LLM Name | Georgesung Llama2 7b Chat Uncensored HQQ 1bit Smashed |
Repository ๐ค | https://huggingface.co/PrunaAI/georgesung-llama2_7b_chat_uncensored-HQQ-1bit-smashed |
Base Model(s) | |
Model Size | 7b |
Required VRAM | 1.5 GB |
Updated | 2024-09-07 |
Maintainer | PrunaAI |
Model Type | llama |
Model Files | |
Quantization Type | 1bit |
Model Architecture | LlamaForCausalLM |
Context Length | 2048 |
Model Max Length | 2048 |
Transformers Version | 4.40.0 |
Tokenizer Class | LlamaTokenizer |
Padding Token | [PAD] |
Vocabulary Size | 32000 |
Torch Data Type | float16 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
...at Uncensored HQQ 1bit Smashed | 0 | 7 | 1 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...7B Uncensored SuperHOT 8K Fp16 | 8K / 13.5 GB | 22 | 4 |
....0 Uncensored SuperHOT 8K Fp16 | 8K / 13.5 GB | 9 | 4 |
...at Uncensored HQQ 2bit Smashed | 2K / 2.3 GB | 5 | 0 |
...at Uncensored HQQ 4bit Smashed | 2K / 3.9 GB | 5 | 0 |
Llama2 7b Chat Uncensored | 2K / 27 GB | 1788 | 352 |
...at Uncensored Bnb 4bit Smashed | 2K / 4.2 GB | 7 | 0 |
Luna AI Llama2 Uncensored | 2K / 27 GB | 829 | 134 |
Llama2 7b Chat Uncensored | 2K / 27 GB | 8 | 1 |
Smaugv0.1 6.0bpw H6 EXL2 | 195K / 26.4 GB | 18 | 4 |
Smaugv0.1 5.0bpw H6 EXL2 | 195K / 22.3 GB | 20 | 3 |
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