EpistemeAI/MathCoder-Llama3.1-8B
LoRA-style vs EpistemeAI/Math-Code-Llama3.1-8B. 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 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 96/96, Attention 128/128, lm_head 0/1
2 derivatives checked
- mradermacher/MathCoder-Llama3.1-8B-GGUF: Same weights, converted
- EpistemeAI/MathCoder-Llama3.1-8B-cot: LoRA-style