Autotrain compatible Dataset:nomic-ai/gpt4all-j-pro... En Endpoints compatible Gptj Pytorch Region:us Safetensors Sharded Tensorflow
Gpt4all J Benchmarks
ARC: 41.3 vs 96.7 (so35)-57.3%
HellaSwag: 64.51 vs 95.3 (gpt4)-32.3%
MMLU: 29.03 vs 88.3 (so35)-67.1%
TruthfulQA: 45.72 vs 59 (gpt4)-22.5%
WinoGrande: 64.33 vs 87.5 (gpt4)-26.5%
GSM8K: 9.25 vs 96.4 (so35)-90.4%
LLME Score: 0.1805
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)
Gpt4all J Parameters and Internals
| LLM Name | Gpt4all J |
| Repository 🤗 | https://huggingface.co/nomic-ai/gpt4all-j |
| Model Size | 6b |
| Required VRAM | 12.2 GB |
| Updated | 2024-10-18 |
| Maintainer | nomic-ai |
| Model Type | gptj |
| Model Files | |
| Supported Languages | en |
| Model Architecture | GPTJForCausalLM |
| License | apache-2.0 |
| Model Max Length | 2048 |
| Transformers Version | 4.28.0.dev0 |
| Tokenizer Class | GPT2Tokenizer |
| Beginning of Sentence Token | <|endoftext|> |
| End of Sentence Token | <|endoftext|> |
| Unk Token | <|endoftext|> |
| Vocabulary Size | 50400 |
| Torch Data Type | bfloat16 |
| Activation Function | gelu_new |
| Errors | replace |
Best Alternatives to Gpt4all J
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Test GPT J 6B | 0K / 2.5 GB | 1374 | 0 |
| Deception Normal | 0K / 12.2 GB | 5 | 0 |
| Deception Filteredpositive | 0K / 12.2 GB | 5 | 0 |
| Gptj Allenai Toxicity Blackbox | 0K / 12.2 GB | 5 | 0 |
| ...j Allenai Toxicity Explainable | 0K / 12.2 GB | 5 | 0 |
| GPT J 6B | 0K / 24.2 GB | 456 | 1 |
| Explainable GPT J 6B | 0K / 24.2 GB | 6 | 0 |
| Pygmalion 6B | 0K / 16.3 GB | 2599 | 728 |
| Jeneri SAMA 6B | 0K / 12.2 GB | 13 | 1 |
| Pygmalion 6B Roleplay | 0K / 12.1 GB | 1175 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than nomic-ai/gpt4all-j .
Rank the Gpt4all J 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