argilla/CapybaraHermes-2.5-Mistral-7B
LoRA-style vs teknium/OpenHermes-2.5-Mistral-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
9 derivatives checked
- TheBloke/CapybaraHermes-2.5-Mistral-7B-GGUF: Quantization
- mradermacher/CapybaraHermes-2.5-Mistral-7B-i1-GGUF: Quantization
- mradermacher/CapybaraHermes-2.5-Mistral-7B-GGUF: Quantization
- newsletter/CapybaraHermes-2.5-Mistral-7B-Q6_K-GGUF: Quantization
- Yuma42/KangalKhan-Ruby-7B-Fixed: LoRA-style
- Yuma42/KangalKhan-RawEmerald-7B: Full fine-tune
- Yuma42/KangalKhan-Sapphire-7B: LoRA-style
- Goekdeniz-Guelmez/J.O.S.I.E.3-Beta11-7B-slerp: Full fine-tune
- Cas-Warehouse/UltraHermes-Merge: Full fine-tune
1 other repos hold byte-for-byte identical weight files.