LLM Name | Llama 30B Gptq 4bit 128g |
Repository ๐ค | https://huggingface.co/PocketDoc/llama-30b-gptq-4bit-128g |
Model Size | 30b |
Required VRAM | 18.1 GB |
Updated | 2024-09-05 |
Maintainer | PocketDoc |
Model Type | llama |
Model Files | |
GPTQ Quantization | Yes |
Quantization Type | gptq|4bit |
Model Architecture | LlamaForCausalLM |
Model Max Length | 2048 |
Transformers Version | 4.28.0.dev0 |
Tokenizer Class | LlamaTokenizer |
Beginning of Sentence Token | <s> |
End of Sentence Token | </s> |
Unk Token | <unk> |
Vocabulary Size | 32000 |
Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
GPlatty 30B SuperHOT 8K GPTQ | 8K / 16.9 GB | 18 | 7 |
... 30B Supercot SuperHOT 8K GPTQ | 8K / 16.9 GB | 9 | 5 |
Platypus 30B SuperHOT 8K GPTQ | 8K / 16.9 GB | 7 | 4 |
Tulu 30B SuperHOT 8K GPTQ | 8K / 16.9 GB | 8 | 5 |
Yayi2 30B Llama GPTQ | 4K / 17 GB | 7 | 2 |
WizardLM 30B GPTQ | 2K / 16.9 GB | 1932 | 18 |
Llama 30B FINAL MODEL MINI | 2K / 19.4 GB | 7 | 1 |
...2 Llama 30B 7K Steps Gptq 2bit | 2K / 9.5 GB | 8 | 2 |
...Assistant SFT 7 Llama 30B GPTQ | 2K / 16.9 GB | 1920 | 35 |
WizardLM 30B V1.0 GPTQ | 2K / 16.9 GB | 8 | 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