LLM Name | Qwen2 0.5B Instruct GPTQ Int4 |
Repository | Open on ๐ค |
Model Size | 0.5b |
Required VRAM | 0.7 GB |
Updated | 2024-07-27 |
Maintainer | Qwen |
Model Type | qwen2 |
Instruction-Based | Yes |
Model Files | |
Supported Languages | en |
GPTQ Quantization | Yes |
Quantization Type | gptq |
Model Architecture | Qwen2ForCausalLM |
License | apache-2.0 |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.37.0 |
Tokenizer Class | Qwen2Tokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 151936 |
Torch Data Type | float16 |
Errors | replace |
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
---|---|---|---|---|
Qwen2 0.5B Instruct GPTQ Int8 | 0.3 | 32K / 1.5 GB | 404 | 2 |
Qwen2Vanilla GPTQ 4bits | 0.2 | 32K / 0.7 GB | 11 | 0 |
Qwen2Vanilla GPTQ 8bits | 0.2 | 32K / 0.9 GB | 7 | 0 |
Qwen2 0.5B Instruct Bnb 4bit | 0.3 | 32K / 0.5 GB | 8223 | 1 |
....5B Instruct Bnb 4bit MAC Lora | 0.2 | 32K / 0.5 GB | 26 | 1 |
New16b3e | 0.2 | 32K / 1 GB | 22 | 0 |
Qwen2 0.5B Instruct 4bit | 0.2 | 32K / 0.3 GB | 55 | 1 |
Newqwen1e | 0.2 | 32K / 1 GB | 13 | 0 |
Qwen2 0.5B Instruct Sorah | 0.2 | 32K / 1 GB | 7 | 0 |
New16b3e | — | 32K / 1 GB | 0 | 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