Arxiv:2310.06825 4-bit Autotrain compatible Base model:mistralai/mistral-7... Conversational Finetuned Gptq Instruct License:apache-2.0 Mistral Quantized Region:us Safetensors
Mistral 7B Instruct V0.2 GPTQ Benchmarks
ARC: 65-32.5%
HellaSwag: 74.5-21.8%
MMLU: 57-34.1%
TruthfulQA: 6713.6%
WinoGrande: 82.6-5.6%
GSM8K: 50.8-44.8%
nn.n% — How the model compares to the GPT-4.
Rank the Mistral 7B Instruct V0.2 GPTQ Capabilities
🆘 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! 🌟
Best Alternatives to Mistral 7B Instruct V0.2 GPTQ
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Maxine 7B 0401 Stock | 76.73 | 32K / 14.4 GB | 891 | 1 |
| CalmExperiment 7B Slerp | 76.67 | 32K / 14.4 GB | 902 | 0 |
| Myriad 7B Slerp | 76.66 | 32K / 14.4 GB | 916 | 0 |
| Versatile 7B | 76.66 | 32K / 14.5 GB | 778 | 0 |
| Calme 7B Instruct V0.9 | 76.62 | 32K / 14.4 GB | 1483 | 9 |
| Calme 7B Instruct V0.2 | 76.61 | 32K / 14.5 GB | 1128 | 11 |
| Calme 7B Instruct V0.3 | 76.5 | 32K / 14.4 GB | 846 | 5 |
| Calme 7B Instruct V0.1.1 | 76.49 | 32K / 14.4 GB | 76 | 10 |
| Calme 7B Instruct V0.5 | 76.05 | 32K / 14.4 GB | 917 | 11 |
| Metis Chat Instruct 7B | 74.66 | 32K / 14.4 GB | 918 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Mistral-7B-Instruct-v0.2-GPTQ .
Mistral 7B Instruct V0.2 GPTQ Parameters and Internals
| LLM Name | Mistral 7B Instruct V0.2 GPTQ |
| Repository | Open on 🤗 |
| Model Name | Mistral 7B Instruct v0.2 |
| Model Creator | Mistral AI_ |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 4.2 GB |
| Updated | 2024-07-01 |
| Maintainer | TheBloke |
| Model Type | mistral |
| Instruction-Based | Yes |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.36.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Initializer Range | 0.02 |
| Torch Data Type | bfloat16 |
What open-source LLMs or SLMs are you in search of? 34238 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801