HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407
LoRA-style vs mistralai/Mistral-Nemo-Instruct-2407. 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 40 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 120/120, Attention 160/160, lm_head 0/1
14 derivatives checked
- mradermacher/Humanish-Mistral-Nemo-Instruct-2407-i1-GGUF: Quantization
- bartowski/Human-Like-Mistral-Nemo-Instruct-2407-GGUF: Same weights, converted
- mradermacher/Human-Like-Mistral-Nemo-Instruct-2407-i1-GGUF: Quantization
- mradermacher/Human-Like-Mistral-Nemo-Instruct-2407-GGUF: Quantization
- mradermacher/Humanish-Mistral-Nemo-Instruct-2407-GGUF: Quantization
- EldritchLabs/Human-Like-Mistral-Nemo-Instruct-2407-MPOA: Abliterated
- mergekit-community/MN-Hekate-Nyktipolos-17B: Full fine-tune
- mergekit-community/MN-Hekate-Kleidoukhos-12B: Full fine-tune
- mergekit-community/MN-Hekate-Deichteira-12B: Full fine-tune
- mergekit-community/MN-Hekate-Enodia-12B: Full fine-tune
- mergekit-community/MN-Hekate-Panopaia-12B: Full fine-tune
- yamatazen/EtherealAurora-12B-v3: Full fine-tune
- mergekit-community/MN-Hekate-Damnomeneia-17B: Full fine-tune
- yamatazen/EtherealNight-12B: Full fine-tune