Model Card on HF 🤗: https://huggingface.co/furiosa-ai/mlperf-gpt-j-6b
Mlperf GPT J 6B Benchmarks
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)
Mlperf GPT J 6B Parameters and Internals
| LLM Name | Mlperf GPT J 6B |
| Repository 🤗 | https://huggingface.co/furiosa-ai/mlperf-gpt-j-6b |
| Model Size | 6b |
| Required VRAM | 24.1 GB |
| Updated | 2025-08-22 |
| Maintainer | furiosa-ai |
| Model Type | gptj |
| Model Files | |
| Model Architecture | GPTJForCausalLM |
| Model Max Length | 1919 |
| Transformers Version | 4.31.0 |
| Tokenizer Class | GPT2Tokenizer |
| Beginning of Sentence Token | <|endoftext|> |
| End of Sentence Token | <|endoftext|> |
| Unk Token | <|endoftext|> |
| Vocabulary Size | 50401 |
| Torch Data Type | float32 |
| Activation Function | gelu_new |
| Errors | replace |
Best Alternatives to Mlperf GPT J 6B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Pygmalion 6B | 0K / 16.3 GB | 2338 | 751 |
| Deception Normal | 0K / 12.2 GB | 6 | 0 |
| Deception Filteredpositive | 0K / 12.2 GB | 6 | 0 |
| Gptj Allenai Toxicity Blackbox | 0K / 12.2 GB | 9 | 0 |
| ...j Allenai Toxicity Explainable | 0K / 12.2 GB | 7 | 0 |
| Pygmalion 6B Roleplay | 0K / 12.1 GB | 1780 | 2 |
| GPT JT 6B V1 | 0K / 12.2 GB | 9662 | 302 |
| GPT J 6B | 0K / 24.2 GB | 43060 | 1509 |
| Test GPT J 6B | 0K / 2.5 GB | 10 | 0 |
| Gpt4all J | 0K / 12.2 GB | 2343 | 300 |
Rank the Mlperf GPT J 6B 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? 51543 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124