trashpanda-org/MS-24B-Instruct-Mullein-v0

Full fine-tune vs unsloth/Mistral-Small-24B-Base-2501. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/1, Norms 2/81, MLP 120/120, Attention 160/160, lm_head 1/1

2 derivatives checked

• mradermacher/MS-24B-Instruct-Mullein-v0-i1-GGUF: Quantization
• mradermacher/MS-24B-Instruct-Mullein-v0-GGUF: Quantization

On the Hub · Downloads on Model Pulse