commit dbc625fd59ba7f9a4282d0ceafe6f88258c132ce Author: ModelHub XC Date: Tue Jun 9 09:22:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: jondurbin/airoboros-l2-13b-gpt4-1.4.1 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..21b3632 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm 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 \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..3c14817 --- /dev/null +++ b/README.md @@ -0,0 +1,31 @@ +--- +license: other +datasets: +- jondurbin/airoboros-gpt4-1.4.1 +--- + +### Overview + +Llama 2 13b fine tune using https://huggingface.co/datasets/jondurbin/airoboros-gpt4-1.4.1 + +See the previous llama 65b model card for info: +https://hf.co/jondurbin/airoboros-65b-gpt4-1.4 + +### Licence and usage restrictions + +This model was built on llama-2, which has a proprietary/custom Meta license. +- See the LICENSE.txt file attached for the original license, along with USE_POLICY.md which was also provided by Meta. + +The data used to fine-tune the llama-2-13b-hf model was generated by GPT4 via OpenAI API calls.using [airoboros](https://github.com/jondurbin/airoboros) +- The ToS for OpenAI API usage has a clause preventing the output from being used to train a model that __competes__ with OpenAI + - what does *compete* actually mean here? + - these small open source models will not produce output anywhere near the quality of gpt-4, or even gpt-3.5, so I can't imagine this could credibly be considered competing in the first place + - if someone else uses the dataset to do the same, they wouldn't necessarily be violating the ToS because they didn't call the API, so I don't know how that works + - the training data used in essentially all large language models includes a significant of copyrighted or otherwise unallowable licensing in the first place + - other work using the self-instruct method, e.g. the original here: https://github.com/yizhongw/self-instruct released the data and model as apache-2 + +I am purposingly leaving this license ambiguous (other than the fact you must comply with the Meta original license) because I am not a lawyer and refuse to attempt to interpret all of the terms accordingly. + +Your best bet is probably to avoid using this commercially due to the OpenAI API usage. + +Either way, by using this model, you agree to completely indemnify me. \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..8c6dcd2 --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "_name_or_path": "airoboros-l2-13b-gpt4-1.4.1", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 13824, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 40, + "num_hidden_layers": 40, + "num_key_value_heads": 40, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.30.2", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..8e7fdfa --- /dev/null +++ b/generation_config.json @@ -0,0 +1,10 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "max_length": 4096, + "pad_token_id": 0, + "temperature": 0.9, + "top_p": 0.6, + "transformers_version": "4.30.2" +} diff --git a/pytorch_model-00001-of-00003.bin b/pytorch_model-00001-of-00003.bin new file mode 100644 index 0000000..773cc13 --- /dev/null +++ b/pytorch_model-00001-of-00003.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3135e4f8cbe260d832cc9faee76d66d89dad84c3287f6ef16c7e7006907993a +size 9948730542 diff --git a/pytorch_model-00002-of-00003.bin b/pytorch_model-00002-of-00003.bin new file mode 100644 index 0000000..7068353 --- /dev/null +++ b/pytorch_model-00002-of-00003.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5498062ed85c022d006216bb014515e7c4628407bcd5ec9b4dcd17c2f3a170be +size 9904167200 diff --git a/pytorch_model-00003-of-00003.bin b/pytorch_model-00003-of-00003.bin new file mode 100644 index 0000000..fc9911f --- /dev/null +++ b/pytorch_model-00003-of-00003.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f651f436f63648293989bc283ab30b8ddb8dbf9560363d2932919ea47d691f9 +size 6178984969 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..af59f83 --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92c31ad5e853e9a6660e248871f9bd0cd273518de7ec12ca893e1b1078c10898 +size 33444 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..451134b --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..21779d6 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcd04f0eadf90287bd26e1a183ac487d8a141b09b06aecb7725bbdd343640f2e +size 1842767 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..6c00c74 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..893bd98 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,32 @@ +{ + "bos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "clean_up_tokenization_spaces": false, + "eos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "legacy": false, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +}