Arxiv:2306.05685 Arxiv:2307.09288 Base model:finetune:lmsys/vicu... Base model:lmsys/vicuna-13b-v1... Ggml Llama Quantized Region:us
Vicuna 13B V1.5 GGML Parameters and Internals
| LLM Name | Vicuna 13B V1.5 GGML |
| Repository | Open on 🤗 |
| Model Name | Vicuna 13B v1.5 |
| Model Creator | lmsys |
| Base Model(s) | |
| Model Size | 13b |
| Required VRAM | 5.5 GB |
| Updated | 2024-07-27 |
| Maintainer | TheBloke |
| Model Type | llama |
| Model Files | |
| GGML Quantization | Yes |
| Quantization Type | ggml |
| Model Architecture | AutoModel |
| License | llama2 |
Best Alternatives to Vicuna 13B V1.5 GGML
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Llama 2 13B Chat GGML | 0.2 | 0K / 5.5 GB | 449 | 689 |
| RuGPT 3.5 13B GGML | 0.2 | 0K / 7.4 GB | 23 | 8 |
| Llama 2 13B GGML | 0.2 | 0K / 5.5 GB | 46 | 172 |
| MythoMax L2 13B GGML | 0.2 | 0K / 5.5 GB | 28 | 81 |
| RuGPT 3.5 13B GGML | 0.2 | 0K / 7.4 GB | 24 | 15 |
| CodeLlama 13B GGML | 0.2 | 0K / 5.7 GB | 15 | 33 |
| OpenOrca Platypus2 13B GGML | 0.2 | 0K / 5.7 GB | 13 | 54 |
| ...zardCoder Python 13B V1.0 GGML | 0.2 | 0K / 5.7 GB | 11 | 22 |
| Nous Hermes Llama2 GGML | 0.2 | 0K / 5.7 GB | 10 | 100 |
| Vicuna 13B V1.5 16K GGML | 0.2 | 0K / 5.5 GB | 25 | 63 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/vicuna-13B-v1.5-GGML .
Rank the Vicuna 13B V1.5 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? 34446 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501