Additional Notes |
|
LLM Name | Orenguteng Llama 3 8B Lexi Uncensored HQQ 1bit Smashed |
Repository ๐ค | https://huggingface.co/PrunaAI/Orenguteng-Llama-3-8B-Lexi-Uncensored-HQQ-1bit-smashed |
Base Model(s) | |
Model Size | 8b |
Required VRAM | 3.1 GB |
Updated | 2024-12-22 |
Maintainer | PrunaAI |
Model Type | llama |
Model Files | |
Quantization Type | 1bit |
Model Architecture | LlamaForCausalLM |
Context Length | 8192 |
Model Max Length | 8192 |
Transformers Version | 4.40.0 |
Tokenizer Class | PreTrainedTokenizerFast |
Padding Token | <|end_of_text|> |
Vocabulary Size | 128256 |
Torch Data Type | float16 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
...xi Uncensored HQQ 1bit Smashed | 0 | 18 | 3 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...rame Uncensored Instruct Small | 8K / 16.1 GB | 212 | 1 |
...8B Uncensored HQQ 1bit Smashed | 8K / 3.1 GB | 14 | 0 |
...8B Uncensored HQQ 4bit Smashed | 8K / 5.8 GB | 11 | 0 |
...8B Uncensored Bnb 4bit Smashed | 8K / 6.1 GB | 15 | 0 |
Llama3 Uncensored | 8K / 16.1 GB | 10 | 1 |
...xi Uncensored HQQ 2bit Smashed | 8K / 4 GB | 31 | 1 |
...xi Uncensored HQQ 4bit Smashed | 8K / 5.8 GB | 21 | 1 |
...a Uncensored L3 8B 6.0bpw EXL2 | 8K / 6.7 GB | 11 | 2 |
...a Uncensored L3 8B 4.0bpw EXL2 | 8K / 5 GB | 11 | 0 |
8B Unaligned BASE V2a | 1024K / 16.1 GB | 78 | 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