Instructions to use trl-internal-testing/tiny-GPT2LMHeadModel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trl-internal-testing/tiny-GPT2LMHeadModel with Transformers:

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

pipe = pipeline("text-generation", model="trl-internal-testing/tiny-GPT2LMHeadModel")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("trl-internal-testing/tiny-GPT2LMHeadModel")
model = AutoModelForCausalLM.from_pretrained("trl-internal-testing/tiny-GPT2LMHeadModel")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use trl-internal-testing/tiny-GPT2LMHeadModel with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "trl-internal-testing/tiny-GPT2LMHeadModel"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trl-internal-testing/tiny-GPT2LMHeadModel",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/trl-internal-testing/tiny-GPT2LMHeadModel

SGLang

How to use trl-internal-testing/tiny-GPT2LMHeadModel 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 "trl-internal-testing/tiny-GPT2LMHeadModel" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trl-internal-testing/tiny-GPT2LMHeadModel",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "trl-internal-testing/tiny-GPT2LMHeadModel" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trl-internal-testing/tiny-GPT2LMHeadModel",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use trl-internal-testing/tiny-GPT2LMHeadModel with Docker Model Runner:
```
docker model run hf.co/trl-internal-testing/tiny-GPT2LMHeadModel
```

qgallouedec HF Staff commited on Dec 9, 2025

Commit

18f8dfc

verified ·

1 Parent(s): 2e6197e

Upload model

Browse files

Files changed (3) hide show

config.json +1 -1
generation_config.json +1 -1
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -27,7 +27,7 @@
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
-  "transformers_version": "4.57.0.dev0",
   "use_cache": true,
   "vocab_size": 50257
 }

   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
+  "transformers_version": "4.57.3",
   "use_cache": true,
   "vocab_size": 50257
 }

generation_config.json CHANGED Viewed

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 50256,
   "eos_token_id": 50256,
-  "transformers_version": "4.57.0.dev0"
 }

   "_from_model_config": true,
   "bos_token_id": 50256,
   "eos_token_id": 50256,
+  "transformers_version": "4.57.3"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7be33b67605f25d79fc603526434e8ca451c0a4dd743ddda54a90c9804aa2e72
 size 1650536

 version https://git-lfs.github.com/spec/v1
+oid sha256:f20b3a1600cf481c93d19325d680f7b895df71d3100d9897cca3b7f26f19fb27
 size 1650536