MasterControlAIML/DeepSeek-R1-Strategy-Qwen-2.5-1.5b-Unstructured-To-Structured
Partial fine-tune vs Qwen/Qwen2.5-1.5B-Instruct. Partial change: 85% of the weights changed (attention, mlp, norms), in 28 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 32/57, MLP 84/84, Attention 174/196
4 derivatives checked
- mradermacher/DeepSeek-R1-Strategy-Qwen-2.5-1.5b-Unstructured-To-Structured-GGUF: Same weights, converted
- MasterControlAIML/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-GGUF: Partial fine-tune
- tensorblock/DeepSeek-R1-Strategy-Qwen-2.5-1.5b-Unstructured-To-Structured-GGUF: Quantization
- MasterControlAIML/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured: LoRA-style