HuggingFaceTB/SmolLM-1.7B-Instruct
Full fine-tune vs HuggingFaceTB/SmolLM-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
13 derivatives checked
- MaziyarPanahi/SmolLM-1.7B-Instruct-GGUF: Full fine-tune
- mradermacher/SmolLM-1.7B-Instruct-GGUF: Full fine-tune
- mradermacher/SmolLM-1.7B-Instruct-i1-GGUF: Quantization
- arzaan789/smollm-1.7b-uncensored: Full fine-tune
- RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16: Quantization
- unsloth/SmolLM-1.7B-Instruct-bnb-4bit: Quantization
- SandLogicTechnologies/SmolLM-1.7B-Instruct-GGUF: Full fine-tune
- prithivMLmods/SmolLM-1.7B-Instruct-GGUF: LoRA-style
- unsloth/SmolLM-1.7B-Instruct: Identical copy
- Ayansk11/FinSenti-SmolLM-1.7B: LoRA-style
- ericlewis/SmolLM-1.7B-Instruct-KTO-V2: Full fine-tune
- ericlewis/SmolLM-1.7B-Instruct-KTO: Full fine-tune
- openfree/TinyLlama-SmolLM: Different architecture
2 other repos hold byte-for-byte identical weight files.