Update README.md

README.md

@@ -1,20 +1,60 @@
 ---
+base_model: Ma7ee7/Meet7_0.6b
 tags:
-- gguf
-- llama.cpp
+- text-generation-inference
+- transformers
 - unsloth
-
+- qwen3
+license: apache-2.0
+language:
+- en
 ---
 
-# Meet7_0.6b_Exp_Q4_K_M : GGUF
+# 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
+
+<img src="https://cdn-uploads.huggingface.co/production/uploads/6466047a326128fd2c693cfa/KfI9qNkT6jPkuquBL39UT.png" width="600"/>
+
+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% |
+
+<details>
+<summary>What these measure</summary>
+
+- **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
+
+</details>
+
+## 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
 
-This model was finetuned and converted to GGUF format using [Unsloth](https://github.com/unslothai/unsloth).
+| | |
+|---|---|
+| **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 |
 
-**Example usage**:
-- For text only LLMs:    `llama-cli -hf Ma7ee7/Meet7_0.6b_Exp_Q4_K_M --jinja`
-- For multimodal models: `llama-mtmd-cli -hf Ma7ee7/Meet7_0.6b_Exp_Q4_K_M --jinja`
+Trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Hugging Face TRL.
 
-## Available Model files:
-- `Meet7_0.6b.Q4_K_M.gguf`
-This was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth)
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)