DeepHat/DeepHat-V1-7B
Full fine-tune vs Qwen/Qwen2.5-Coder-7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 196/196, lm_head 1/1
15 derivatives checked
- bartowski/WhiteRabbitNeo_WhiteRabbitNeo-V3-7B-GGUF: Full fine-tune
- liodon-ai/DeepHat-V1-7B-imatrix-GGUF: Quantization
- mradermacher/DeepHat-V1-7B-GGUF: Same weights, converted
- mradermacher/WhiteRabbitNeo-V3-7B-i1-GGUF: Quantization
- mradermacher/WhiteRabbitNeo-V3-7B-GGUF: Same weights, converted
- KikoCis/DeepHat-V1-7B-GGUF: Quantization
- niemozeszwyswietlicnazwyuzytkownikaerror69/WhiteRabbitNeo_WhiteRabbitNeo-V3-7B-GGUF: Full fine-tune
- liodon-ai/DeepHat-V1-7B-FP8: Quantization
- tthoman79/WhiteRabbitNeo-V3-7B-mlx-8bit: Quantization
- Neandrthal/WhiteRabbitNeo-V3-7B-i1-GGUF: Quantization
- Otilde/DeepHat-V1-7B-Q8-MLX: Quantization
- jmainformatique/DeepHat-V1-7B-Q4_K_M-GGUF: Quantization
- VISHNUDHAT/DeepHat-V1-7B-Q4_K_M-GGUF: Quantization
- usermma/DeepHat-V1-7B-Heretic-Abliterated: Partial fine-tune
- Yukendiran/Liceron-SecOps-Model: Full fine-tune
10 other repos hold byte-for-byte identical weight files.