kaist-ai/janus-orpo-7b

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

Tensors changed: Embeddings 1/1, Norms 13/65, MLP 96/96, Attention 128/128, lm_head 1/1

3 derivatives checked

• mradermacher/janus-orpo-7b-GGUF: Same weights, converted
• mradermacher/janus-orpo-7b-i1-GGUF: Quantization
• tensorblock/janus-orpo-7b-GGUF: Quantization

On the Hub · Downloads on Model Pulse