InferenceIllusionist/Excalibur-7b

Full fine-tune vs InferenceIllusionist/Magic-Dolphin-7b. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

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

3 derivatives checked

• mradermacher/Excalibur-7b-i1-GGUF: Quantization
• InferenceIllusionist/Excalibur-7b-DPO: LoRA-style
• flammenai/flammen27-mistral-7B: Full fine-tune

On the Hub · Downloads on Model Pulse