Obsolete, succeeded by a new merge: https://huggingface.co/brucethemoose/CaPlatTessDolXaBoros-Yi-34B-200K-DARE-Ties-HighDensity
NousResearch/Nous-Capybara-34B and migtissera/Tess-M-Creative-v1.0 ties merged with mergekit.
I would suggest an exllama version for local inference with 40K+ context in 24GB: https://huggingface.co/brucethemoose/Capybara-Tess-Yi-34B-200K-exl2-4bpw-fiction https://huggingface.co/brucethemoose/Capybara-Tess-Yi-34B-200K-exl2-31bpw-fiction
Merged with the following config:
models:
- model: /home/alpha/Storage/Models/Raw/larryvrh_Yi-34B-200K-Llamafied
# no parameters necessary for base model
- model: /home/alpha/Storage/Models/Raw/migtissera_Tess-M-v1.0
parameters:
density: 0.6
weight: 1.0
- model: /home/alpha/Storage/Models/Raw/Nous-Capybara-34B
parameters:
density: 0.6
weight: 1.0
merge_method: ties
base_model: //home/alpha/Storage/Models/Raw/larryvrh_Yi-34B-200K-Llamafied
parameters:
normalize: true
int8_mask: true
dtype: float16
Both are 200K context models with Vicuna syntax, so:
Prompt Format:
SYSTEM: ...
USER: ...
ASSISTANT: ...
Sometimes the model "spells out" the stop token as </s> like Capybara, so you may need to add </s> this as an additional stopping condition.
Credits:
https://github.com/cg123/mergekit
https://huggingface.co/NousResearch/Nous-Capybara-34B/discussions
https://huggingface.co/migtissera/Tess-M-Creative-v1.0
- Downloads last month
- 1,247
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.