Instructions to use Isotonic/smol_llama_DialogSumm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Isotonic/smol_llama_DialogSumm with Transformers:

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

pipe = pipeline("text-generation", model="Isotonic/smol_llama_DialogSumm")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Isotonic/smol_llama_DialogSumm")
model = AutoModelForCausalLM.from_pretrained("Isotonic/smol_llama_DialogSumm")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Isotonic/smol_llama_DialogSumm with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Isotonic/smol_llama_DialogSumm

SGLang

How to use Isotonic/smol_llama_DialogSumm 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 "Isotonic/smol_llama_DialogSumm" \
    --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": "Isotonic/smol_llama_DialogSumm",
		"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 "Isotonic/smol_llama_DialogSumm" \
        --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": "Isotonic/smol_llama_DialogSumm",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Isotonic/smol_llama_DialogSumm with Docker Model Runner:
```
docker model run hf.co/Isotonic/smol_llama_DialogSumm
```

smol_llama_DialogSumm

This model is a fine-tuned version of Felladrin/Smol-Llama-101M-Chat-v1 on Isotonic/DialogSumm dataset. It achieves the following results on the evaluation set:

Loss: 1.8918
Accuracy: 0.6050

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-04
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine_with_restarts
lr_scheduler_warmup_ratio: 0.3
num_epochs: 4
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	411	2.0053	0.5871
2.0885	2.0	822	1.9287	0.5971
1.8728	3.0	1233	1.8916	0.6039
1.7214	4.0	1644	1.8918	0.6050

Framework versions

Transformers 4.37.2
Pytorch 2.1.0+cu121
Datasets 2.17.0
Tokenizers 0.15.1

Downloads last month: 8

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for Isotonic/smol_llama_DialogSumm

Base model

BEE-spoke-data/smol_llama-101M-GQA

Finetuned

Felladrin/Smol-Llama-101M-Chat-v1

Finetuned

(1)

this model