LLM Name | Mistral 7B Instruct V0.3 GPTQ 4bit |
Repository | Open on ๐ค |
Base Model(s) | |
Model Size | 7b |
Required VRAM | 4.2 GB |
Updated | 2024-07-26 |
Maintainer | neuralmagic |
Model Type | mistral |
Instruction-Based | Yes |
Model Files | |
GPTQ Quantization | Yes |
Quantization Type | gptq|4bit |
Model Architecture | MistralForCausalLM |
License | apache-2.0 |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.40.2 |
Tokenizer Class | LlamaTokenizer |
Vocabulary Size | 32768 |
Torch Data Type | float16 |
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
---|---|---|---|---|
...tral 7B Instruct 32K GPTQ INT8 | 0.3 | 32K / 7.7 GB | 2189 | 1 |
Mistral 7B Instruct V0.1 GPTQ | 0.3 | 32K / 4.2 GB | 344706 | 73 |
Mistral 7B Instruct V0.3 GPTQ | 0.3 | 32K / 4.2 GB | 566 | 0 |
Mistral 7B Instruct V0.2 GPTQ | 0.3 | 32K / 4.2 GB | 24739 | 42 |
...stral 7B Instruct V0.3 GPTQ 8B | 0.2 | 32K / 7.7 GB | 37 | 0 |
Mistral 7B Instruct V0.3 GPTQ | 0.2 | 32K / 4.2 GB | 7 | 0 |
...ral 7B Instruct V0.3 GPTQ 4bit | 0.2 | 32K / 4.2 GB | 15 | 0 |
...stral 7B Instruct V0.3 GPTQ 4B | 0.2 | 32K / 4.2 GB | 33 | 0 |
...nstruct V0.2 Neural Story GPTQ | 0.2 | 32K / 4.6 GB | 8 | 1 |
... 2.6 Mistral 7B DPO Laser GPTQ | 0.2 | 32K / 4.2 GB | 118 | 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