agentica-org/DeepCoder-14B-Preview
Partial fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Qwen-14B. Partial change: 89% of the weights changed (attention, mlp, norms), in 48 of 48 layers.
Tensors changed: Embeddings 0/1, Attention 336/336, MLP 144/144, Norms 92/97, lm_head 0/1
6 derivatives checked
- bartowski/agentica-org_DeepCoder-14B-Preview-GGUF: Same weights, converted
- Joumdane/DeepCoder-14B-Preview-GGUF: Same weights, converted
- mradermacher/DeepCoder-14B-Preview-GGUF: Quantization
- DevQuasar-12/agentica-org.DeepCoder-14B-Preview-GGUF: Same weights, converted
- lmstudio-community/DeepCoder-14B-Preview-GGUF: Full fine-tune
- EpistemeAI/SAI-DeepCoder-14B-Preview-v1.0: LoRA-style