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 datagemma models (#3540)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-09-13 21:49:18 +02:00 committed by GitHub
parent 925315ab5c
commit cbfab81c35
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 28 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
gallery/index.yaml
View File

@ -1756,6 +1756,34 @@
- filename: Athena-codegemma-2-2b-it.Q4_K_M.gguf
sha256: 59ce17023438b0da603dd211c7d39f78e7acac4108258ac0818a97a4ca7d64e3
uri: huggingface://mradermacher/Athena-codegemma-2-2b-it-GGUF/Athena-codegemma-2-2b-it.Q4_K_M.gguf
- !!merge <<: *gemma
name: "datagemma-rag-27b-it"
urls:
- https://huggingface.co/google/datagemma-rag-27b-it
- https://huggingface.co/bartowski/datagemma-rag-27b-it-GGUF
description: |
DataGemma is a series of fine-tuned Gemma 2 models used to help LLMs access and incorporate reliable public statistical data from Data Commons into their responses. DataGemma RAG is used with Retrieval Augmented Generation, where it is trained to take a user query and generate natural language queries that can be understood by Data Commons' existing natural language interface. More information can be found in this research paper.
overrides:
parameters:
model: datagemma-rag-27b-it-Q4_K_M.gguf
files:
- filename: datagemma-rag-27b-it-Q4_K_M.gguf
sha256: 3dfcf51b05e3f0ab0979ad194de350edea71cb14444efa0a9f2ef5bfc80753f8
uri: huggingface://bartowski/datagemma-rag-27b-it-GGUF/datagemma-rag-27b-it-Q4_K_M.gguf
- !!merge <<: *gemma
name: "datagemma-rig-27b-it"
urls:
- https://huggingface.co/google/datagemma-rig-27b-it
- https://huggingface.co/bartowski/datagemma-rig-27b-it-GGUF
description: |
DataGemma is a series of fine-tuned Gemma 2 models used to help LLMs access and incorporate reliable public statistical data from Data Commons into their responses. DataGemma RIG is used in the retrieval interleaved generation approach (based off of tool-use approaches), where it is trained to annotate a response with natural language queries to Data Commons’ existing natural language interface wherever there are statistics. More information can be found in this research paper.
overrides:
parameters:
model: datagemma-rig-27b-it-Q4_K_M.gguf
files:
- filename: datagemma-rig-27b-it-Q4_K_M.gguf
sha256: a6738ffbb49b6c46d220e2793df85c0538e9ac72398e32a0914ee5e55c3096ad
uri: huggingface://bartowski/datagemma-rig-27b-it-GGUF/datagemma-rig-27b-it-Q4_K_M.gguf
- &llama3
url: "github:mudler/LocalAI/gallery/llama3-instruct.yaml@master"
icon: https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/aJJxKus1wP5N-euvHEUq7.png