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

Libraries

How to use grozatech/sft_output with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("grozatech/sft_output")
model = AutoModelForCausalLM.from_pretrained("grozatech/sft_output")
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 grozatech/sft_output with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/grozatech/sft_output

SGLang

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

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

grozatech commited on Aug 15, 2025

Commit

8e48691

verified ·

1 Parent(s): bb52296

End of training

Browse files

Files changed (3) hide show

README.md +2 -2
runs/Aug15_11-44-03_0f202c445862/events.out.tfevents.1755258244.0f202c445862.28607.0 +3 -0
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -4,9 +4,9 @@ library_name: transformers
 model_name: sft_output
 tags:
 - generated_from_trainer
 - trl
 - smol-course
-- module_1
 - sft
 licence: license
 ---
@@ -29,7 +29,7 @@ print(output["generated_text"])
 ## Training procedure
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/groza-higher-school-of-economics/huggingface/runs/sl6xqszb)
 This model was trained with SFT.

 model_name: sft_output
 tags:
 - generated_from_trainer
+- module_1
 - trl
 - smol-course
 - sft
 licence: license
 ---
 ## Training procedure
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/groza-higher-school-of-economics/huggingface/runs/shxzblrh)
 This model was trained with SFT.

runs/Aug15_11-44-03_0f202c445862/events.out.tfevents.1755258244.0f202c445862.28607.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f34eac35a4948bb9ca525e42223cb298a839973b91760a0524f3cef6e97c854b
+size 38813

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ee74ae24f01f1c67575c4335f78b4dddc246892b6399b31fe02434121a9975a
 size 5688

 version https://git-lfs.github.com/spec/v1
+oid sha256:ecf33b6bac5aca19dad1ef41a136b91aaa0faf331d656416a5604f992c9f041c
 size 5688