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

Libraries

How to use OscarNav/flan-gpt2-medium-distill with Transformers:

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

pipe = pipeline("text-generation", model="OscarNav/flan-gpt2-medium-distill")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OscarNav/flan-gpt2-medium-distill")
model = AutoModelForCausalLM.from_pretrained("OscarNav/flan-gpt2-medium-distill", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OscarNav/flan-gpt2-medium-distill with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OscarNav/flan-gpt2-medium-distill"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OscarNav/flan-gpt2-medium-distill",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OscarNav/flan-gpt2-medium-distill

SGLang

How to use OscarNav/flan-gpt2-medium-distill 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 "OscarNav/flan-gpt2-medium-distill" \
    --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": "OscarNav/flan-gpt2-medium-distill",
		"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 "OscarNav/flan-gpt2-medium-distill" \
        --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": "OscarNav/flan-gpt2-medium-distill",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OscarNav/flan-gpt2-medium-distill with Docker Model Runner:
```
docker model run hf.co/OscarNav/flan-gpt2-medium-distill
```

OscarNav commited on May 12, 2025

Commit

4c5cd19

verified ·

1 Parent(s): 70dde90

Uploaded/updated model with loss 1.368461799621582

Browse files

Files changed (3) hide show

config.json +3 -2
generation_config.json +1 -1
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -18,6 +18,7 @@
   "n_layer": 24,
   "n_positions": 1024,
   "n_special": 0,
   "predict_special_tokens": true,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
@@ -35,7 +36,7 @@
     }
   },
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.45.0",
   "use_cache": true,
-  "vocab_size": 50257
 }

   "n_layer": 24,
   "n_positions": 1024,
   "n_special": 0,
+  "pad_token_id": 50257,
   "predict_special_tokens": true,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
     }
   },
   "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.2",
   "use_cache": true,
+  "vocab_size": 50258
 }

generation_config.json CHANGED Viewed

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 50256,
   "eos_token_id": 50256,
-  "transformers_version": "4.45.0"
 }

   "_from_model_config": true,
   "bos_token_id": 50256,
   "eos_token_id": 50256,
+  "transformers_version": "4.46.2"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab7a688d661727bce04ab590d58cc6d1ca6e682b5ecbdebfb28b1552be5e502e
-size 709676664

 version https://git-lfs.github.com/spec/v1
+oid sha256:e4a61b8cffd0c486b8776fed997298de5b688b0e7964eca65a9deafd4c0ec50c
+size 709678712