Instructions to use curiousily/tiny-crypto-sentiment-analysis with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use curiousily/tiny-crypto-sentiment-analysis with Transformers:

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

pipe = pipeline("text-generation", model="curiousily/tiny-crypto-sentiment-analysis")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("curiousily/tiny-crypto-sentiment-analysis")
model = AutoModelForCausalLM.from_pretrained("curiousily/tiny-crypto-sentiment-analysis")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use curiousily/tiny-crypto-sentiment-analysis with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/curiousily/tiny-crypto-sentiment-analysis

SGLang

How to use curiousily/tiny-crypto-sentiment-analysis 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 "curiousily/tiny-crypto-sentiment-analysis" \
    --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": "curiousily/tiny-crypto-sentiment-analysis",
		"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 "curiousily/tiny-crypto-sentiment-analysis" \
        --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": "curiousily/tiny-crypto-sentiment-analysis",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use curiousily/tiny-crypto-sentiment-analysis with Docker Model Runner:
```
docker model run hf.co/curiousily/tiny-crypto-sentiment-analysis
```

curiousily commited on Feb 13, 2024

Commit

f0b6f68

verified ·

1 Parent(s): b63e376

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -2

README.md CHANGED Viewed

@@ -27,8 +27,7 @@ tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, use_fast=True)
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_NAME,
     device_map="auto",
-    torch_dtype=torch.float16,
-    trust_remote_code=True,
 )
 pipe = pipeline(

 model = AutoModelForCausalLM.from_pretrained(
     MODEL_NAME,
     device_map="auto",
+    torch_dtype=torch.float16
 )
 pipe = pipeline(