nbeerbower/Hemlock-Jan-code-4B
LoRA-style vs janhq/Jan-code-4b. 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 36 of 36 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Norms 0/145, MLP 108/108, Attention 144/144, Embeddings 0/1
2 derivatives checked
- mradermacher/Hemlock-Jan-code-4B-i1-GGUF: Quantization
- mradermacher/Hemlock-Jan-code-4B-GGUF: Same weights, converted