LLM Name | V3 Gptq |
Repository ๐ค | https://huggingface.co/NotoriousH2/v3_gptq |
Merged Model | Yes |
Required VRAM | 6.1 GB |
Updated | 2024-12-22 |
Maintainer | NotoriousH2 |
Model Type | llama |
Model Files | |
GPTQ Quantization | Yes |
Quantization Type | gptq|4bit |
Model Architecture | LlamaForCausalLM |
Context Length | 4096 |
Model Max Length | 4096 |
Transformers Version | 4.38.2 |
Tokenizer Class | LlamaTokenizer |
Padding Token | </s> |
Vocabulary Size | 40960 |
Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
LWM Text Chat 512K GPTQ | 512K / 4.3 GB | 9 | 2 |
LWM Text Chat 256K GPTQ | 256K / 4.3 GB | 7 | 1 |
LWM Text Chat 128K GPTQ | 128K / 4.3 GB | 9 | 1 |
StoryTeller10.7B GPTQ 4Bit | 41K / 6.6 GB | 7 | 0 |
Alpha Merged Gptq | 19K / 9.2 GB | 7 | 0 |
...lama 3 Lima Nsfw 16K Test GPTQ | 16K / 5.7 GB | 45 | 5 |
Taiwan LLaMa V1.0 4bits GPTQ | 4K / 7.3 GB | 12 | 1 |
MythoMax22b Falseblock GPT | 4K / 12 GB | 10 | 0 |
Taiwan LLaMa V1.0 4bits GPTQ | 4K / 7.3 GB | 15 | 9 |
Nous Hermes Llama2 8bit GPTQ | 4K / 13.7 GB | 10 | 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