crestf411/MS-sunfall-v0.7.0
LoRA-style vs mistralai/Mistral-Small-Instruct-2409. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 56 of 56 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 168/168, Attention 224/224, lm_head 0/1
3 derivatives checked
- bartowski/MS-sunfall-v0.7.0-GGUF: Same weights, converted
- mradermacher/MS-sunfall-v0.7.0-i1-GGUF: Quantization
- mradermacher/MS-sunfall-v0.7.0-GGUF: Quantization