Meet7_0.6b_Exp_Thinking

Meet7 0.6B — Experimental Thinking

A thinking trained variant of Meet7 0.6B Experimental, re-enabling Qwen3's built-in chain-of-thought reasoning at inference time.

Note: At 0.6B scale, thinking mode does not improve benchmark performance. (Except over base model which was tested with reasoning.) The model still lacks sufficient capacity to reason coherently across extended thought chains. For best results, use Meet7 Experimental without thinking mode, or Meet7 0.6B if BoolQ-style QA is your primary use case.

Benchmarks

<img src="https://cdn-uploads.huggingface.co/production/uploads/6466047a326128fd2c693cfa/KGguR5E4-kmXnxXCIZ-T5.png" width="750"/>

0-shot evaluation across all four models in the Meet7 family. Scores are acc_norm.

<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>

Meet7 Model Family

Model Details

Trained 2x faster with Unsloth and Hugging Face TRL.

<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>