Run Gemma 3 with Keras 3: JAX, PyTorch, or TensorFlow
zeromodels/gemma-3-1b-it
Pure-
Keras 3
conversion of
google/gemma-3-1b-it
for
zeromodels
. One implementation runs unmodified on
TensorFlow / Torch / JAX
. This is the instruction-tuned checkpoint, served here as
text -> text
via
Gemma3TextGenerate
; weights are
stored in
bfloat16
.
For model details, license, and usage terms, see Google's
model card
.
✨ Quick start
import os
os.environ["KERAS_BACKEND"] = "torch"# or "jax" / "tensorflow"from zeromodels.models.gemma3 import Gemma3TextGenerate, Gemma3Tokenizer
model = Gemma3TextGenerate.from_weights("zeromodels/gemma-3-1b-it")
tokenizer = Gemma3Tokenizer.from_weights("zeromodels/gemma-3-1b-it")
inputs = tokenizer([{"role": "user", "content": "Hello, who are you?"}])
outputs = model.generate(**inputs, max_new_tokens=64)
print(tokenizer.decode(outputs[0]))
Load any Gemma 3 variant the same way with
from_weights("zeromodels/<variant>")
:
gemma-3-1b-it huggingface.co is an AI model on huggingface.co that provides gemma-3-1b-it's model effect (), which can be used instantly with this zeromodels gemma-3-1b-it model. huggingface.co supports a free trial of the gemma-3-1b-it model, and also provides paid use of the gemma-3-1b-it. Support call gemma-3-1b-it model through api, including Node.js, Python, http.
gemma-3-1b-it huggingface.co is an online trial and call api platform, which integrates gemma-3-1b-it's modeling effects, including api services, and provides a free online trial of gemma-3-1b-it, you can try gemma-3-1b-it online for free by clicking the link below.
zeromodels gemma-3-1b-it online free url in huggingface.co:
gemma-3-1b-it is an open source model from GitHub that offers a free installation service, and any user can find gemma-3-1b-it on GitHub to install. At the same time, huggingface.co provides the effect of gemma-3-1b-it install, users can directly use gemma-3-1b-it installed effect in huggingface.co for debugging and trial. It also supports api for free installation.