mlabonne/NeuralBeagle14-7B
LoRA-style vs mlabonne/Beagle14-7B. 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
17 derivatives checked
- MaziyarPanahi/NeuralBeagle14-7B-GGUF: Quantization
- second-state/NeuralBeagle14-7B-GGUF: Quantization
- backyardai/NeuralBeagle14-7B-GGUF: Same weights, converted
- TheBloke/NeuralBeagle14-7B-GGUF: Quantization
- mradermacher/NeuralBeagle14-7B-i1-GGUF: Quantization
- eren23/FrankenBeagle-SmallOverlap-test: Partial fine-tune
- mlabonne/NeuralBeagle14-7B-GGUF: Quantization
- mradermacher/NeuralBeagle14-7B-GGUF: Same weights, converted
- Dzluck/NeuralBeagle14-7B-GGUF: Quantization
- jsfs11/TurdusTrixBeagle-DARETIES-7B: Full fine-tune
- jsfs11/SnorkelWestBeagle-DARETIES-7B: Full fine-tune
- Kukedlc/NeuralKukedlc-7B-Labonned: Full fine-tune
- mlabonne/ArchBeagle-7B: Full fine-tune
- merge-crew/munin-neuralbeagle-7b-density-high: Full fine-tune
- mlabonne/Omnarch-7B: Full fine-tune
- merge-crew/munin-neuralbeagle-7b-density-very-low: Full fine-tune
- merge-crew/munin-neuralbeagle-7b-density-low: Full fine-tune
1 other repos hold byte-for-byte identical weight files.