commit 5837e20a6e0394d13b52ab939d170db86f54f36e Author: ModelHub XC Date: Thu Jun 18 08:41:17 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: theprint/Conversely-Mistral-7B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4a96d95 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,51 @@ +*.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 +unsloth.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +unsloth.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +unsloth.F16.gguf filter=lfs diff=lfs merge=lfs -text +unsloth.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +unsloth.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +unsloth.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +unsloth.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +unsloth.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Conversely-Mistral-7B.F16.gguf filter=lfs diff=lfs merge=lfs -text +Conversely-Mistral-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Conversely-Mistral-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Conversely-Mistral-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Conversely-Mistral-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Conversely-Mistral-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Conversely-Mistral-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Conversely-Mistral-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Conversely-Mistral-7B.F16.gguf b/Conversely-Mistral-7B.F16.gguf new file mode 100644 index 0000000..4f2ea6f --- /dev/null +++ b/Conversely-Mistral-7B.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2e78124430a0e64da0975977c6eca8b9f4b985de81958f219a73db5fdd9dce5 +size 14497337216 diff --git a/Conversely-Mistral-7B.Q3_K_M.gguf b/Conversely-Mistral-7B.Q3_K_M.gguf new file mode 100644 index 0000000..872d293 --- /dev/null +++ b/Conversely-Mistral-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d7f67540dc7336c36a7c68720bef66aed13523326e13599995470db39243de6 +size 3522940800 diff --git a/Conversely-Mistral-7B.Q3_K_S.gguf b/Conversely-Mistral-7B.Q3_K_S.gguf new file mode 100644 index 0000000..4a13cd7 --- /dev/null +++ b/Conversely-Mistral-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7691608df4ae6043d3e3be90e0077190d158de86cf631fccbc7d33adc070b6e +size 3168522112 diff --git a/Conversely-Mistral-7B.Q4_K_M.gguf b/Conversely-Mistral-7B.Q4_K_M.gguf new file mode 100644 index 0000000..3304ba1 --- /dev/null +++ b/Conversely-Mistral-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:612a36e083d02838aa37f50622bdb09350d77c06ed66195f2cf973091951ecef +size 4372811648 diff --git a/Conversely-Mistral-7B.Q4_K_S.gguf b/Conversely-Mistral-7B.Q4_K_S.gguf new file mode 100644 index 0000000..cb52081 --- /dev/null +++ b/Conversely-Mistral-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0d538d79e6568a4181c3d2f646a72e618e7f9ad687f82387348eeaa507dda80 +size 4144746368 diff --git a/Conversely-Mistral-7B.Q5_K_M.gguf b/Conversely-Mistral-7B.Q5_K_M.gguf new file mode 100644 index 0000000..bbe744f --- /dev/null +++ b/Conversely-Mistral-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16b0d93a9d6863928421eee0f64abfd2bcd2282331533e27a817450b2e1fec6c +size 5136174976 diff --git a/Conversely-Mistral-7B.Q6_K.gguf b/Conversely-Mistral-7B.Q6_K.gguf new file mode 100644 index 0000000..d49fbfd --- /dev/null +++ b/Conversely-Mistral-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a475e2556d84d5c07db820f6b6506879cc82aa3c68cd6d95e2366eb0d440b271 +size 5947248512 diff --git a/Conversely-Mistral-7B.Q8_0.gguf b/Conversely-Mistral-7B.Q8_0.gguf new file mode 100644 index 0000000..320ace3 --- /dev/null +++ b/Conversely-Mistral-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a6d3f91f723e332b023d9ed80a167b428b890acf3c72950fe8904b95eeb9507 +size 7702564736 diff --git a/README.md b/README.md new file mode 100644 index 0000000..384b4a0 --- /dev/null +++ b/README.md @@ -0,0 +1,135 @@ +--- +language: +- en +license: apache-2.0 +tags: +- text-generation-inference +- transformers +- unsloth +- mistral +- trl +- theprint +- conversely +base_model: unsloth/mistral-7b-v0.3-bnb-4bit +datasets: +- theprint/Conversely +pipeline_tag: text-generation +model-index: +- name: Conversely-Mistral-7B + results: + - task: + type: text-generation + name: Text Generation + dataset: + name: IFEval (0-Shot) + type: HuggingFaceH4/ifeval + args: + num_few_shot: 0 + metrics: + - type: inst_level_strict_acc and prompt_level_strict_acc + value: 26.08 + name: strict accuracy + source: + url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/Conversely-Mistral-7B + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: BBH (3-Shot) + type: BBH + args: + num_few_shot: 3 + metrics: + - type: acc_norm + value: 25.71 + name: normalized accuracy + source: + url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/Conversely-Mistral-7B + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: MATH Lvl 5 (4-Shot) + type: hendrycks/competition_math + args: + num_few_shot: 4 + metrics: + - type: exact_match + value: 0.91 + name: exact match + source: + url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/Conversely-Mistral-7B + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: GPQA (0-shot) + type: Idavidrein/gpqa + args: + num_few_shot: 0 + metrics: + - type: acc_norm + value: 4.7 + name: acc_norm + source: + url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/Conversely-Mistral-7B + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: MuSR (0-shot) + type: TAUR-Lab/MuSR + args: + num_few_shot: 0 + metrics: + - type: acc_norm + value: 10.63 + name: acc_norm + source: + url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/Conversely-Mistral-7B + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: MMLU-PRO (5-shot) + type: TIGER-Lab/MMLU-Pro + config: main + split: test + args: + num_few_shot: 5 + metrics: + - type: acc + value: 20.29 + name: accuracy + source: + url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/Conversely-Mistral-7B + name: Open LLM Leaderboard +--- + +# Uploaded model + +- **Developed by:** theprint +- **License:** apache-2.0 +- **Finetuned from model :** unsloth/mistral-7b-v0.3-bnb-4bit + +This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. + +[](https://github.com/unslothai/unsloth) +# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) +Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_theprint__Conversely-Mistral-7B) + +| Metric |Value| +|-------------------|----:| +|Avg. |14.72| +|IFEval (0-Shot) |26.08| +|BBH (3-Shot) |25.71| +|MATH Lvl 5 (4-Shot)| 0.91| +|GPQA (0-shot) | 4.70| +|MuSR (0-shot) |10.63| +|MMLU-PRO (5-shot) |20.29| + diff --git a/adapter_config.json b/adapter_config.json new file mode 100644 index 0000000..0792e61 --- /dev/null +++ b/adapter_config.json @@ -0,0 +1,34 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "unsloth/mistral-7b-v0.3-bnb-4bit", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_dropout": 0, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "gate_proj", + "down_proj", + "k_proj", + "o_proj", + "up_proj", + "v_proj", + "q_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/adapter_model.safetensors b/adapter_model.safetensors new file mode 100644 index 0000000..9254f6f --- /dev/null +++ b/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a219efe1080c54bf43afcb3df951cd4e79eabab17b60424ab9bd0b437b3f4220 +size 167832240 diff --git a/config.json b/config.json new file mode 100644 index 0000000..9f0f76f --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +{ + "model_type": "mistral" +} \ No newline at end of file