ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2024-12-19 20:57:54 +00:00
Code Issues Actions 13 Packages Projects Releases Wiki Activity

models(gallery): add meta-llama-3.1-instruct-9.99b-brainstorm-10x-form-3 (#3103)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-08-01 09:35:43 +02:00 committed by GitHub
parent af0545834f
commit 26f393bd99
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

@ -238,6 +238,19 @@
- filename: Llama3.1-70B-Chinese-Chat.Q4_K_M.gguf
sha256: 395cff3cce2b092f840b68eb6e31f4c8b670bc8e3854bbb230df8334369e671d
uri: huggingface://mradermacher/Llama3.1-70B-Chinese-Chat-GGUF/Llama3.1-70B-Chinese-Chat.Q4_K_M.gguf
- !!merge <<: *llama31
name: "meta-llama-3.1-instruct-9.99b-brainstorm-10x-form-3"
urls:
- https://huggingface.co/DavidAU/Meta-Llama-3.1-Instruct-9.99B-BRAINSTORM-10x-FORM-3-GGUF
description: |
The Meta-Llama-3.1-8B Instruct model is a large language model trained on a diverse range of text data, with the goal of generating high-quality and coherent text in response to user input. This model is enhanced through a process called "Brainstorm", which involves expanding and recalibrating the model's reasoning center to improve its creative and generative capabilities. The resulting model is capable of generating detailed, vivid, and nuanced text, with a focus on prose quality, conceptually complex responses, and a deeper understanding of the user's intent. The Brainstorm process is designed to enhance the model's performance in creative writing, roleplaying, and story generation, and to improve its ability to generate coherent and engaging text in a wide range of contexts. The model is based on the Llama3 architecture and has been fine-tuned using the Instruct framework, which provides it with a strong foundation for understanding natural language instructions and generating appropriate responses. The model can be used for a variety of tasks, including creative writing,Generating coherent and detailed text, exploring different perspectives and scenarios, and brainstorming ideas.
overrides:
parameters:
model: Meta-Llama-3.1-8B-Instruct-Instruct-exp10-3-Q4_K_M.gguf
files:
- filename: Meta-Llama-3.1-8B-Instruct-Instruct-exp10-3-Q4_K_M.gguf
sha256: f52ff984100b1ff6acfbd7ed1df770064118274a54ae5d48749400a662113615
uri: huggingface://DavidAU/Meta-Llama-3.1-Instruct-9.99B-BRAINSTORM-10x-FORM-3-GGUF/Meta-Llama-3.1-8B-Instruct-Instruct-exp10-3-Q4_K_M.gguf
## Uncensored models
- !!merge <<: *llama31
name: "darkidol-llama-3.1-8b-instruct-1.0-uncensored-i1"