Downloads · 30 days
132
5% of all-time downloads
TeeZee_-_DarkForest-20B-v3.0-gguf
RichardErkhov/TeeZee_-_DarkForest-20B-v3.0-gguf
TeeZee_-_DarkForest-20B-v3.0-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
2.7K
Public
Repo size
200 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf236 GB · 100%
At a glance
- Access
- Public
- Created
- Oct 27, 2024
- Updated
- Oct 27, 2024
- SHA
- 9ac996b6
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
DarkForest-20B-v3.0 - GGUF
- Model creator: https://huggingface.co/TeeZee/
- Original model: https://huggingface.co/TeeZee/DarkForest-20B-v3.0/
| Name | Quant method | Size |
|---|---|---|
| DarkForest-20B-v3.0.Q2_K.gguf | Q2_K | 6.91GB |
| DarkForest-20B-v3.0.Q3_K_S.gguf | Q3_K_S | 8.06GB |
| DarkForest-20B-v3.0.Q3_K.gguf | Q3_K | 9.04GB |
| DarkForest-20B-v3.0.Q3_K_M.gguf | Q3_K_M | 9.04GB |
| DarkForest-20B-v3.0.Q3_K_L.gguf | Q3_K_L | 9.9GB |
| DarkForest-20B-v3.0.IQ4_XS.gguf | IQ4_XS | 10.01GB |
| DarkForest-20B-v3.0.Q4_0.gguf | Q4_0 | 10.52GB |
| DarkForest-20B-v3.0.IQ4_NL.gguf | IQ4_NL | 10.57GB |
| DarkForest-20B-v3.0.Q4_K_S.gguf | Q4_K_S | 10.59GB |
| DarkForest-20B-v3.0.Q4_K.gguf | Q4_K | 11.22GB |
| DarkForest-20B-v3.0.Q4_K_M.gguf | Q4_K_M | 11.22GB |
| DarkForest-20B-v3.0.Q4_1.gguf | Q4_1 | 11.67GB |
| DarkForest-20B-v3.0.Q5_0.gguf | Q5_0 | 12.83GB |
| DarkForest-20B-v3.0.Q5_K_S.gguf | Q5_K_S | 12.83GB |
| DarkForest-20B-v3.0.Q5_K.gguf | Q5_K | 13.18GB |
| DarkForest-20B-v3.0.Q5_K_M.gguf | Q5_K_M | 13.18GB |
| DarkForest-20B-v3.0.Q5_1.gguf | Q5_1 | 13.98GB |
| DarkForest-20B-v3.0.Q6_K.gguf | Q6_K | 15.28GB |
| DarkForest-20B-v3.0.Q8_0.gguf | Q8_0 | 19.79GB |
Original model description:
license: other tags:
- merge
- not-for-all-audiences license_name: microsoft-research-license
DarkForest 20B v3.0
Model Details
- To create this model five step procedure was used.
- The resulting model has approximately 20 billion parameters.
- details of merge steps are in files:
- darkforest_v3_step1.yml
- darkforest_v3_step2.yml
- darkforest_v3_step3.yml
- darkforest_v3_step4.yml
- darkforest_v3_step5.yml
Models used
- custom model, based on athirdpath/Orca-2-13b-Alpaca-Uncensored and KoboldAI/LLaMA2-13B-Erebus-v3
- BigMaid-20B-v2.0
- athirdpath/Harmonia-20B
- athirdpath/Iambe-RP-v3-20b
Models removed
- jebcarter_psyonic-cetacean-20B
Merge method
- all merges done in float32 precision, when applicable, breadcrumbs_ties merge method was used.
Warning: This model can produce NSFW content!
Results
- main difference to v2.x - model follows much better character cards and also user profile.
- produces SFW nad NSFW content without issues, switches context seamlessly.
- good at following instructions.
- good at tracking multiple characters in one scene.
- very creative, scenarios produced are mature and complicated, model doesn't shy from writing about PTSD, mental issues or complicated relationships.
- NSFW output is more creative and suprising than typical limaRP output.
- definitely for mature audiences, not only because of vivid NSFW content but also because of overall maturity of stories it produces.
- This is NOT Harry Potter level storytelling.
All comments are greatly appreciated, download, test and if you appreciate my work, consider buying me my fuel: <a href="https://www.buymeacoffee.com/TeeZee" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
- Created
- Oct 27, 2024
- Updated
- Oct 27, 2024