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 Feb 6, 2024

Commit

c73aac2

verified ·

1 Parent(s): 5c2bd2e

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -3

README.md CHANGED Viewed

@@ -34,7 +34,7 @@ Inference speed and loading time is much faster with the 'tool' versions of the
 The intended use of SLIM models is to re-imagine traditional 'hard-coded' classifiers through the use of function calls, and to provide a natural language flexible tool that can be used as decision gates and processing steps in a complex LLM-based automation workflow.
 <details>
-<summary></summary><b>Getting Started: </b> </summary>
     model = AutoModelForCausalLM.from_pretrained("llmware/slim-sentiment")
     tokenizer = AutoTokenizer.from_pretrained("llmware/slim-sentiment")
@@ -42,7 +42,6 @@ The intended use of SLIM models is to re-imagine traditional 'hard-coded' classi
     function = "classify"
     params = "sentiment"
-    text = "That was the worst earnings call of the year.  The CEO should be fired."
     text = "The stock market declined yesterday as investors worried increasingly about the slowing economy."
     prompt = "<human>: " + text + "\n" + f"<{function}> {params} </{function}>\n<bot>:"
@@ -69,7 +68,7 @@ Sample output:
     {"sentiment": ["negative"]}
-All of the SLIM models use a novel prompt instruction structured as follows:
     "<human> " + {text} + "\n" +

 The intended use of SLIM models is to re-imagine traditional 'hard-coded' classifiers through the use of function calls, and to provide a natural language flexible tool that can be used as decision gates and processing steps in a complex LLM-based automation workflow.
 <details>
+<summary><b>Getting Started: </b> </summary>
     model = AutoModelForCausalLM.from_pretrained("llmware/slim-sentiment")
     tokenizer = AutoTokenizer.from_pretrained("llmware/slim-sentiment")
     function = "classify"
     params = "sentiment"
     text = "The stock market declined yesterday as investors worried increasingly about the slowing economy."
     prompt = "<human>: " + text + "\n" + f"<{function}> {params} </{function}>\n<bot>:"
     {"sentiment": ["negative"]}
+## Prompt Instruction format: all of the SLIM models use a novel prompt instruction structured as follows:
     "<human> " + {text} + "\n" +