Text Generation
cortiq
cmf
quantized
q4tp
q8_2f
mixed-precision
granite
reasoning
4-bit precision
8-bit precision
Instructions to use infosave/Granite-4.2-cmf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- cortiq
How to use infosave/Granite-4.2-cmf with cortiq:
# one Rust binary, no additional dependencies cargo install cortiq-cli # or a prebuilt binary from github.com/infosave2007/cmf/releases hf download infosave/Granite-4.2-cmf --include "*.cmf" --local-dir . ls *.cmf # some repos ship more than one quantization
cortiq run FILE.cmf --prompt "What is the capital of France?"
cortiq serve FILE.cmf --port 8080 # OpenAI-compatible server
- Notebooks
- Google Colab
- Kaggle
Upload Granite 4.2 8B Q4TP
Browse files- .gitattributes +1 -0
- granite-4.2-8b-q4tp.cmf +3 -0
.gitattributes
CHANGED
|
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
granite-4.2-3b-q4tp.cmf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
granite-4.2-3b-q8_2f.cmf filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
granite-4.2-3b-q4tp.cmf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
granite-4.2-3b-q8_2f.cmf filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
granite-4.2-8b-q4tp.cmf filter=lfs diff=lfs merge=lfs -text
|
granite-4.2-8b-q4tp.cmf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f1f9f76f92f3b8b28e6f5e7c00f037c81d6b208f01a00be37f5ae6f4c573bf7
|
| 3 |
+
size 4984141574
|