Instructions to use mazesmazes/tiny-turn with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mazesmazes/tiny-turn with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mazesmazes/tiny-turn")
model = AutoModelForCausalLM.from_pretrained("mazesmazes/tiny-turn")
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 mazesmazes/tiny-turn with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mazesmazes/tiny-turn

SGLang

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

Docker Model Runner
How to use mazesmazes/tiny-turn with Docker Model Runner:
```
docker model run hf.co/mazesmazes/tiny-turn
```

mazesmazes commited on 15 days ago

Commit

1dc885b

verified ·

1 Parent(s): 619c3b1

Model save

Browse files

Files changed (3) hide show

README.md +76 -0
model.safetensors +1 -1
tiny_turn_meta.json +1 -0

README.md ADDED Viewed

	@@ -0,0 +1,76 @@

+---
+library_name: transformers
+license: apache-2.0
+base_model: HuggingFaceTB/SmolLM2-135M-Instruct
+tags:
+- generated_from_trainer
+model-index:
+- name: tiny-turn
+  results: []
+---
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+# tiny-turn
+This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5122
+## 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-05
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 10
+### Training results
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| 1.5988        | 0.4819 | 1000  | 1.6036          |
+| 1.5668        | 0.9639 | 2000  | 1.5508          |
+| 1.5337        | 1.4458 | 3000  | 1.5326          |
+| 1.5210        | 1.9277 | 4000  | 1.5227          |
+| 1.5078        | 2.4096 | 5000  | 1.5176          |
+| 1.5247        | 2.8916 | 6000  | 1.5157          |
+| 1.5034        | 3.3735 | 7000  | 1.5140          |
+| 1.5273        | 3.8554 | 8000  | 1.5137          |
+| 1.5209        | 4.3373 | 9000  | 1.5127          |
+| 1.5108        | 4.8193 | 10000 | 1.5123          |
+| 1.5134        | 5.3012 | 11000 | 1.5123          |
+| 1.5131        | 5.7831 | 12000 | 1.5124          |
+| 1.5197        | 6.2651 | 13000 | 1.5122          |
+| 1.5254        | 6.7470 | 14000 | 1.5122          |
+| 1.5139        | 7.2289 | 15000 | 1.5120          |
+| 1.5068        | 7.7108 | 16000 | 1.5122          |
+| 1.5128        | 8.1928 | 17000 | 1.5121          |
+| 1.5168        | 8.6747 | 18000 | 1.5122          |
+### Framework versions
+- Transformers 5.5.4
+- Pytorch 2.8.0+cu128
+- Datasets 3.6.0
+- Tokenizers 0.22.2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6256f01f8f54b2856c8c1b67f97cdfbd3118fbd0b4fc8d5af956c6a0fe598ac2
 size 269060552

 version https://git-lfs.github.com/spec/v1
+oid sha256:8978e60c2ab06988ebb3cf5eddb63e6843a9a079b62800ae7f8e1cfbf6c1023d
 size 269060552

tiny_turn_meta.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"threshold": 0.01}