Instructions to use hf-internal-testing/tiny-random-Gemma2ForCausalLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hf-internal-testing/tiny-random-Gemma2ForCausalLM with Transformers:

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

pipe = pipeline("text-generation", model="hf-internal-testing/tiny-random-Gemma2ForCausalLM")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hf-internal-testing/tiny-random-Gemma2ForCausalLM")
model = AutoModelForCausalLM.from_pretrained("hf-internal-testing/tiny-random-Gemma2ForCausalLM")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hf-internal-testing/tiny-random-Gemma2ForCausalLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hf-internal-testing/tiny-random-Gemma2ForCausalLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hf-internal-testing/tiny-random-Gemma2ForCausalLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/hf-internal-testing/tiny-random-Gemma2ForCausalLM

SGLang

How to use hf-internal-testing/tiny-random-Gemma2ForCausalLM 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 "hf-internal-testing/tiny-random-Gemma2ForCausalLM" \
    --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": "hf-internal-testing/tiny-random-Gemma2ForCausalLM",
		"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 "hf-internal-testing/tiny-random-Gemma2ForCausalLM" \
        --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": "hf-internal-testing/tiny-random-Gemma2ForCausalLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hf-internal-testing/tiny-random-Gemma2ForCausalLM with Docker Model Runner:
```
docker model run hf.co/hf-internal-testing/tiny-random-Gemma2ForCausalLM
```

Xenova HF Staff commited on Jul 25, 2024

Commit

dec1f9b

verified ·

1 Parent(s): 8db7a83

Update README.md

Browse files

Files changed (1) hide show

README.md +35 -0

README.md CHANGED Viewed

@@ -11,6 +11,41 @@ tags: []
 ## Model Details
 ### Model Description
 <!-- Provide a longer summary of what this model is. -->

 ## Model Details
+Tiny `Gemma2ForCausalLM` with randomly-initialized weights for testing. Code to generate:
+```py
+import torch
+from transformers import Gemma2ForCausalLM, Gemma2Config, AutoTokenizer
+# Set seed for reproducibility
+torch.manual_seed(0)
+# Initializing a Gemma2 gemma2-9b style configuration
+configuration = Gemma2Config(
+  head_dim=16,
+  hidden_size=32,
+  initializer_range=0.02,
+  intermediate_size=64,
+  max_position_embeddings=8192,
+  model_type="gemma2",
+  num_attention_heads=2,
+  num_hidden_layers=1,
+  num_key_value_heads=2,
+  vocab_size=256000,
+  attn_implementation='eager',
+)
+# Initializing a model from the gemma2-9b style configuration
+model = Gemma2ForCausalLM(configuration)
+# Re-use gemma2 tokenizer
+tokenizer = AutoTokenizer.from_pretrained("Xenova/gemma2-tokenizer")
+# Upload to the HF Hub
+model_id = 'hf-internal-testing/tiny-random-Gemma2ForCausalLM'
+model.push_to_hub(model_id)
+tokenizer.push_to_hub(model_id)
+```
 ### Model Description
 <!-- Provide a longer summary of what this model is. -->