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

Libraries

How to use sergiopaniego/trainer_output with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sergiopaniego/trainer_output")
model = AutoModelForCausalLM.from_pretrained("sergiopaniego/trainer_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 sergiopaniego/trainer_output with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sergiopaniego/trainer_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": "sergiopaniego/trainer_output",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sergiopaniego/trainer_output

SGLang

How to use sergiopaniego/trainer_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 "sergiopaniego/trainer_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": "sergiopaniego/trainer_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 "sergiopaniego/trainer_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": "sergiopaniego/trainer_output",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

sergiopaniego HF Staff commited on Aug 26, 2025

Commit

0d7f3db

verified ·

1 Parent(s): 81ffc2e

Training in progress, step 60

Browse files

Files changed (3) hide show

README.md +3 -3
model.safetensors +1 -1
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -1,18 +1,18 @@
 ---
 base_model: Qwen/Qwen2-0.5B
-datasets: trl-lib/Capybara
 library_name: transformers
 model_name: trainer_output
 tags:
 - generated_from_trainer
-- sft
 - trl
 licence: license
 ---
 # Model Card for trainer_output
-This model is a fine-tuned version of [Qwen/Qwen2-0.5B](https://huggingface.co/Qwen/Qwen2-0.5B) on the [trl-lib/Capybara](https://huggingface.co/datasets/trl-lib/Capybara) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start

 ---
 base_model: Qwen/Qwen2-0.5B
 library_name: transformers
 model_name: trainer_output
 tags:
 - generated_from_trainer
 - trl
+- sft
+- generated_with_hf_jobs
 licence: license
 ---
 # Model Card for trainer_output
+This model is a fine-tuned version of [Qwen/Qwen2-0.5B](https://huggingface.co/Qwen/Qwen2-0.5B).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5faeb5f9ba69e7acefd30fffa231b12c72bb0a9c7d7d9ea6f81bb43b9304943
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:a1ab46832fe5eeda679e373a9120c7c78a15e70d62e8f352b67d757a97a269d7
 size 1976163472

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a5dc5a016efeee9eec8d64fc70271d6b715fff95ca032a3d60b5ccbfe1bace2
 size 6161

 version https://git-lfs.github.com/spec/v1
+oid sha256:3a4758b5efeb2f1c62dc7546f5d5d8943e73979b216c0e73a4a2e4168c4da7c4
 size 6161