sequelbox/Muse-Glimmer-30B-Tachibana-Agent
LoRA-style vs meta-models/Muse-Glimmer-30B. 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 52 of 52 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/3, Norms 0/413, MLP 156/358, Attention 260/660, lm_head 0/1, other 0/1
2 derivatives checked
- mradermacher/Muse-Glimmer-30B-Tachibana-Agent-i1-GGUF: Quantization
- mradermacher/Muse-Glimmer-30B-Tachibana-Agent-GGUF: Quantization