4-bit 4bit Autotrain compatible Bitsandbytes Endpoints compatible Fp16 Ggml Gptj Instruct Pytorch Q4 Quantized Region:us Safetensors
Zenos GPT J 6B Instruct 4bit 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)
Zenos GPT J 6B Instruct 4bit Parameters and Internals
| LLM Name | Zenos GPT J 6B Instruct 4bit |
| Repository 🤗 | https://huggingface.co/webpolis/zenos-gpt-j-6B-instruct-4bit |
| Model Size | 6b |
| Required VRAM | 3.4 GB |
| Updated | 2024-09-16 |
| Maintainer | webpolis |
| Model Type | gptj |
| Instruction-Based | Yes |
| Model Files | |
| GGML Quantization | Yes |
| Quantization Type | fp16|ggml|q4|4bit |
| Model Architecture | GPTJForCausalLM |
| Model Max Length | 2048 |
| Transformers Version | 4.35.0.dev0 |
| Tokenizer Class | GPT2Tokenizer |
| Vocabulary Size | 50260 |
| Torch Data Type | bfloat16 |
| Activation Function | gelu_new |
Best Alternatives to Zenos GPT J 6B Instruct 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| GPT J 6B Alpaca Gpt4 | 0K / 24.3 GB | 41 | 20 |
| Pyg Instruct Wizardlm | 0K / 12.2 GB | 699 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than webpolis/zenos-gpt-j-6B-instruct-4bit .
Rank the Zenos GPT J 6B Instruct 4bit 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? 35941 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803