Altworld/Hemmingway-1
Full fine-tune vs Qwen/Qwen3.8-27B. Fine-tune: 91% of the weights changed, across 64 of 64 layers.
Tensors changed: Norms 3/209, Attention 304/448, MLP 192/192, Embeddings 0/1, lm_head 0/1
46 derivatives checked
- mradermacher/Hemmingway-1-GGUF: Quantization
- bartowski/Altworld_Hemmingway-1-GGUF: Same weights, converted
- brainnxdomain/Hemmingway-1-Heretic-MTP-V3-Final-GGUF: Abliterated
- JohnDi/Hemmingway-1-Abliterated-Extreme-GGUF: Quantization
- Abiray/Hemmingway-1-heretic-GGUF: Quantization
- mradermacher/Hemmingway-1-i1-GGUF: Quantization
- brainnxdomain/Hemmingway-1-Heretic-MTP-GGUF: Abliterated
- botp/Altworld_Hemmingway-1-GGUF: Same weights, converted
- brainnxdomain/Hemmingway-1-Heretic-MTP-V3-VISION-Final-GGUF: Abliterated
- arelath/Hemmingway-1-heretic-GGUF: Quantization
- sixstringzen/Hemmingway-1-oQ6e-mtp: Quantization
- sixstringzen/Hemmingway-1-oQ4e-mtp: Quantization
- taniks/Hemmingway-1-Q4_K_M-GGUF: Quantization
- sixstringzen/Hemmingway-1-oQ8e-mtp: Quantization
- darrellbest/Hemmingway-1-GGUF: Same weights, converted
- sixstringzen/Hemmingway-1-oQ3.5e-mtp: Quantization
- sixstringzen/Hemmingway-1-oQ3e-mtp: Quantization
- sixstringzen/Hemmingway-1-oQ2e-mtp: Quantization
- ailexleon/Hemmingway-1-mlx-8Bit: Quantization
- zagy1234/ZeryEasyCoder27B: Partial fine-tune
- hermitdave/Hemmingway-1-oQ4e: Quantization
- hermitdave/Hemmingway-1-MLX-6bit: Quantization
- mlx-community/Hemmingway-1-OptiQ-4bit: Quantization
- taniks/Hemmingway-1-Q6_K-GGUF: Quantization
- brainnxdomain/Hemmingway-1-Heretic-MTP-GGUF-V2: Abliterated
- bjonor/Hemmingway-1-GPTQ-Int4-sym-G128-MTP-BF16: Quantization
- ailexleon/Hemmingway-1-mlx-4Bit: Quantization
- hermitdave/Hemmingway-1-MLX-4bit: Quantization
- theanupdas/Altworld_Hemmingway-1-GGUF: Same weights, converted
- richardyoung/Hemmingway-1-heretic: Abliterated