Instructions to use heegyu/TinyLlama-augesc-context-strategy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use heegyu/TinyLlama-augesc-context-strategy with Transformers:

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

pipe = pipeline("text-generation", model="heegyu/TinyLlama-augesc-context-strategy")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("heegyu/TinyLlama-augesc-context-strategy")
model = AutoModelForCausalLM.from_pretrained("heegyu/TinyLlama-augesc-context-strategy", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use heegyu/TinyLlama-augesc-context-strategy with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/heegyu/TinyLlama-augesc-context-strategy

SGLang

How to use heegyu/TinyLlama-augesc-context-strategy 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 "heegyu/TinyLlama-augesc-context-strategy" \
    --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": "heegyu/TinyLlama-augesc-context-strategy",
		"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 "heegyu/TinyLlama-augesc-context-strategy" \
        --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": "heegyu/TinyLlama-augesc-context-strategy",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use heegyu/TinyLlama-augesc-context-strategy with Docker Model Runner:
```
docker model run hf.co/heegyu/TinyLlama-augesc-context-strategy
```

Test set performance

Top 1 Accuracy: 0.4346
Top 3 Accuracy: 0.7677
Top 1 Macro F1: 0.2668
Top 3 Macro F1: 0.5669

Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification

device="cuda:0"
model = "heegyu/TinyLlama-augesc-context-strategy"
tokenizer = AutoTokenizer.from_pretrained(model)
model = AutoModelForSequenceClassification.from_pretrained(model).eval().to(device)

example = """usr: Hi
sys[Question]: Hello, how are you today?
usr: I was scolded by my parents yesterday"""

inputs = tokenizer(example, return_tensors="pt").to(device)
logits = model(**inputs).logits.softmax(-1)
print(logits)

label = logits.argmax(-1).item()


ESCONV_STRATEGY = [
    "Question",
    "Restatement or Paraphrasing",
    "Reflection of feelings",
    "Self-disclosure",
    "Affirmation and Reassurance",
    "Providing Suggestions",
    "Information",
    "Others"
]
id2label = {i:k for i, k in enumerate(ESCONV_STRATEGY)}

print(id2label[label])

Downloads last month: 9

Safetensors

Model size

1B params

Tensor type

F16

heegyu
/

TinyLlama-augesc-context-strategy

Usage

Dataset used to train heegyu/TinyLlama-augesc-context-strategy