Autotrain compatible Endpoints compatible Llama Merge Mixtral Model-index Moe Region:us Safetensors Sharded Tensorflow
TinyExperts V0 4x1B Benchmarks
ARC: 31.4 vs 96.7 (so35)-67.5%
HellaSwag: 52.29 vs 95.3 (gpt4)-45.1%
MMLU: 25.87 vs 88.3 (so35)-70.7%
TruthfulQA: 41.13 vs 59 (gpt4)-30.3%
WinoGrande: 60.14 vs 87.5 (gpt4)-31.3%
GSM8K: 0.53 vs 96.4 (so35)-99.5%
LLME Score: 0.2401
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)
TinyExperts V0 4x1B Parameters and Internals
| LLM Name | TinyExperts V0 4x1B |
| Repository 🤗 | https://huggingface.co/beberik/TinyExperts-v0-4x1B |
| Model Size | 2.6b |
| Required VRAM | 5.2 GB |
| Updated | 2024-09-07 |
| Maintainer | beberik |
| Model Type | mixtral |
| Model Files | |
| Model Architecture | MixtralForCausalLM |
| License | cc-by-nc-4.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.37.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <s> |
| Vocabulary Size | 32003 |
| Torch Data Type | float16 |
Best Alternatives to TinyExperts V0 4x1B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| TinyEnsemble 3x1.1B TinyMoE | 4K / 5.3 GB | 11 | 0 |
| ...x MoE Samantha Chatml Therabot | 4K / 5.2 GB | 10 | 1 |
| ...Oasst2 ChatML Cluster 3 2 1 V1 | 4K / 5.2 GB | 11 | 3 |
| LiteLlamix 8x460M 1T | 1K / 5.2 GB | 21 | 3 |
Rank the TinyExperts V0 4x1B 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? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803