From e42da32ce9d73de93d71402abafc299bf2a145dd Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 5 Jul 2026 15:07:17 +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: acrastt/Puma-3B Source: Original Platform --- .gitattributes | 35 +++++++++ README.md | 156 ++++++++++++++++++++++++++++++++++++++++ config.json | 23 ++++++ generation_config.json | 7 ++ model.safetensors | 3 + pytorch_model.bin | 3 + special_tokens_map.json | 1 + tokenizer.model | 3 + tokenizer_config.json | 1 + 9 files changed, 232 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 config.json create mode 100644 generation_config.json create mode 100644 model.safetensors create mode 100644 pytorch_model.bin 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..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..73467f7 --- /dev/null +++ b/README.md @@ -0,0 +1,156 @@ +--- +language: +- en +license: apache-2.0 +library_name: transformers +datasets: +- totally-not-an-llm/sharegpt-hyperfiltered-3k +pipeline_tag: text-generation +model-index: +- name: Puma-3B + 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: 41.3 + name: normalized accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Puma-3B + 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: 71.85 + name: normalized accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Puma-3B + 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: 27.51 + name: accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Puma-3B + 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: 38.34 + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Puma-3B + 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: 66.38 + name: accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Puma-3B + 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: 0.76 + name: accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Puma-3B + name: Open LLM Leaderboard +--- + +Buy Me A Coffee + +This is [OpenLLaMA 3B V2](https://huggingface.co/openlm-research/open_llama_3b_v2) finetuned on [ShareGPT Hyperfiltered](https://huggingface.co/datasets/totally-not-an-llm/sharegpt-hyperfiltered-3k) for 1 epochs. + +Prompt template: +``` +### HUMAN: +{prompt} + +### RESPONSE: + +``` +GGML quants available [here](https://huggingface.co/TheBloke/Puma-3b-GGML).
+GPTQ quants available [here](https://huggingface.co/TheBloke/Puma-3b-GPTQ). + +Note: Don't expect this model to be good, I was just starting out to finetune. So don't roast me please! + +# [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_acrastt__Puma-3B) + +| Metric | Value | +|-----------------------|---------------------------| +| Avg. | 41.02 | +| ARC (25-shot) | 41.3 | +| HellaSwag (10-shot) | 71.85 | +| MMLU (5-shot) | 27.51 | +| TruthfulQA (0-shot) | 38.34 | +| Winogrande (5-shot) | 66.38 | +| GSM8K (5-shot) | 0.76 | + +# [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_acrastt__Puma-3B) + +| Metric |Value| +|---------------------------------|----:| +|Avg. |41.02| +|AI2 Reasoning Challenge (25-Shot)|41.30| +|HellaSwag (10-Shot) |71.85| +|MMLU (5-Shot) |27.51| +|TruthfulQA (0-shot) |38.34| +|Winogrande (5-shot) |66.38| +|GSM8k (5-shot) | 0.76| + diff --git a/config.json b/config.json new file mode 100644 index 0000000..a3bf924 --- /dev/null +++ b/config.json @@ -0,0 +1,23 @@ +{ + "_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, + "pad_token_id": 0, + "rms_norm_eps": 1e-06, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.30.2", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..89c31b8 --- /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": "4.30.2" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..0620a27 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddda743de6be5e8ad4b8bd20bbf99efdfb66d5856e89b9732ec3c739477ee655 +size 6852982288 diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..00896b4 --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1566e139cf3781ae7b64d861e40118e3b88c37066960ea30dd1cc78cff0e4aab +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