From 5a8667ac3b4cc9eac5c26b1439187964457955ac Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Thu, 2 Jul 2026 11:56:12 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: camel-ai/CAMEL-33B-Combined-Data Source: Original Platform --- .gitattributes | 47 ++++++++++++++++++++++++++++++++ README.md | 21 ++++++++++++++ config.json | 23 ++++++++++++++++ configuration.json | 1 + generation_config.json | 7 +++++ pytorch_model-00001-of-00007.bin | 3 ++ pytorch_model-00002-of-00007.bin | 3 ++ pytorch_model-00003-of-00007.bin | 3 ++ pytorch_model-00004-of-00007.bin | 3 ++ pytorch_model-00005-of-00007.bin | 3 ++ pytorch_model-00006-of-00007.bin | 3 ++ pytorch_model-00007-of-00007.bin | 3 ++ pytorch_model.bin.index.json | 3 ++ special_tokens_map.json | 23 ++++++++++++++++ tokenizer.model | 3 ++ tokenizer_config.json | 33 ++++++++++++++++++++++ 16 files changed, 182 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 config.json create mode 100644 configuration.json create mode 100644 generation_config.json create mode 100644 pytorch_model-00001-of-00007.bin create mode 100644 pytorch_model-00002-of-00007.bin create mode 100644 pytorch_model-00003-of-00007.bin create mode 100644 pytorch_model-00004-of-00007.bin create mode 100644 pytorch_model-00005-of-00007.bin create mode 100644 pytorch_model-00006-of-00007.bin create mode 100644 pytorch_model-00007-of-00007.bin create mode 100644 pytorch_model.bin.index.json create mode 100644 special_tokens_map.json create mode 100644 tokenizer.model create mode 100644 tokenizer_config.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53d7257 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..46e2481 --- /dev/null +++ b/README.md @@ -0,0 +1,21 @@ +CAMEL-33B-Combined-Data is a chat large language model obtained by finetuning LLaMA-33B model on a total of 229K conversations collected through our CAMEL framework, 100K English public conversations from ShareGPT that can be found here, and 52K instructions from Alpaca dataset that can be found here. We evaluate our model offline using EleutherAI's language model evaluation harness used by Huggingface's Open LLM Benchmark. CAMEL-33B scores an average of 64.2. + +Regarding the prompt format, we follow the same prompt as LMSYS's [FastChat](https://github.com/lm-sys/FastChat/tree/main) Vicuna-13B-1.1 conversation template. It assumes a conversation between a user and AI assistant seperated by a <\/s> at the end of every role message. More details can be found [here](https://github.com/lm-sys/FastChat/blob/daa2b9abe20597ebf34dc5df164d450456610c74/fastchat/conversation.py#LL247C1-L247C1). + +--- +license: cc-by-nc-4.0 +--- + +# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) +Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_camel-ai__CAMEL-33B-Combined-Data) + +| Metric | Value | +|-----------------------|---------------------------| +| Avg. | 50.79 | +| ARC (25-shot) | 62.97 | +| HellaSwag (10-shot) | 83.83 | +| MMLU (5-shot) | 58.98 | +| TruthfulQA (0-shot) | 50.21 | +| Winogrande (5-shot) | 78.3 | +| GSM8K (5-shot) | 14.1 | +| DROP (3-shot) | 7.12 | diff --git a/config.json b/config.json new file mode 100644 index 0000000..8347195 --- /dev/null +++ b/config.json @@ -0,0 +1,23 @@ +{ + "_name_or_path": "../FastChat/llama-hf-30B/", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 6656, + "initializer_range": 0.02, + "intermediate_size": 17920, + "max_position_embeddings": 2048, + "model_type": "llama", + "num_attention_heads": 52, + "num_hidden_layers": 60, + "pad_token_id": 0, + "rms_norm_eps": 1e-06, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.31.0.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..505e57a --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "pad_token_id": 0, + "transformers_version": "4.31.0.dev0" +} diff --git a/pytorch_model-00001-of-00007.bin b/pytorch_model-00001-of-00007.bin new file mode 100644 index 0000000..398b924 --- /dev/null +++ b/pytorch_model-00001-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0db0b6596712c9bf6014e647cb90ec0ed0e47581a5cbfa20ce248f2eaf3d7bb +size 9818324627 diff --git a/pytorch_model-00002-of-00007.bin b/pytorch_model-00002-of-00007.bin new file mode 100644 index 0000000..007edd0 --- /dev/null +++ b/pytorch_model-00002-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5d6c45e6e6a8265d6f453246097313cf144ab624aeec5c108c169f261425f25 +size 9958102743 diff --git a/pytorch_model-00003-of-00007.bin b/pytorch_model-00003-of-00007.bin new file mode 100644 index 0000000..d39e191 --- /dev/null +++ b/pytorch_model-00003-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:451de1081a51b0c5b7fb5be3512245a16c5fe699781ef7861a9bb0bb3a67efeb +size 9896734715 diff --git a/pytorch_model-00004-of-00007.bin b/pytorch_model-00004-of-00007.bin new file mode 100644 index 0000000..8c15bff --- /dev/null +++ b/pytorch_model-00004-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c12dea28d88bcff7b3516b388c141b0b7e9e7c9f8c3f9b11a25849cda688caba +size 9869470481 diff --git a/pytorch_model-00005-of-00007.bin b/pytorch_model-00005-of-00007.bin new file mode 100644 index 0000000..6ad5be9 --- /dev/null +++ b/pytorch_model-00005-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73c3af30f78273bdaab66d4a3a7cccf5e6c737c9f64b5fa4b16358c4ddb3eb98 +size 9869470445 diff --git a/pytorch_model-00006-of-00007.bin b/pytorch_model-00006-of-00007.bin new file mode 100644 index 0000000..e1d4dcf --- /dev/null +++ b/pytorch_model-00006-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac98c7cd2da947b9162901ff29e96bb0fb701a15c6f615c3ebfe4ac58d82a3ce +size 9958102743 diff --git a/pytorch_model-00007-of-00007.bin b/pytorch_model-00007-of-00007.bin new file mode 100644 index 0000000..71fa5f4 --- /dev/null +++ b/pytorch_model-00007-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35ddfc8288d67291e8cb929ceec4f23569164f99740cf4bab68afe4529e4d30b +size 5900895281 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..84bd4c2 --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:132d90ebefb682313eb66bf40238fbe1eb0a18225f75b569cfadcb533ff4e0b6 +size 50084 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/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..400e3de --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,33 @@ +{ + "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 + } +}