Instructions to use lodestones/gemma-2b-flax with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lodestones/gemma-2b-flax with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="lodestones/gemma-2b-flax")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lodestones/gemma-2b-flax")
model = AutoModelForCausalLM.from_pretrained("lodestones/gemma-2b-flax", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lodestones/gemma-2b-flax with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lodestones/gemma-2b-flax"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lodestones/gemma-2b-flax",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/lodestones/gemma-2b-flax

SGLang

How to use lodestones/gemma-2b-flax with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "lodestones/gemma-2b-flax" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lodestones/gemma-2b-flax",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "lodestones/gemma-2b-flax" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lodestones/gemma-2b-flax",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use lodestones/gemma-2b-flax with Docker Model Runner:
```
docker model run hf.co/lodestones/gemma-2b-flax
```

lodestones commited on Feb 26, 2024

Commit

56f6f5e

verified ·

1 Parent(s): d1a3731

Update README.md

Browse files

Files changed (1) hide show

README.md +30 -13

README.md CHANGED Viewed

@@ -13,7 +13,7 @@ license_link: https://ai.google.dev/gemma/terms
 **Model Page**: [Gemma](https://ai.google.dev/gemma/docs)
-This model card corresponds to the 7B base version of the Gemma model. You can also visit the model card of the [2B base model](https://huggingface.co/google/gemma-2b), [7B instruct model](https://huggingface.co/google/gemma-7b-it), and [2B instruct model](https://huggingface.co/google/gemma-2b-it).
 **Resources and Technical Documentation**:
@@ -59,8 +59,8 @@ You can find fine-tuning notebooks under the [`examples/` directory](https://hug
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-7b")
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt")
@@ -69,6 +69,23 @@ outputs = model.generate(**input_ids)
 print(tokenizer.decode(outputs[0]))
 ```
 #### Running the model on a single / multi GPU
@@ -77,8 +94,8 @@ print(tokenizer.decode(outputs[0]))
 # pip install accelerate
 from transformers import AutoTokenizer, AutoModelForCausalLM
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", device_map="auto")
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
@@ -96,8 +113,8 @@ print(tokenizer.decode(outputs[0]))
 # pip install accelerate
 from transformers import AutoTokenizer, AutoModelForCausalLM
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", device_map="auto", torch_dtype=torch.float16)
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
@@ -112,8 +129,8 @@ print(tokenizer.decode(outputs[0]))
 # pip install accelerate
 from transformers import AutoTokenizer, AutoModelForCausalLM
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", device_map="auto", torch_dtype=torch.bfloat16)
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
@@ -132,8 +149,8 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 quantization_config = BitsAndBytesConfig(load_in_8bit=True)
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", quantization_config=quantization_config)
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
@@ -150,8 +167,8 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 quantization_config = BitsAndBytesConfig(load_in_4bit=True)
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", quantization_config=quantization_config)
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

 **Model Page**: [Gemma](https://ai.google.dev/gemma/docs)
+This model card corresponds to the 2B base version of the Gemma model. You can also visit the model card of the [7B base model](https://huggingface.co/google/gemma-7b), [7B instruct model](https://huggingface.co/google/gemma-7b-it), and [2B instruct model](https://huggingface.co/google/gemma-2b-it).
 **Resources and Technical Documentation**:
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
+model = AutoModelForCausalLM.from_pretrained("google/gemma-2b")
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt")
 print(tokenizer.decode(outputs[0]))
 ```
+#### Running the model using Flax on a single GPU / TPU
+```python
+from transformers import AutoTokenizer, FlaxGemmaForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
+model = FlaxGemmaForCausalLM.from_pretrained("google/gemma-2b-flax")
+model.params = jax.tree_map(lambda x: jax.device_put(x, jax.devices()[0]).astype(jnp.float16), flax.params)
+input_text = "Write me a poem about Machine Learning."
+input_ids = jax.device_put(tokenizer(input_text, return_tensors="jax"), jax.devices()[0])
+outputs = model.generate(**input_ids)
+print(tokenizer.decode(outputs[0][0]))
+```
 #### Running the model on a single / multi GPU
 # pip install accelerate
 from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
+model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", device_map="auto")
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
 # pip install accelerate
 from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
+model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", device_map="auto", torch_dtype=torch.float16)
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
 # pip install accelerate
 from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
+model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", device_map="auto", torch_dtype=torch.bfloat16)
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
 quantization_config = BitsAndBytesConfig(load_in_8bit=True)
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
+model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", quantization_config=quantization_config)
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
 quantization_config = BitsAndBytesConfig(load_in_4bit=True)
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
+model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", quantization_config=quantization_config)
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")