LLM Name | Qwen2 7B Instruct GPTQ Int8 |
Repository ๐ค | https://huggingface.co/Qwen/Qwen2-7B-Instruct-GPTQ-Int8 |
Base Model(s) | |
Model Size | 7b |
Required VRAM | 8.9 GB |
Updated | 2024-09-07 |
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 | 4.38.2 |
Tokenizer Class | Qwen2Tokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 152064 |
Torch Data Type | float16 |
Errors | replace |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
Term Qwen2 7 Json Lora | 0 | 6 | 0 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Qwen2 7B Instruct GPTQ Int4 | 32K / 5.6 GB | 4800 | 18 |
Qwen2 7B Instruct Bnb 4bit | 32K / 5.5 GB | 9824 | 4 |
...Spanish English Asistant 16bit | 32K / 15.2 GB | 40 | 0 |
Qwen2 7B Instruct 4bit | 32K / 4.3 GB | 169 | 3 |
Qwen2 7B Instruct 4bit | 32K / 5.6 GB | 48 | 1 |
Qwenwared | 32K / 15.2 GB | 21 | 0 |
....O.S.I.E.v4o 7B Stage1 Beta3.2 | 32K / 15.2 GB | 5 | 1 |
....O.S.I.E.v4o 7B Stage1 Beta3.0 | 32K / 15.2 GB | 5 | 1 |
Qwen2 7B Instruct 8bit | 32K / 8.1 GB | 50 | 4 |
...en2 7b Instruct 4bit 45706 Ft1 | 32K / 5.6 GB | 5 | 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