TheDrummer/Snowpiercer-15B-v2
LoRA-style vs SillyTilly/ServiceNow-AI-Apriel-Nemotron-15b-Thinker-Chatml. 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 50 of 50 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/101, MLP 150/150, Attention 200/200
3 derivatives checked
- bartowski/TheDrummer_Snowpiercer-15B-v2-GGUF: Same weights, converted
- mradermacher/Snowpiercer-15B-v2-i1-GGUF: Quantization
- mradermacher/Snowpiercer-15B-v2-GGUF: Quantization