botbotrobotics/CabraMistral7b

Full fine-tune vs mistralai/Mistral-7B-Instruct-v0.2. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 24/65, MLP 96/96, Attention 128/128, lm_head 1/1

3 derivatives checked

• mradermacher/CabraMistral7b-v2-GGUF: Quantization
• mradermacher/CabraMistral7b-i1-GGUF: Quantization
• mradermacher/CabraMistral7b-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse