Instructions to use Ayansk11/FinSenti-DeepSeek-R1-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ayansk11/FinSenti-DeepSeek-R1-1.5B with Transformers:

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

pipe = pipeline("text-generation", model="Ayansk11/FinSenti-DeepSeek-R1-1.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ayansk11/FinSenti-DeepSeek-R1-1.5B")
model = AutoModelForCausalLM.from_pretrained("Ayansk11/FinSenti-DeepSeek-R1-1.5B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Ayansk11/FinSenti-DeepSeek-R1-1.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ayansk11/FinSenti-DeepSeek-R1-1.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ayansk11/FinSenti-DeepSeek-R1-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ayansk11/FinSenti-DeepSeek-R1-1.5B

SGLang

How to use Ayansk11/FinSenti-DeepSeek-R1-1.5B 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 "Ayansk11/FinSenti-DeepSeek-R1-1.5B" \
    --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": "Ayansk11/FinSenti-DeepSeek-R1-1.5B",
		"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 "Ayansk11/FinSenti-DeepSeek-R1-1.5B" \
        --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": "Ayansk11/FinSenti-DeepSeek-R1-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Ayansk11/FinSenti-DeepSeek-R1-1.5B with Docker Model Runner:
```
docker model run hf.co/Ayansk11/FinSenti-DeepSeek-R1-1.5B
```

FinSenti-DeepSeek-R1-1.5B

Commit History

Fix chat_template crash when assistant message omits the `content` key (#1)

23d90a8

Ayansk11

qgallouedec HF Staff commited on 20 days ago

Update model card

909c10b
verified

Ayansk11 commited on 23 days ago

Update model card

9020f26
verified

Ayansk11 commited on 24 days ago

Update model card

74199dd
verified

Ayansk11 commited on Apr 20

Update model card

1fd303c
verified

Ayansk11 commited on Apr 20

Update model card

c5f575e
verified

Ayansk11 commited on Apr 20

Upload folder using huggingface_hub

3e44c3d
verified

Ayansk11 commited on Apr 8

initial commit

637c75f
verified

Ayansk11 commited on Apr 8

Commit History

Fix chat_template crash when assistant message omits the `content` key (#1) 23d90a8

Update model card 909c10b verified

Update model card 9020f26 verified

Update model card 74199dd verified

Update model card 1fd303c verified

Update model card c5f575e verified

Upload folder using huggingface_hub 3e44c3d verified

initial commit 637c75f verified

Fix chat_template crash when assistant message omits the `content` key (#1)

23d90a8

Update model card

909c10b
verified

Update model card

9020f26
verified

Update model card

74199dd
verified

Update model card

1fd303c
verified

Update model card

c5f575e
verified

Upload folder using huggingface_hub

3e44c3d
verified

initial commit

637c75f
verified