DavidAU/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning
LoRA-style vs allura-forge/Llama-3.3-8B-Instruct. 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
5 derivatives checked
- mradermacher/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-i1-GGUF: Quantization
- mradermacher/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-GGUF: Same weights, converted
- genai-archive/DavidAU__Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-mlx-mxfp4: Quantization
- LoveGlaze/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-Q4_K_M-GGUF: Quantization
- mondk/claude-llama-8B-think: LoRA-style
1 other repos hold byte-for-byte identical weight files.