Uncanned/Cammell-Twilight-v0.2-12B

Full fine-tune vs ChaoticNeutrals/Captain-Eris_Twilight-V0.420-12B. Fine-tune: 98% of the weights changed, across 40 of 40 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 38/81, MLP 117/120, Attention 156/160

3 derivatives checked

• mradermacher/Cammell-Twilight-v0.2-12B-i1-GGUF: Quantization
• Uncanned/Cammell-Twilight-v0.2-12B-GGUF-imatrix: Same weights, converted
• mradermacher/Cammell-Twilight-v0.2-12B-GGUF: Quantization

On the Hub · Downloads on Model Pulse