LLM Name | SmolLM 1.7B Instruct 4bit |
Repository ๐ค | https://huggingface.co/mlx-community/SmolLM-1.7B-Instruct-4bit |
Model Size | 1.7b |
Required VRAM | 1 GB |
Updated | 2024-11-21 |
Maintainer | mlx-community |
Model Type | llama |
Instruction-Based | Yes |
Model Files | |
Supported Languages | en |
Quantization Type | 4bit |
Model Architecture | LlamaForCausalLM |
License | apache-2.0 |
Context Length | 2048 |
Model Max Length | 2048 |
Transformers Version | 4.42.3 |
Tokenizer Class | GPT2Tokenizer |
Padding Token | <|im_end|> |
Vocabulary Size | 49152 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
SmolLM 1.7B Instruct 8bit | 2K / 1.8 GB | 23 | 1 |
SmolLM2 1.7B Instruct | 8K / 3.4 GB | 69219 | 345 |
SmolLM2 1.7 Persona | 8K / 3.5 GB | 18 | 0 |
SmolLM2 1.7B Instruct | 8K / 3.4 GB | 611 | 3 |
SmolLM2 1.7B Instruct | 8K / 3.4 GB | 185 | 3 |
...uerkrautLM SOLAR Instruct GPTQ | 8K / 6 GB | 9 | 2 |
...auerkrautLM SOLAR Instruct AWQ | 8K / 6 GB | 1 | 2 |
...auerkrautLM SOLAR Instruct AWQ | 8K / 6 GB | 6 | 0 |
Sakura SOLAR Instruct GPTQ | 4K / 6 GB | 5 | 3 |
Sakura SOLAR Instruct AWQ | 4K / 6 GB | 4 | 1 |
๐ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐