MathGenie/MathCoder2-Llama-3-8B
Full fine-tune vs meta-llama/Meta-Llama-3-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1
5 derivatives checked
- bartowski/MathCoder2-Llama-3-8B-GGUF: Same weights, converted
- mradermacher/MathCoder2-Llama-3-8B-i1-GGUF: Quantization
- featherless-ai-quants/MathGenie-MathCoder2-Llama-3-8B-GGUF: Quantization
- mradermacher/MathCoder2-Llama-3-8B-GGUF: Same weights, converted
- mergekit-community/L3.1-Athena-d-8B: Full fine-tune