HuggingFaceTB/SmolLM2-1.7B-Instruct
Full fine-tune vs HuggingFaceTB/SmolLM2-1.7B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 1/1, Norms 49/49, MLP 72/72, Attention 96/96
54 derivatives checked
- HuggingFaceTB/SmolVLM-Instruct: Full fine-tune (fewer layers)
- bartowski/SmolLM2-1.7B-Instruct-GGUF: Same weights, converted
- HuggingFaceTB/SmolLM2-1.7B-Instruct-GGUF: Quantization
- lmstudio-community/SmolLM2-1.7B-Instruct-GGUF: Quantization
- unsloth/SmolLM2-1.7B-Instruct: Same weights, repacked
- webAI-Official/TwIL-LM: LoRA-style
- unsloth/SmolLM2-1.7B-Instruct-GGUF: Same weights, converted
- MaziyarPanahi/SmolLM2-1.7B-Instruct-GGUF: Same weights, converted
- mradermacher/SmolLM2-1.7B-Instruct-i1-GGUF: Quantization
- second-state/SmolLM2-1.7B-Instruct-GGUF: Same weights, converted
- unsloth/SmolLM2-1.7B-Instruct-bnb-4bit: Quantization
- Mungert/SmolVLM-Instruct-GGUF: Full fine-tune
- arzaan789/smolm2-1.7b-uncensored: Full fine-tune
- HuggingFaceTB/SmolVLM-Base: Full fine-tune (fewer layers)
- mradermacher/SmolLM2-1.7B-Instruct-GGUF: Same weights, converted
- prithivMLmods/SmolLM2-1.7B-F32-GGUF: Same weights, converted
- Zynerji/Ektome-SmolLM2-1.7Bi-PristinelyUncensored: Abliterated
- tensorblock/SmolLM2-1.7B-Instruct-GGUF: Quantization
- ngxson/SmolLM2-1.7B-Instruct-Q4_K_M-GGUF: Quantization
- ElementMerc/smollm2-1.7b-abliterated: Abliterated
- neonforestmist/smolgpt-fables: LoRA-style
- HuggingFaceTB/SmolLM2-1.7B-Instruct-Q8-mlx: Quantization
- mlx-community/SmolLM2-1.7B-Instruct: Same weights, repacked
- taniota/Warlock-1.7B: LoRA-style
- DhruvalLabs/SmolLM2-1.7B-Instruct-GGUF: Quantization
- aa1602295777/SmolLM2-1.7B-Instruct-GGUF: Same weights, converted
- Alcoft/SmolLM2-1.7B-Instruct-GGUF: Same weights, converted
- HuggingFaceTB/SmolVLM-Synthetic: Full fine-tune (fewer layers)
- RunSLM-AI/SmolLM2-1.7B-Instruct-GGUF: Quantization
- gaianet/SmolLM2-1.7B-Instruct-GGUF: Same weights, converted
12 other repos hold byte-for-byte identical weight files.