Cerebras GPT 6.7B Benchmarks
ARC: 35.07 vs 96.7 (so35)-63.7%
HellaSwag: 59.36 vs 95.3 (gpt4)-37.7%
MMLU: 25.93 vs 88.3 (so35)-70.6%
TruthfulQA: 38.02 vs 59 (gpt4)-35.6%
WinoGrande: 58.72 vs 87.5 (gpt4)-32.9%
GSM8K: 0.53 vs 96.4 (so35)-99.5%
LLME Score: 0.16545
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)
Cerebras GPT 6.7B Parameters and Internals
| LLM Name | Cerebras GPT 6.7B |
| Repository 🤗 | https://huggingface.co/cerebras/Cerebras-GPT-6.7B |
| Model Size | 6.7b |
| Required VRAM | 26.8 GB |
| Updated | 2024-09-16 |
| Maintainer | cerebras |
| Model Type | gpt2 |
| Model Files | |
| Supported Languages | en |
| Model Architecture | AutoModel |
| License | apache-2.0 |
| Vocabulary Size | 50257 |
| Activation Function | gelu |
Best Alternatives to Cerebras GPT 6.7B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Alpaca Cerebras 6.7B | 0K / 0 GB | 0 | 3 |
| Vigogne Opt 6.7B Instruct | 0K / 0 GB | 0 | 2 |
| ...pseek Coder 6.7B Instruct GGUF | 0K / 2.8 GB | 6637 | 168 |
| ...ydecompiler 3.7 6.7B V0.9 GGUF | 0K / 2.5 GB | 67 | 0 |
| ...enCodeInterpreter DS 6.7B GGUF | 0K / 2.5 GB | 136 | 2 |
| Magicoder S DS 6.7B GGUF | 0K / 2.8 GB | 550 | 76 |
| Deepseek Coder 6.7B Base GGUF | 0K / 2.8 GB | 1485 | 11 |
Note: green Score (e.g. "73.2") means that the model is better than cerebras/Cerebras-GPT-6.7B .
Rank the Cerebras GPT 6.7B 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? 35926 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803