LLM Name | Kunoichi 7B GPTQ |
Repository ๐ค | https://huggingface.co/TheBloke/Kunoichi-7B-GPTQ |
Model Name | Kunoichi 7B |
Model Creator | Sanji Watsuki |
Base Model(s) | |
Model Size | 7b |
Required VRAM | 4.2 GB |
Updated | 2024-09-18 |
Maintainer | TheBloke |
Model Type | mistral |
Model Files | |
GPTQ Quantization | Yes |
Quantization Type | gptq |
Model Architecture | MistralForCausalLM |
License | cc-by-nc-4.0 |
Context Length | 8192 |
Model Max Length | 8192 |
Transformers Version | 4.37.0.dev0 |
Tokenizer Class | LlamaTokenizer |
Vocabulary Size | 32000 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...ral 7B Instruct V0.3 GPTQ 4bit | 32K / 4.2 GB | 223198 | 11 |
Mistral 7B Instruct V0.3 GPTQ | 32K / 4.2 GB | 278395 | 0 |
Microsoft WizardLM 2 7B GPTQ | 32K / 4.2 GB | 3946 | 0 |
Mistral 7B Instruct V0.1 GPTQ | 32K / 4.2 GB | 340487 | 75 |
...ephyr 7B Beta Channelwise Gptq | 32K / 4 GB | 23408 | 0 |
Mistral 7B Instruct V0.2 GPTQ | 32K / 4.2 GB | 46430 | 47 |
...tral 7B Instruct 32K GPTQ INT8 | 32K / 7.7 GB | 626 | 1 |
Mistral 7B OpenOrca GPTQ | 32K / 4.2 GB | 83909 | 100 |
Mistral 7B V0.1 GPTQ | 32K / 4.2 GB | 152566 | 35 |
...hyr 7B Beta Channelwise Marlin | 32K / 4 GB | 7163 | 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