Autotrain compatible Conversational Endpoints compatible Felladrin/tinymistral-248m-sft... Lazymergekit Locutusque/locutusquexfelladri... Locutusque/tinymistral-248m-v2... Locutusque/tinymistral-248m-v2... Merge Mergekit Mixtral Moe Region:us Safetensors Sharded Tensorflow
TinyMixtral 4x248M MoE Benchmarks
ARC: 27.47 vs 96.7 (so35)-71.6%
HellaSwag: 25.43 vs 95.3 (gpt4)-73.3%
MMLU: 25.15 vs 88.3 (so35)-71.5%
TruthfulQA: 48.3 vs 59 (gpt4)-18.1%
WinoGrande: 48.7 vs 87.5 (gpt4)-44.3%
LLME Score: 0.25668
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)
TinyMixtral 4x248M MoE Parameters and Internals
| LLM Name | TinyMixtral 4x248M MoE |
| Repository 🤗 | https://huggingface.co/Isotonic/TinyMixtral-4x248M-MoE |
| Model Size | 701.1m |
| Required VRAM | 2.8 GB |
| Updated | 2024-10-08 |
| Maintainer | Isotonic |
| Model Type | mixtral |
| Model Files | |
| Model Architecture | MixtralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.38.1 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <s> |
| Vocabulary Size | 32003 |
| Torch Data Type | float32 |
Best Alternatives to TinyMixtral 4x248M MoE
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ... 248Mx4 MoE Not Tuned Pls Help | 32K / 1.4 GB | 11 | 0 |
Rank the TinyMixtral 4x248M 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? 36644 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803