LLM Name | Mistral 7B Unsloth Gptq 8bit |
Repository ๐ค | https://huggingface.co/acl-srw-2024/mistral-7b-unsloth-gptq-8bit |
Model Size | 7b |
Required VRAM | 7.7 GB |
Updated | 2024-11-23 |
Maintainer | acl-srw-2024 |
Model Type | mistral |
Model Files | |
GPTQ Quantization | Yes |
Quantization Type | gptq|8bit |
Model Architecture | MistralForCausalLM |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.41.2 |
Tokenizer Class | LlamaTokenizer |
Padding Token | </s> |
Vocabulary Size | 32768 |
Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Mistral 7B Instruct V0.2 GPTQ | 32K / 4.2 GB | 463319 | 50 |
Mistral 7B Instruct V0.1 GPTQ | 32K / 4.2 GB | 1133673 | 77 |
Mistral 7B Instruct V0.3 GPTQ | 32K / 4.2 GB | 7855 | 0 |
Mistral 7B OpenOrca GPTQ | 32K / 4.2 GB | 441647 | 100 |
...ral 7B Instruct V0.3 GPTQ 4bit | 32K / 4.2 GB | 1586 | 15 |
...ephyr 7B Beta Channelwise Gptq | 32K / 4 GB | 12683 | 0 |
...hyr 7B Beta Channelwise Marlin | 32K / 4 GB | 6513 | 0 |
Zephyr 7B Beta Marlin | 32K / 4.1 GB | 6589 | 0 |
Dolphin 2.0 Mistral 7B GPTQ | 32K / 4.2 GB | 119013 | 8 |
...istral 7B Pruned50 GPTQ Marlin | 32K / 4 GB | 10 | 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