BEE-spoke-data/smol_llama-220M-openhermes
Partial fine-tune vs BEE-spoke-data/smol_llama-220M-GQA. Partial change: 85% of the weights changed (attention, lm_head, mlp), in 10 of 10 layers.
Tensors changed: lm_head 1/1, Embeddings 0/1, Norms 0/21, MLP 30/30, Attention 40/40
5 derivatives checked
- Felladrin/gguf-smol_llama-220M-openhermes: Same weights, converted
- afrideva/smol_llama-220M-openhermes-GGUF: Same weights, converted
- mradermacher/smol_llama-220M-openhermes-i1-GGUF: Quantization
- BEE-spoke-data/zephyr-220m-sft-full: Partial fine-tune
- mradermacher/smol_llama-220M-openhermes-GGUF: Same weights, converted