Locutusque/TinyMistral-248M-v2-Instruct

Full fine-tune vs Locutusque/TinyMistral-248M-v2. Fine-tune: 100% of the weights changed, across 12 of 12 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 0/25, MLP 36/36, Attention 48/48

3 derivatives checked

• M4-ai/TinyMistral-248M-v2-Instruct-GGUF: Quantization
• mradermacher/TinyMistral-248M-v2-Instruct-GGUF: Same weights, converted
• mradermacher/TinyMistral-248M-v2-Instruct-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse