Instructions to use llmware/slim-sentiment with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llmware/slim-sentiment with Transformers:

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

pipe = pipeline("text-generation", model="llmware/slim-sentiment")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("llmware/slim-sentiment")
model = AutoModelForCausalLM.from_pretrained("llmware/slim-sentiment", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use llmware/slim-sentiment with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/llmware/slim-sentiment

SGLang

How to use llmware/slim-sentiment 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 "llmware/slim-sentiment" \
    --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": "llmware/slim-sentiment",
		"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 "llmware/slim-sentiment" \
        --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": "llmware/slim-sentiment",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use llmware/slim-sentiment with Docker Model Runner:
```
docker model run hf.co/llmware/slim-sentiment
```

doberst commited on Jan 22, 2024

Commit

e2fac82

verified ·

1 Parent(s): 9c87204

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -3

README.md CHANGED Viewed

@@ -10,7 +10,9 @@ license: apache-2.0
 slim-sentiment has been fine-tuned for **sentiment analysis** function calls, generating output consisting of JSON dictionary corresponding to specified keys.
-Each slim model has a corresponding 'tool' in a separate repository, e.g., [**'slim-sentiment-tool'**](https://huggingface.co/llmware/slim-sentiment-tool), which a 4-bit quantized gguf version of the model that is intended to be used for inference.
 Inference speed and loading time is much faster with the 'tool' versions of the model.
@@ -42,7 +44,7 @@ All of the SLIM models use a novel prompt instruction structured as follows:
     "<human> " + text + "<classify> " + keys + "</classify>" + "/n<bot>: "
-=
 ## How to Get Started with the Model
 The fastest way to get started with BLING is through direct import in transformers:
@@ -87,7 +89,6 @@ The fastest way to get started with BLING is through direct import in transforme
     except:
         print("could not convert to json automatically - ", output_only)
-   '''
 ## Using as Function Call in LLMWare

 slim-sentiment has been fine-tuned for **sentiment analysis** function calls, generating output consisting of JSON dictionary corresponding to specified keys.
+Each slim model has a corresponding 'tool' in a separate repository, e.g.,
+[**'slim-sentiment-tool'**](https://huggingface.co/llmware/slim-sentiment-tool), which a 4-bit quantized gguf version of the model that is intended to be used for inference.
 Inference speed and loading time is much faster with the 'tool' versions of the model.
     "<human> " + text + "<classify> " + keys + "</classify>" + "/n<bot>: "
 ## How to Get Started with the Model
 The fastest way to get started with BLING is through direct import in transformers:
     except:
         print("could not convert to json automatically - ", output_only)
 ## Using as Function Call in LLMWare