LLM Name | Quantized Granite 4bit 3B Code Instruct |
Repository ๐ค | https://huggingface.co/RyanJT/quantized-granite-4bit-3b-code-instruct |
Model Size | 3b |
Required VRAM | 2 GB |
Updated | 2024-09-06 |
Maintainer | RyanJT |
Model Type | llama |
Instruction-Based | Yes |
Model Files | |
Quantization Type | 4bit |
Model Architecture | LlamaForCausalLM |
Context Length | 2048 |
Model Max Length | 2048 |
Transformers Version | 4.42.0.dev0 |
Tokenizer Class | GPT2Tokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 49152 |
Torch Data Type | float16 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
Trained Quant 4bit | 0 | 5 | 0 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...3b V2 Python Instruct 0.1 4bit | 8K / 2.5 GB | 5 | 0 |
...ma 3b V2 Python Instruct 0.1.2 | 8K / 6.9 GB | 5 | 0 |
PRIME 3B | 8K / 5.8 GB | 2 | 1 |
... Granite 8bit 3B Code Instruct | 2K / 3.6 GB | 5 | 0 |
Llama 3.1 Mini Instruct | 128K / 6.1 GB | 76 | 0 |
Granite 3B Code Instruct 128K | 125K / 7 GB | 541 | 2 |
Granite 3B Code Instruct | 2K / 7 GB | 7313 | 29 |
Granite 3B Code Instruct 2K | 2K / 7 GB | 6228 | 29 |
KhanomTanLLM 3B Instruct | 2K / 6.9 GB | 64 | 0 |
KhanomTanLLM 3B Instruct | 2K / 6.9 GB | 22 | 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