OpenMistral MoE is an open-source language model by Yash21. Features: 7b LLM, VRAM: 48.3GB, Context: 32K, Instruction-Based, HF Score: 66.4, LLM Explorer Score: 0.14, Arc: 64.1, HellaSwag: 84, MMLU: 60.7, TruthfulQA: 54.6, WinoGrande: 76.8, GSM8K: 58.4.
Autotrain compatible Conversational Endpoints compatible Instruct Mixtral Moe Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Yash21/OpenMistral-MoE
OpenMistral MoE Benchmarks
ARC: 64.08 vs 96.7 (so35)-33.7%
HellaSwag: 83.99 vs 95.3 (gpt4)-11.9%
MMLU: 60.69 vs 88.3 (so35)-31.3%
TruthfulQA: 54.57 vs 59 (gpt4)-7.5%
WinoGrande: 76.8 vs 87.5 (gpt4)-12.2%
GSM8K: 58.38 vs 96.4 (so35)-39.4%
LLME Score: 0.14051
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
OpenMistral MoE Parameters and Internals
| Model Type |
| |||
| Input Output |
|
| LLM Name | OpenMistral MoE |
| Repository 🤗 | https://huggingface.co/Yash21/OpenMistral-MoE |
| Model Size | 7b |
| Required VRAM | 48.3 GB |
| Updated | 2024-10-29 |
| Maintainer | Yash21 |
| Model Type | mixtral |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | MixtralForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <s> |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to OpenMistral MoE
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mini Mixtral V0.2 | 32K / 25.8 GB | 6 | 4 |
| Multilingual Mistral | 32K / 93.5 GB | 724 | 2 |
| Magiq 3 | 32K / 37.1 GB | 20 | 3 |
| FNCARL9000 | 32K / 48.3 GB | 21 | 0 |
| CollAIborate4x7B | 32K / 48.7 GB | 7 | 1 |
| Bigstral 12B 32K 8xMoE | 32K / 163.3 GB | 7 | 2 |
| CollAIborate4x7B | 32K / 48.7 GB | 1 | 1 |
| OpenMistral MoE | 32K / 48.3 GB | 26 | 0 |
| ...t V0.2 2x7B MoE 6.0bpw H6 EXL2 | 32K / 9.9 GB | 14 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than Yash21/OpenMistral-MoE .
Rank the OpenMistral MoE 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! 🌟
What open-source LLMs or SLMs are you in search of? 52628 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a