HuggingFaceTB/SmolLM-360M-Instruct
Full fine-tune vs HuggingFaceTB/SmolLM-360M. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128
12 derivatives checked
- mradermacher/SmolLM-360M-Instruct-GGUF: Full fine-tune
- second-state/SmolLM-360M-Instruct-GGUF: Full fine-tune
- QuantFactory/Biggie-SmoLlm-0.4B-GGUF: Full fine-tune
- MaziyarPanahi/SmolLM-360M-Instruct-GGUF: Full fine-tune
- mradermacher/SmolLM-360M-Instruct-i1-GGUF: Quantization
- nisten/Biggie-SmoLlm-0.4B: Full fine-tune
- arzaan789/smollm-360m-uncensored: Full fine-tune
- gaianet/SmolLM-360M-Instruct-GGUF: Full fine-tune
- Felladrin/gguf-SmolLM-360M-Instruct: Full fine-tune
- unsloth/SmolLM-360M-Instruct-bnb-4bit: Quantization
- LSXPrime/ProseFlow-v1-360M-Instruct: Full fine-tune
- aistrova/SmolLM-360M-Instruct-8k-ctx: Identical copy
3 other repos hold byte-for-byte identical weight files.