Intel/neural-chat-7b-v3-3
LoRA-style vs Intel/neural-chat-7b-v3-1. 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
11 derivatives checked
- TheBloke/neural-chat-7B-v3-3-GGUF: Quantization
- mradermacher/neural-chat-7b-v3-3-GGUF: Same weights, converted
- mradermacher/neural-chat-7b-v3-3-i1-GGUF: Quantization
- second-state/Neural-Chat-7B-v3-3-GGUF: Quantization
- OpenPipe/mistral-ft-optimized-1227: Full fine-tune
- tensorblock/neural-chat-7b-v3-3-GGUF: Quantization
- mlabonne/Darewin-7B-v2: Full fine-tune
- mlabonne/Darewin-7B: Full fine-tune
- fhai50032/SamChat: Full fine-tune
- giraffe176/WestLake_Noromaid_OpenHermes_neural-chatv0.1: Full fine-tune
- Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp: Full fine-tune