Downloads · 30 days
0
WizardLM-Uncensored-SCOT-ST-30B-Q3_K_S-GGML
RachidAR/WizardLM-Uncensored-SCOT-ST-30B-Q3_K_S-GGML
WizardLM-Uncensored-SCOT-ST-30B-Q3_K_S-GGML is a machine learning model from RachidAR. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
These files are GGML format model files for Monero's WizardLM-Uncensored-SuperCOT-Storytelling-30B.
Access
Public
Updated Jun 6, 2023
Repo size
14.1 GB
Likes
8
Public
Repo makeup
Click a slice to open those files.
.bin14.1 GB · 100%
At a glance
- License
- other
- Access
- Public
- Created
- Jun 5, 2023
- Updated
- Jun 6, 2023
- SHA
- 44f8f192
Model card
From the Hugging Face model README
Monero's WizardLM-Uncensored-SuperCOT-Storytelling-30B GGML
These files are GGML format model files for Monero's WizardLM-Uncensored-SuperCOT-Storytelling-30B.
Works with latest llama.cpp version. (05/06/23 build = 622)
Prompt template
Optional instruction ("You are a helpful assistant" etc)
USER: prompt
ASSISTANT:
The quality of the 3-bit model is higher than the 2-bit model, but the interface is slower. The 3-bit model (type q3_K_S) barely fits into 16 GB of RAM, but it works.
llama_model_load_internal: mem required = 15716.00 MB (+ 3124.00 MB per state)
On my Xeon E3-1225 v3 4/8 old cpu, it runs with ~740 ms per token.
- License
- other
- Created
- Jun 5, 2023
- Updated
- Jun 6, 2023