LLM Name | WizardLM 7B Uncensored |
Repository ๐ค | https://huggingface.co/cognitivecomputations/WizardLM-7B-Uncensored |
Model Size | 7b |
Required VRAM | 13.5 GB |
Updated | 2024-09-19 |
Maintainer | cognitivecomputations |
Model Type | llama |
Instruction-Based | Yes |
Model Files | |
Model Architecture | LlamaForCausalLM |
License | other |
Context Length | 2048 |
Model Max Length | 2048 |
Transformers Version | 4.29.0.dev0 |
Tokenizer Class | LlamaTokenizer |
Beginning of Sentence Token | <s> |
End of Sentence Token | </s> |
Unk Token | <unk> |
Vocabulary Size | 32001 |
Torch Data Type | float16 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
WizardLM 7B Uncensored GPTQ | 0 | 6 | 4 GB |
WizardLM 7B Uncensored GPTQ | 7 | 16 | 3 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
WizardLM 7B V1.0 Uncensored | 2K / 13.5 GB | 19 | 19 |
Llama 2 7B 32K Instruct | 32K / 13.5 GB | 10342 | 160 |
Qwen2 7B Instruct Llama | 32K / 15.2 GB | 4 | 3 |
Qwen2 7B Instruct Mistral | 32K / 15.2 GB | 3 | 1 |
AIRIC The Mistral | 32K / 14.4 GB | 688 | 7 |
...ls Vikhr 7B Instruct 0.4 4bits | 32K / 5.2 GB | 6 | 0 |
Vikhr 7B Instruct 0.3 | 32K / 14.6 GB | 20 | 4 |
... Samantha Philosopher 7B Slerp | 32K / 13.4 GB | 4 | 2 |
Vikhr 7B Instruct Merged | 32K / 14.6 GB | 4 | 4 |
Clinical Ehr Prototype 0.1 | 32K / 14.4 GB | 14 | 2 |
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