LLM Name | Llama2 7b Chat Uncensored |
Repository | Open on ๐ค |
Model Size | 7b |
Required VRAM | 27 GB |
Updated | 2024-07-27 |
Maintainer | georgesung |
Model Type | llama |
Model Files | |
Quantization Type | fp16 |
Model Architecture | LlamaForCausalLM |
License | other |
Context Length | 2048 |
Model Max Length | 2048 |
Transformers Version | 4.30.2 |
Tokenizer Class | LlamaTokenizer |
Beginning of Sentence Token | <s> |
End of Sentence Token | </s> |
Unk Token | <unk> |
Vocabulary Size | 32000 |
Torch Data Type | float32 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
...at Uncensored AWQ 4bit Smashed | 0 | 20 | 3 GB |
...at Uncensored HQQ 2bit Smashed | 0 | 16 | 2 GB |
Llama2 7b Chat Uncensored GGUF | 27 | 5716 | 2 GB |
Llama2 7b Chat Uncensored AWQ | 5 | 33 | 3 GB |
Llama2 7b Chat Uncensored GGML | 114 | 34 | 2 GB |
Llama2 7b Chat Uncensored GPTQ | 65 | 90 | 3 GB |
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
---|---|---|---|---|
...7B Uncensored SuperHOT 8K Fp16 | 0.1 | 8K / 13.5 GB | 17 | 4 |
....0 Uncensored SuperHOT 8K Fp16 | 0.1 | 8K / 13.5 GB | 12 | 4 |
...at Uncensored HQQ 1bit Smashed | 0.2 | 2K / 1.5 GB | 26 | 0 |
...at Uncensored HQQ 4bit Smashed | 0.2 | 2K / 3.9 GB | 22 | 0 |
...at Uncensored HQQ 2bit Smashed | 0.2 | 2K / 2.3 GB | 16 | 0 |
...at Uncensored Bnb 4bit Smashed | 0.2 | 2K / 4.2 GB | 24 | 0 |
Luna AI Llama2 Uncensored | 0.2 | 2K / 27 GB | 1164 | 131 |
Llama2 7b Chat Uncensored | 0.2 | 2K / 27 GB | 24 | 1 |
Smaugv0.1 6.0bpw H6 EXL2 | 0.2 | 195K / 26.4 GB | 8 | 4 |
Smaugv0.1 5.0bpw H6 EXL2 | 0.2 | 195K / 22.3 GB | 7 | 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