Skip to content

Commit cbfab81

Browse files
authored
models(gallery): add datagemma models (#3540)
Signed-off-by: Ettore Di Giacinto <[email protected]>
1 parent 925315a commit cbfab81

File tree

1 file changed

+28
-0
lines changed

1 file changed

+28
-0
lines changed

gallery/index.yaml

Lines changed: 28 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1756,6 +1756,34 @@
17561756
- filename: Athena-codegemma-2-2b-it.Q4_K_M.gguf
17571757
sha256: 59ce17023438b0da603dd211c7d39f78e7acac4108258ac0818a97a4ca7d64e3
17581758
uri: huggingface://mradermacher/Athena-codegemma-2-2b-it-GGUF/Athena-codegemma-2-2b-it.Q4_K_M.gguf
1759+
- !!merge <<: *gemma
1760+
name: "datagemma-rag-27b-it"
1761+
urls:
1762+
- https://huggingface.co/google/datagemma-rag-27b-it
1763+
- https://huggingface.co/bartowski/datagemma-rag-27b-it-GGUF
1764+
description: |
1765+
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.
1766+
overrides:
1767+
parameters:
1768+
model: datagemma-rag-27b-it-Q4_K_M.gguf
1769+
files:
1770+
- filename: datagemma-rag-27b-it-Q4_K_M.gguf
1771+
sha256: 3dfcf51b05e3f0ab0979ad194de350edea71cb14444efa0a9f2ef5bfc80753f8
1772+
uri: huggingface://bartowski/datagemma-rag-27b-it-GGUF/datagemma-rag-27b-it-Q4_K_M.gguf
1773+
- !!merge <<: *gemma
1774+
name: "datagemma-rig-27b-it"
1775+
urls:
1776+
- https://huggingface.co/google/datagemma-rig-27b-it
1777+
- https://huggingface.co/bartowski/datagemma-rig-27b-it-GGUF
1778+
description: |
1779+
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.
1780+
overrides:
1781+
parameters:
1782+
model: datagemma-rig-27b-it-Q4_K_M.gguf
1783+
files:
1784+
- filename: datagemma-rig-27b-it-Q4_K_M.gguf
1785+
sha256: a6738ffbb49b6c46d220e2793df85c0538e9ac72398e32a0914ee5e55c3096ad
1786+
uri: huggingface://bartowski/datagemma-rig-27b-it-GGUF/datagemma-rig-27b-it-Q4_K_M.gguf
17591787
- &llama3
17601788
url: "github:mudler/LocalAI/gallery/llama3-instruct.yaml@master"
17611789
icon: https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/aJJxKus1wP5N-euvHEUq7.png

0 commit comments

Comments
 (0)