Skip to content

Commit c14f1ff

Browse files
authored
chore(model gallery): add ibm-granite_granite-4.0-h-tiny (#6374)
Signed-off-by: Ettore Di Giacinto <[email protected]>
1 parent 07cca4b commit c14f1ff

File tree

1 file changed

+14
-0
lines changed

1 file changed

+14
-0
lines changed

gallery/index.yaml

Lines changed: 14 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -21,6 +21,20 @@
2121
- filename: ibm-granite_granite-4.0-h-small-Q4_K_M.gguf
2222
sha256: c59ce76239bd5794acdbdf88616dfc296247f4e78792a9678d4b3e24966ead69
2323
uri: huggingface://bartowski/ibm-granite_granite-4.0-h-small-GGUF/ibm-granite_granite-4.0-h-small-Q4_K_M.gguf
24+
- !!merge <<: *granite4
25+
name: "ibm-granite_granite-4.0-h-tiny"
26+
urls:
27+
- https://huggingface.co/ibm-granite/granite-4.0-h-tiny
28+
- https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF
29+
description: |
30+
Granite-4.0-H-Tiny is a 7B parameter long-context instruct model finetuned from Granite-4.0-H-Tiny-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets. This model is developed using a diverse set of techniques with a structured chat format, including supervised finetuning, model alignment using reinforcement learning, and model merging. Granite 4.0 instruct models feature improved instruction following (IF) and tool-calling capabilities, making them more effective in enterprise applications.
31+
overrides:
32+
parameters:
33+
model: ibm-granite_granite-4.0-h-tiny-Q4_K_M.gguf
34+
files:
35+
- filename: ibm-granite_granite-4.0-h-tiny-Q4_K_M.gguf
36+
sha256: 33a689fe7f35b14ebab3ae599b65aaa3ed8548c393373b1b0eebee36c653146f
37+
uri: huggingface://bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/ibm-granite_granite-4.0-h-tiny-Q4_K_M.gguf
2438
- &ernie
2539
url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
2640
name: "baidu_ernie-4.5-21b-a3b-thinking"

0 commit comments

Comments
 (0)