Model Card on HF 🤗: https://huggingface.co/tekkithorse/GPT-J-6B-PNY-GGML
GPT J 6B PNY GGML 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)
GPT J 6B PNY GGML Parameters and Internals
| Model Type |
| |
| Additional Notes |
|
| LLM Name | GPT J 6B PNY GGML |
| Repository 🤗 | https://huggingface.co/tekkithorse/GPT-J-6B-PNY-GGML |
| Model Size | 6b |
| Required VRAM | 4.5 GB |
| Updated | 2025-09-10 |
| Maintainer | tekkithorse |
| Model Type | gptj |
| Model Files | |
| GGML Quantization | Yes |
| Quantization Type | ggml|q4 |
| Model Architecture | GPTJForCausalLM |
| Model Max Length | 2048 |
| Transformers Version | 4.10.0.dev0 |
| Tokenizer Class | GPT2Tokenizer |
| Vocabulary Size | 50400 |
| Torch Data Type | float16 |
| Activation Function | gelu_new |
Best Alternatives to GPT J 6B PNY GGML
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Bertin GPT J 6B Alpaca | 0K / 24.4 GB | 1731 | 7 |
| Zenos GPT J 6B Instruct 4bit | 0K / 3.4 GB | 10 | 1 |
| Model | 0K / 6.2 GB | 7 | 0 |
| ...oduct NER GPT J 6B 4bit Merged | 0K / 2.5 GB | 17 | 0 |
| ...nese Novel GPT J 6B F16 Marisa | 0K / 12.2 GB | 7 | 3 |
| Kakaobrain Kogpt 6B 8bit | 0K / 6.7 GB | 10 | 2 |
| Pygmalion 6b Dev 4bit 128g | 0K / 4 GB | 18 | 120 |
| GPT J 6B Skein 4bit 128g | 0K / 4 GB | 15 | 1 |
| GPT J 6B Alpaca Gpt4 | 0K / 24.3 GB | 9 | 20 |
| Pygmalion 6B 4bit 128g | 0K / 4 GB | 6 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than tekkithorse/GPT-J-6B-PNY-GGML .
Rank the GPT J 6B PNY GGML 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? 51262 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124