LLM Name | SmolLM 135M Instruct 4bit |
Repository ๐ค | https://huggingface.co/mlx-community/SmolLM-135M-Instruct-4bit |
Model Size | 135m |
Required VRAM | 0.1 GB |
Updated | 2024-11-07 |
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 135M Instruct 8bit | 2K / 0.1 GB | 18 | 2 |
SmolLM 135M Instruct Fp16 | 2K / 0.3 GB | 13 | 2 |
SmolLM2 135M Instruct | 8K / 0.3 GB | 4861 | 48 |
SmolLM2 Prompt Enhance | 8K / 0.5 GB | 32 | 4 |
SmolLM2 135M Instruct | 8K / 0.3 GB | 42 | 0 |
SmolLM 135M Instruct | 2K / 0.3 GB | 26856 | 95 |
... Instruct Layer Pruned 90M Raw | 2K / 0.2 GB | 255 | 1 |
...5m Skunkworks Reasoning Alpaca | 2K / 0.3 GB | 19 | 0 |
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