codefuse-ai/F2LLM-v2-330M
Full fine-tune vs codefuse-ai/F2LLM-v2-0.6B-Preview-Pruned-330M. Fine-tune: 100% of the weights changed, across 16 of 16 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 48/48, Attention 64/64
3 derivatives checked
- spelunk-cloud/F2LLM-v2-330M-Q8_0-GGUF: Quantization
- mradermacher/F2LLM-v2-330M-GGUF: Same weights, converted
- cstr/f2llm-v2-330m-GGUF: Not comparable yet
1 other repos hold byte-for-byte identical weight files.