zhang2023law, + title={Towards the Law of Capacity Gap in Distilling Language Models}, + author={Zhang, Chen and Song, Dawei and Ye, Zheyu and Gao, Yan}, + year={2023}, + url={https://arxiv.org/abs/2311.07052} +} +``` \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..b54f5dc --- /dev/null +++ b/config.json @@ -0,0 +1,23 @@ +{ + "_name_or_path": "MiniMA-3B", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 3072, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 24, + "num_hidden_layers": 24, + "pad_token_id": 0, + "rms_norm_eps": 1e-05, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.30.2", + "use_cache": true, + "vocab_size": 49216 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..7b5b0c3 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework":"Pytorch","task":"fill-mask"} \ No newline at end of file diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..cf0c08c --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e64e665a7d3fb59f34fe7c9bfe6e0e5ad69413b803b7ac6db21c60acdfde234 +size 6040967525 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..d85ba6c --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/teaser_a.jpg b/teaser_a.jpg new file mode 100644 index 0000000..5525594 Binary files /dev/null and b/teaser_a.jpg differ diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..14cb1e6 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae87c0db2b21b0fa3fdc5e19d1f9cea94efb703cc7c6281d8718a6714b3cc2be +size 748869 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..64f06a6 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "bos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "clean_up_tokenization_spaces": false, + "eos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "use_fast": true +}