commit 694a105aea003eae33994325862d173df4c35bab Author: ModelHub XC Date: Tue Jul 14 17:17:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: jondurbin/airoboros-7b-gpt4-1.2 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..84d05e2 --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +license: cc-by-nc-4.0 +datasets: +- jondurbin/airoboros-gpt4-1.2 +--- + +### Overview + +This is a qlora fine-tuned 7b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros + +This is mostly an extension of [1.1](https://huggingface.co/jondurbin/airoboros-7b-gpt4-1.1), but with thousands of new training data and an update to allow "PLAINFORMAT" at the end of coding prompts to just print the code without backticks or explanations/usage/etc. + +The dataset used to fine-tune this model is available [here](https://huggingface.co/datasets/jondurbin/airoboros-gpt4-1.2), with a specific focus on: +- coding +- math/reasoning (using orca style ELI5 instruction/response pairs) +- trivia +- role playing +- multiple choice and fill-in-the-blank +- context-obedient question answering +- theory of mind +- misc/general + +This model was fine-tuned with a fork of [qlora](https://github.com/jondurbin/qlora), which among other things was updated to use a slightly modified vicuna template to be compatible with the previous versions: + +``` +A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. USER: [prompt] ASSISTANT: +``` + +So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon). + +### Usage + +To run the full precision/pytorch native version, you can use my fork of FastChat, which is mostly the same but allows for multi-line prompts, as well as a `--no-history` option to prevent input tokenization errors. +``` +pip install git+https://github.com/jondurbin/FastChat +``` + +Be sure you are pulling the latest branch! + +Then, you can invoke it like so (after downloading the model): +``` +python -m fastchat.serve.cli \ + --model-path airoboros-7b-gpt4-1.2 \ + --temperature 0.5 \ + --max-new-tokens 2048 \ + --no-history +``` + +Alternatively, please check out TheBloke's quantized versions: + +- https://huggingface.co/TheBloke/airoboros-7B-gpt4-1.2-GPTQ +- https://huggingface.co/TheBloke/airoboros-7B-gpt4-1.2-GGML + +### Coding updates from gpt4/1.1: + +I added a few hundred instruction/response pairs to the training data with "PLAINFORMAT" as a single, all caps term at the end of the normal instructions, which produce plain text output instead of markdown/backtick code formatting. + +It's not guaranteed to work all the time, but mostly it does seem to work as expected. + +So for example, instead of: +``` +Implement the Snake game in python. +``` + +You would use: +``` +Implement the Snake game in python. PLAINFORMAT +``` + +### Other updates from gpt4/1.1: + +- Several hundred role-playing data. +- A few thousand ORCA style reasoning/math questions with ELI5 prompts to generate the responses (should not be needed in your prompts to this model however, just ask the question). +- Many more coding examples in various languages, including some that use specific libraries (pandas, numpy, tensorflow, etc.) + +### Usage and License Notices + +All airoboros models and datasets are intended and licensed for research use only. I've used the 'cc-nc-4.0' license, but really it is subject to a custom/special license because: + +- the base model is LLaMa, which has it's own special research license +- the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai + +So, to reiterate: this model (and datasets) cannot be used commercially. \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..aa2e482 --- /dev/null +++ b/config.json @@ -0,0 +1,24 @@ +{ + "_name_or_path": "/data/llama-7b-hf", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 0, + "eos_token_id": 1, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_position_embeddings": 2048, + "max_sequence_length": 2048, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "pad_token_id": -1, + "rms_norm_eps": 1e-06, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.30.0.dev0", + "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..f564ee0 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 0, + "eos_token_id": 1, + "pad_token_id": -1, + "transformers_version": "4.30.0.dev0" +} diff --git a/pytorch_model-00001-of-00003.bin b/pytorch_model-00001-of-00003.bin new file mode 100644 index 0000000..06f681d --- /dev/null +++ b/pytorch_model-00001-of-00003.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f759da59a427dab2bf0f7f620098e6c642d44558c362fa75a6017992ddd9242 +size 9877991186 diff --git a/pytorch_model-00002-of-00003.bin b/pytorch_model-00002-of-00003.bin new file mode 100644 index 0000000..a883ca0 --- /dev/null +++ b/pytorch_model-00002-of-00003.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebcaa68f9db3fb97a1bb5bdb43d09347553062904bbfbc98f26335dd801e4467 +size 9894802678 diff --git a/pytorch_model-00003-of-00003.bin b/pytorch_model-00003-of-00003.bin new file mode 100644 index 0000000..82e5042 --- /dev/null +++ b/pytorch_model-00003-of-00003.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ecf089962b36583469eb73ccac90648d9e4b350778413b1bcb466b41fa1633a +size 7180991865 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..b83466f --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:773618361c0b7570f0ea528dc07b9c127018231316a548ec4ddfb87cd0dcecf0 +size 26788 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..f928b24 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..d8b7a78 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a40299bfde8716e0d57648952665d606c5319685133c03c944797edbed230198 +size 1842765 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..764a9f6 --- /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": 4096, + "pad_token": null, + "padding_side": "right", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +}