LLM Name | Qwen2.5 32B Instruct Bnb 4bit |
Repository ๐ค | https://huggingface.co/unsloth/Qwen2.5-32B-Instruct-bnb-4bit |
Base Model(s) | |
Model Size | 32b |
Required VRAM | 19.2 GB |
Updated | 2024-09-29 |
Maintainer | unsloth |
Model Type | qwen2 |
Instruction-Based | Yes |
Model Files | |
Quantization Type | 4bit |
Model Architecture | Qwen2ForCausalLM |
License | apache-2.0 |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.44.2 |
Tokenizer Class | Qwen2Tokenizer |
Padding Token | <|PAD_TOKEN|> |
Vocabulary Size | 152064 |
Torch Data Type | bfloat16 |
Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Qwen2.5 32B Instruct | 32K / 65.5 GB | 27915 | 74 |
Qwen2.5 32B AGI | 32K / 44.6 GB | 237 | 40 |
Qwen2.5 32B Instruct AWQ | 32K / 19.4 GB | 3025 | 20 |
Qwen2.5 32B Instruct GPTQ Int4 | 32K / 19.5 GB | 1397 | 6 |
Qwen2.5 32B Instruct GPTQ Int8 | 32K / 35.1 GB | 1347 | 4 |
EZO Qwen2.5 32B Instruct | 32K / 65.8 GB | 175 | 2 |
BigQwen2.5 Echo 47B Instruct | 32K / 95.3 GB | 53 | 3 |
BigQwen2.5 52B Instruct | 32K / 105 GB | 102 | 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