Instructions to use hyokwan/fintech_gemma_2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hyokwan/fintech_gemma_2b with Transformers:

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

pipe = pipeline("text-generation", model="hyokwan/fintech_gemma_2b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hyokwan/fintech_gemma_2b")
model = AutoModelForCausalLM.from_pretrained("hyokwan/fintech_gemma_2b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hyokwan/fintech_gemma_2b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hyokwan/fintech_gemma_2b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hyokwan/fintech_gemma_2b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hyokwan/fintech_gemma_2b

SGLang

How to use hyokwan/fintech_gemma_2b 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 "hyokwan/fintech_gemma_2b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hyokwan/fintech_gemma_2b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "hyokwan/fintech_gemma_2b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hyokwan/fintech_gemma_2b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use hyokwan/fintech_gemma_2b with Docker Model Runner:
```
docker model run hf.co/hyokwan/fintech_gemma_2b
```

hyokwan commited on Apr 13

Commit

fc917a7

verified ·

1 Parent(s): d900225

Upload GemmaForCausalLM

Browse files

Files changed (3) hide show

README.md +1 -1
model-00001-of-00002.safetensors +1 -1
model-00002-of-00002.safetensors +1 -1

README.md CHANGED Viewed

@@ -10,4 +10,4 @@ base_model:
 - google/gemma-2b
 pipeline_tag: text-generation
 library_name: transformers
----

 - google/gemma-2b
 pipeline_tag: text-generation
 library_name: transformers
+---

model-00001-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9ab732d2a3756b8a850c5cf51384016d5eca3a8c3bba766298ff330820a61cd
 size 4945242104

 version https://git-lfs.github.com/spec/v1
+oid sha256:24ce1cffd65f586ca25cc2c56fa4868e0a3939a9aa9b8ca937b6945e510fc288
 size 4945242104

model-00002-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ad177a71f8db9e20efe063068cc316a103640ac21fff56d00abecdcdadffcbd
 size 67121600

 version https://git-lfs.github.com/spec/v1
+oid sha256:eb6c2e843cde1566872e1dbd176ea5e630eb4bc42bf10ffe85289ced36854fa9
 size 67121600