commit 62717b99ee78412cba5efc97d70c3ebbd3bc23e3 Author: ModelHub XC Date: Tue Jul 14 08:19:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: harborwater/open-llama-3b-everythingLM-2048 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.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 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b5a6f22 --- /dev/null +++ b/README.md @@ -0,0 +1,143 @@ +--- +language: +- en +license: apache-2.0 +library_name: transformers +datasets: +- totally-not-an-llm/EverythingLM-data-V3 +model-index: +- name: open-llama-3b-everythingLM-2048 + results: + - task: + type: text-generation + name: Text Generation + dataset: + name: AI2 Reasoning Challenge (25-Shot) + type: ai2_arc + config: ARC-Challenge + split: test + args: + num_few_shot: 25 + metrics: + - type: acc_norm + value: 42.75 + name: normalized accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=harborwater/open-llama-3b-everythingLM-2048 + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: HellaSwag (10-Shot) + type: hellaswag + split: validation + args: + num_few_shot: 10 + metrics: + - type: acc_norm + value: 71.72 + name: normalized accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=harborwater/open-llama-3b-everythingLM-2048 + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: MMLU (5-Shot) + type: cais/mmlu + config: all + split: test + args: + num_few_shot: 5 + metrics: + - type: acc + value: 27.16 + name: accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=harborwater/open-llama-3b-everythingLM-2048 + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: TruthfulQA (0-shot) + type: truthful_qa + config: multiple_choice + split: validation + args: + num_few_shot: 0 + metrics: + - type: mc2 + value: 34.26 + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=harborwater/open-llama-3b-everythingLM-2048 + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: Winogrande (5-shot) + type: winogrande + config: winogrande_xl + split: validation + args: + num_few_shot: 5 + metrics: + - type: acc + value: 66.3 + name: accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=harborwater/open-llama-3b-everythingLM-2048 + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: GSM8k (5-shot) + type: gsm8k + config: main + split: test + args: + num_few_shot: 5 + metrics: + - type: acc + value: 1.52 + name: accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=harborwater/open-llama-3b-everythingLM-2048 + name: Open LLM Leaderboard +--- + +Trained on 2 epochs on the EverythingLM-data-V3 dataset. + +This model uses the alpaca prompt format: +``` +Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request. + +### Instruction: +Instruction + +### Input: +Input + +### Response: +``` + +[Built with Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) + + +# [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_harborwater__open-llama-3b-everythingLM-2048) + +| Metric |Value| +|---------------------------------|----:| +|Avg. |40.62| +|AI2 Reasoning Challenge (25-Shot)|42.75| +|HellaSwag (10-Shot) |71.72| +|MMLU (5-Shot) |27.16| +|TruthfulQA (0-shot) |34.26| +|Winogrande (5-shot) |66.30| +|GSM8k (5-shot) | 1.52| + diff --git a/config.json b/config.json new file mode 100644 index 0000000..1cec8e2 --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "_name_or_path": "openlm-research/open_llama_3b_v2", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 3200, + "initializer_range": 0.02, + "intermediate_size": 8640, + "max_position_embeddings": 2048, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 26, + "num_key_value_heads": 32, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.31.0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..2b10330 --- /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" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..50c20ff --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b16f53514c83606200e78926825ff3e79c5b8aa4fad4d2681a1755d67ebcd00 +size 6852982288 diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..3cd8ea7 --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92fdf298eb876a7fb5f02151f60ebd15a8904a1e5384c714fe3141b7b937f1b8 +size 6853038093 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..1c141cf --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1 @@ +{"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}} \ No newline at end of file diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..98866ff --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91b289e85fa20fd375d8b33dc12f77616f18abc6359804471d1fafcb425fecb8 +size 511574 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..75ff0f5 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1 @@ +{"add_bos_token": true, "add_eos_token": false, "model_max_length": 2048, "pad_token": null, "sp_model_kwargs": {}, "tokenizer_class": "LlamaTokenizer", "clean_up_tokenization_spaces": false, "bos_token": {"__type": "AddedToken", "content": "", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false}, "eos_token": {"__type": "AddedToken", "content": "", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false}, "unk_token": {"__type": "AddedToken", "content": "", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false}} \ No newline at end of file