unsloth/DeepSeek-R1-Distill-Llama-8B
Same weights, repacked vs deepseek-ai/DeepSeek-R1-Distill-Llama-8B. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Embeddings 0/1, Attention 0/128, MLP 0/96, Norms 0/65, lm_head 0/1
11 derivatives checked
- MANSTAGE/analysis-llm-v2: Quantization
- SURESHBEEKHANI/Deep-seek-R1-Medical-reasoning-SFT: Full fine-tune
- MaziyarPanahi/DeepSeek-R1-Distill-Llama-8B-GGUF: Same weights, converted
- BEncoderRT/medical_inference: Full fine-tune
- tensorblock/DeepSeek-R1-Distill-Llama-8B-GGUF: Quantization
- Kunakornjack/DeepSeek-R1-Distill-Llama-8B_synthetic_1: LoRA-style
- KAHRAMAN42/DeepSeek-R1-Farmer: LoRA-style
- natthawadee/DeepSeek-R1-Distill-Llama-text-to-sql: LoRA-style
- Fornit/DeepSeek-R1-Medical-COT-LORA: LoRA-style
- Melody923/DeepSeek-R1-Medicalai-923: LoRA-style
- Samarth2511/DS-Llama-8B-DA-med-both: LoRA-style
8 other repos hold byte-for-byte identical weight files.