ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-02-19 17:06:33 +00:00
Code Issues Actions 12 Packages Projects Releases Wiki Activity

models(gallery): add meta-llama-3-instruct-8.9b-brainstorm-5x-form-11 (#3083)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-07-30 12:12:55 +02:00 committed by GitHub
parent 2d59c99d31
commit 17634b394b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 13 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
gallery/index.yaml
View File

@ -3705,6 +3705,19 @@
- filename: calme-2.4-llama3-70b.Q4_K_M.gguf
sha256: 0b44ac8a88395dfc60f1b9d3cfffc0ffef74ec0a302e610ef91fc787187568f2
uri: huggingface://mradermacher/calme-2.4-llama3-70b-GGUF/calme-2.4-llama3-70b.Q4_K_M.gguf
- !!merge <<: *llama3
name: "meta-llama-3-instruct-8.9b-brainstorm-5x-form-11"
urls:
- https://huggingface.co/DavidAU/Meta-Llama-3-Instruct-8.9B-BRAINSTORM-5x-FORM-11-GGUF
description: |
Meta-Llama-3-8B Instruct (now at 8.9B) is an enhanced version of the LLM model, specifically designed for creative use cases such as story writing, roleplaying, and fiction. This model has been augmented through the "Brainstorm" process, which involves expanding and calibrating the reasoning center of the LLM to improve its performance in various creative tasks. The enhancements brought by this process include more detailed and nuanced descriptions, stronger prose, and a greater sense of immersion in the story. The model is capable of generating long and vivid content, with fewer clichés and more focused, coherent narratives. Users can provide more instructions and details to elicit stronger and more engaging responses from the model. The "Brainstorm" process has been tested on multiple LLM models, including Llama2, Llama3, and Mistral, as well as on individual models like Llama3 Instruct, Mistral Instruct, and custom fine-tuned models.
overrides:
parameters:
model: Meta-Llama-3-8B-Instruct-exp5-11-Q4_K_M.gguf
files:
- filename: Meta-Llama-3-8B-Instruct-exp5-11-Q4_K_M.gguf
sha256: 5dd81b8b809667d10036499affdd1461cf95af50b405cbc9f800b421a4b60e98
uri: huggingface://DavidAU/Meta-Llama-3-Instruct-8.9B-BRAINSTORM-5x-FORM-11-GGUF/Meta-Llama-3-8B-Instruct-exp5-11-Q4_K_M.gguf
- &command-R
### START Command-r
url: "github:mudler/LocalAI/gallery/command-r.yaml@master"