Intel/neural-chat-7b-v3-1
LoRA-style vs mistralai/Mistral-7B-v0.1. 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
7 derivatives checked
- Intel/neural-chat-7b-v3-3: LoRA-style
- TheBloke/neural-chat-7B-v3-1-GGUF: Quantization
- mradermacher/neural-chat-7b-v3-1-GGUF: Quantization
- second-state/Neural-Chat-7B-v3-1-GGUF: Quantization
- MaziyarPanahi/neural-chat-7b-v3-1-GGUF: Quantization
- tensorblock/neural-chat-7b-v3-1-GGUF: Quantization
- giraffe176/Open_Neural_Monarch_Maidv0.1: Full fine-tune
1 other repos hold byte-for-byte identical weight files.