Arxiv:2309.12284 Arxiv:2310.10631 Autotrain compatible Dataset:meta-math/metamathqa Endpoints compatible Llama Pytorch Region:us Sharded
MetaMath Llemma 7B Benchmarks
ARC: 46.5 vs 96.7 (so35)-51.9%
HellaSwag: 61.69 vs 95.3 (gpt4)-35.3%
MMLU: 47.66 vs 88.3 (so35)-46%
TruthfulQA: 39.61 vs 59 (gpt4)-32.9%
WinoGrande: 62.75 vs 87.5 (gpt4)-28.3%
GSM8K: 60.96 vs 96.4 (so35)-36.8%
LLME Score: 0.20791
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)
MetaMath Llemma 7B Parameters and Internals
| LLM Name | MetaMath Llemma 7B |
| Repository 🤗 | https://huggingface.co/meta-math/MetaMath-Llemma-7B |
| Model Size | 7b |
| Required VRAM | 27 GB |
| Updated | 2024-10-18 |
| Maintainer | meta-math |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.35.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | [PAD] |
| Vocabulary Size | 32001 |
| Torch Data Type | float32 |
Best Alternatives to MetaMath Llemma 7B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...1M 1000000ctx AEZAKMI 3 1 1702 | 1024K / 13.5 GB | 57 | 1 |
| ... Qwen2.5llamaify 7B V23.1 200K | 195K / 15.2 GB | 684 | 0 |
| Yarn Llama 2 7B 128K | 128K / 13.5 GB | 1609 | 38 |
| LLaMA 7B PoSE YaRN 128K | 128K / 13.5 GB | 1 | 3 |
| LLaMA 7B PoSE Linear 96K | 96K / 27 GB | 6 | 2 |
| LLaMA 7B PoSE YaRN 96K | 96K / 13.5 GB | 1 | 1 |
| Chat Llama2 7B 80K | 80K / 13.8 GB | 12 | 0 |
| Llama2 7B 80K | 80K / 13.8 GB | 6 | 0 |
| Lloma Step400 | 64K / 13.5 GB | 57 | 0 |
| Lloma Step200 | 64K / 13.5 GB | 60 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than meta-math/MetaMath-Llemma-7B .
Rank the MetaMath Llemma 7B 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? 36966 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803