Codex commited on
Commit ·
5f62353
1
Parent(s): e14663c
WIP: add multimodal TranslateGemma bundle
Browse files
README.md
CHANGED
|
@@ -29,6 +29,7 @@ Google only publishes WebGPU-only TFLite files. This repo bridges that gap with
|
|
| 29 |
|------|------|-------|
|
| 30 |
| `artifacts/int4-generic/translategemma-4b-it-int4-generic.litertlm` | ~2 GB | INT4 blockwise quant — faster, lower RAM |
|
| 31 |
| `artifacts/dynamic_int8-generic/translategemma-4b-it-dynamic_int8-generic.litertlm` | ~4 GB | Dynamic INT8 — better quality |
|
|
|
|
| 32 |
|
| 33 |
**Start with INT4** if you're unsure — it loads faster and uses less RAM. Use dynamic_int8 for better translation quality.
|
| 34 |
|
|
|
|
| 29 |
|------|------|-------|
|
| 30 |
| `artifacts/int4-generic/translategemma-4b-it-int4-generic.litertlm` | ~2 GB | INT4 blockwise quant — faster, lower RAM |
|
| 31 |
| `artifacts/dynamic_int8-generic/translategemma-4b-it-dynamic_int8-generic.litertlm` | ~4 GB | Dynamic INT8 — better quality |
|
| 32 |
+
| `artifacts/int4-multimodal/translategemma-4b-it-int4-multimodal.litertlm` | ~2.6 GB | INT4 multimodal bundle with image translation support |
|
| 33 |
|
| 34 |
**Start with INT4** if you're unsure — it loads faster and uses less RAM. Use dynamic_int8 for better translation quality.
|
| 35 |
|
artifacts/int4-multimodal/translategemma-4b-it-int4-multimodal.litertlm
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1bc8e828fbe56dfb503ac033ac84a9eb941d85a9c196803167fa39b35f7fb033
|
| 3 |
+
size 2757894128
|