Base model:finetune:nytk/puli-... Base model:nytk/puli-gpt-3sx Ggml Gpt-neox Hu Puli Quantized Region:us
PULI GPT 3SX 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)
PULI GPT 3SX GGML Parameters and Internals
| LLM Name | PULI GPT 3SX GGML |
| Repository 🤗 | https://huggingface.co/TheBloke/PULI-GPT-3SX-GGML |
| Model Name | PULI GPT 3SX |
| Model Creator | NYTK |
| Base Model(s) | |
| Required VRAM | 3.9 GB |
| Updated | 2024-09-18 |
| Maintainer | TheBloke |
| Model Type | gpt-neox |
| Model Files | |
| Supported Languages | hu |
| GGML Quantization | Yes |
| Quantization Type | ggml |
| Model Architecture | AutoModel |
| License | cc-by-nc-4.0 |
Best Alternatives to PULI GPT 3SX GGML
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Athena V1 GGML | 0K / 5.5 GB | 0 | 1 |
| MythoMax Kimiko Mix GGML | 0K / 5.7 GB | 0 | 3 |
| Octocoder GGML | 0K / 10.7 GB | 5 | 15 |
| ...ax22b Instruct Falseblock GGML | 0K / 9.2 GB | 2 | 6 |
| NewHope GGML | 0K / 5.7 GB | 2 | 38 |
| Spring Dragon GGML | 0K / 5.5 GB | 1 | 3 |
| QCammel 13 GGML | 0K / 5.5 GB | 6 | 8 |
| OpenChat V3.2 GGML | 0K / 5.7 GB | 2 | 15 |
| QCammel 70 X GGML | 0K / 28.6 GB | 6 | 3 |
| Replit Openorca GGML | 0K / 1.5 GB | 2 | 6 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/PULI-GPT-3SX-GGML .
Rank the PULI GPT 3SX 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? 36026 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803