Instructions to use gumran/gpt2-medium-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gumran/gpt2-medium-sft with Transformers:

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

pipe = pipeline("text-generation", model="gumran/gpt2-medium-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("gumran/gpt2-medium-sft")
model = AutoModelForMultimodalLM.from_pretrained("gumran/gpt2-medium-sft")
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 Settings

vLLM

How to use gumran/gpt2-medium-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gumran/gpt2-medium-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gumran/gpt2-medium-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/gumran/gpt2-medium-sft

SGLang

How to use gumran/gpt2-medium-sft 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 "gumran/gpt2-medium-sft" \
    --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": "gumran/gpt2-medium-sft",
		"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 "gumran/gpt2-medium-sft" \
        --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": "gumran/gpt2-medium-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use gumran/gpt2-medium-sft with Docker Model Runner:
```
docker model run hf.co/gumran/gpt2-medium-sft
```

gumran commited on Jun 11, 2025

Commit

0c1677c

verified ·

1 Parent(s): d027ea9

End of training

Browse files

Files changed (3) hide show

config.yaml +4 -4
model.safetensors +1 -1
training_args.bin +1 -1

config.yaml CHANGED Viewed

@@ -4,14 +4,14 @@ project_name: "scaling-post-training"
 training_args:
   seed: 42
   num_train_epochs: 1
-  per_device_train_batch_size: 2
-  per_device_eval_batch_size: 2
-  gradient_accumulation_steps: 32
   warmup_ratio: 0.05
   weight_decay: 0.01
   logging_steps: 10
   eval_strategy: "steps"
-  eval_steps: 100
   report_to: "wandb"
   fp16: true
   learning_rate: 3.0e-5

 training_args:
   seed: 42
   num_train_epochs: 1
+  per_device_train_batch_size: 4
+  per_device_eval_batch_size: 4
+  gradient_accumulation_steps: 4
   warmup_ratio: 0.05
   weight_decay: 0.01
   logging_steps: 10
   eval_strategy: "steps"
+  eval_steps: 50
   report_to: "wandb"
   fp16: true
   learning_rate: 3.0e-5

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afdc8de377cb9e8e40f0ff492f8e95ceb46a0b09a2cf6ba868c2d190dfb98583
 size 1419331072

 version https://git-lfs.github.com/spec/v1
+oid sha256:2c13ce005268a30bde2786b4c66a70bb35b751397adeb3fe38556d3fe615c400
 size 1419331072

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a07e2b08ec67e0b9d3253b18c52f3a333ac3259c863f01777cbd983360e49ea
 size 6097

 version https://git-lfs.github.com/spec/v1
+oid sha256:8edc5d723ec0aebd722c0167ece4459da84b1c47efb6c8963bc927cc12eafb2b
 size 6097