commit 0fe7c83063005ae347a49904f528bc010fe429f1 Author: ModelHub XC Date: Sat Apr 11 13:56:03 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Ma7ee7/Meet7_0.6b_Exp_Q8 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..493219f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.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 +Meet7_0.6b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Meet7_0.6b.Q8_0.gguf b/Meet7_0.6b.Q8_0.gguf new file mode 100644 index 0000000..9b1353a --- /dev/null +++ b/Meet7_0.6b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8703b7031a494561db4672e9c44f1c1633843c5d8444907b1b6e01f378321a6 +size 639446624 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d83698f --- /dev/null +++ b/README.md @@ -0,0 +1,60 @@ +--- +base_model: Ma7ee7/Meet7_0.6b +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3 +license: apache-2.0 +language: +- en +--- + +# Meet7 0.6B — Experimental + +A continued fine-tune of [Meet7 0.6B](https://huggingface.co/Ma7ee7/Meet7_0.6b), trained at a lower learning rate on the same 600-sample dataset. Trades Meet7's sharp BoolQ spike for more balanced commonsense and reasoning gains across the board. + +## Benchmarks + + + +0-shot evaluation, scores are `acc_norm`. + +| Task | Qwen3-0.6B (Base) | Meet7 0.6B | Experimental | Δ vs Base | +|------|:-----------------:|:----------:|:------------:|:---------:| +| BoolQ | 0.3798 | **0.5554** | 0.3991 | +01.93% | +| ARC Easy | 0.3384 | 0.3952 | **0.3965** | +05.81% | +| ARC Challenge | 0.2841 | **0.3285** | 0.3259 | +04.18% | +| HellaSwag | 0.3981 | 0.4205 | **0.4265** | +02.84% | +| PIQA | 0.6338 | 0.6583 | **0.6687** | +03.49% | +| Winogrande | 0.5225 | 0.5201 | **0.5304** | +00.79% | + +
+What these measure + +- **BoolQ** — Reading comprehension and yes/no factual grounding +- **ARC Easy / Challenge** — Grade-school science reasoning; Challenge is the retrieval-resistant subset +- **HellaSwag** — Commonsense sentence completion +- **PIQA** — Physical world intuition +- **Winogrande** — Commonsense pronoun resolution + +
+ +## vs Meet7 0.6B + +This model is more **balanced** than Meet7. It outperforms Meet7 on HellaSwag, PIQA, and Winogrande — the physical and commonsense intuition tasks — at the cost of Meet7's large BoolQ advantage. If you need consistent commonsense reasoning, prefer this model. If yes/no QA is your primary use case, prefer Meet7. + +## Model Details + +| | | +|---|---| +| **Developed by** | Ma7ee7 | +| **License** | Apache-2.0 | +| **Base model** | Ma7ee7/Meet7_0.6b | +| **Original base** | unsloth/Qwen3-0.6B-unsloth-bnb-4bit | +| **Training samples** | 600 | +| **Training** | Continued LoRA fine-tune, lower LR | + +Trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Hugging Face TRL. + +[](https://github.com/unslothai/unsloth) \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..5953613 --- /dev/null +++ b/config.json @@ -0,0 +1,61 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "torch_dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 40960, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "pad_token_id": 151669, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "unsloth_version": "2026.3.4", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file