Autotrain compatible Bee-spoke-data/beecoder-220m-p... Bee-spoke-data/smol llama-220m... Bee-spoke-data/zephyr-220m-dpo... Bee-spoke-data/zephyr-220m-sft... Dataset:bigcode/the-stack-smol... Dataset:eleutherai/proof-pile-... Dataset:huggingfaceh4/ultracha... Dataset:huggingfaceh4/ultrafee... Dataset:jeankaddour/minipile Dataset:mattymchen/refinedweb-... Dataset:pszemraj/simple wikipe... Dataset:teknium/openhermes Endpoints compatible Lazymergekit Merge Mergekit Mixtral Moe Region:us Safetensors Sharded Tensorflow
Smol Llama 4x220M MoE Benchmarks
ARC: 25.09-73.9%
HellaSwag: 29.24-69.3%
MMLU: 25.88-70.1%
TruthfulQA: 43.92-25.6%
WinoGrande: 51.22-41.5%
GSM8K: 0.15-99.8%
nn.n% — How the model compares to the GPT-4.
Smol Llama 4x220M MoE Parameters and Internals
| LLM Name | Smol Llama 4x220M MoE |
| Repository | Open on 🤗 |
| Model Size | 595.4m |
| Required VRAM | 1.2 GB |
| Updated | 2024-07-27 |
| Maintainer | Isotonic |
| Model Type | mixtral |
| Model Files | |
| Model Architecture | MixtralForCausalLM |
| License | apache-2.0 |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.37.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <s> |
| Vocabulary Size | 32128 |
| Torch Data Type | bfloat16 |
Best Alternatives to Smol Llama 4x220M MoE
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| ...inyMixtral 4x220M UniversalNER | 0.2 | 2K / 2.4 GB | 20 | 0 |
Rank the Smol Llama 4x220M 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? 34447 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501