pragmaticcs/PentaCoder-9B
Full fine-tune (fewer layers) vs Jackrong/Qwopus3.5-9B-Coder. pragmaticcs/PentaCoder-9B matches part of Jackrong/Qwopus3.5-9B-Coder (427 of its 775 tensors; the rest of Jackrong/Qwopus3.5-9B-Coder has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, MLP 96/96, Attention 188/224, Norms 85/105
4 derivatives checked
- mradermacher/PentaCoder-9B-i1-GGUF: Quantization
- pragmaticcs/PentaCoder-9B-i1-GGUF: Quantization
- mradermacher/PentaCoder-9B-GGUF: Same weights, converted
- pragmaticcs/PentaCoder-9B-GGUF: Quantization