Instructions to use alhusains/gpt-oss-20b-ddx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alhusains/gpt-oss-20b-ddx with Transformers:

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

pipe = pipeline("text-generation", model="alhusains/gpt-oss-20b-ddx")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("alhusains/gpt-oss-20b-ddx", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use alhusains/gpt-oss-20b-ddx with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alhusains/gpt-oss-20b-ddx"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alhusains/gpt-oss-20b-ddx",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/alhusains/gpt-oss-20b-ddx

SGLang

How to use alhusains/gpt-oss-20b-ddx 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 "alhusains/gpt-oss-20b-ddx" \
    --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": "alhusains/gpt-oss-20b-ddx",
		"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 "alhusains/gpt-oss-20b-ddx" \
        --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": "alhusains/gpt-oss-20b-ddx",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use alhusains/gpt-oss-20b-ddx with Docker Model Runner:
```
docker model run hf.co/alhusains/gpt-oss-20b-ddx
```

alhusains commited on Nov 26, 2025

Commit

e5456f1

1 Parent(s): c805f3f

update readme

Browse files

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -32,16 +32,16 @@ model-index:
           name: Eurorad radiology cases
         metrics:
           - type: accuracy
-            value: 0.8615
             name: exact-match accuracy
 ---
-# **GPT-OSS-20B – Eurorad Radiology Reasoning (LoRA Adapter)**
-This repository provides a **LoRA adapter** fine-tuned on radiology cases from the **Eurorad** library to enhance differential diagnosis and structured medical reasoning. The adapter attaches to the base model **`openai/gpt-oss-20b`**, enabling stronger radiology-focused performance while remaining lightweight and deployable on a single GPU.
 **Highlights**
-- Improved **differential diagnosis accuracy** on Eurorad cases (from 78.6% → **86.2%**)
 - Trained with **structured chain-of-thought** derived from gpt-oss-120b
 - Adapter-only; the base model remains unchanged
 - Works with **Unsloth**, **PEFT**, and **Transformers**
@@ -86,4 +86,4 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 - **Framework:** Unsloth + PEFT (4-bit training)
 - **Precision:** bfloat16 mixed precision
 - **Training schedule:** 3 epochs, AdamW, LR = 1e-4 with cosine decay and warmup
-- **Result:** Improved exact-match diagnostic accuracy on Eurorad cases (base 78.6% → **86.2%**)

           name: Eurorad radiology cases
         metrics:
           - type: accuracy
+            value: 0.862
             name: exact-match accuracy
 ---
+# **GPT-OSS-20B – Differential Diagnosis Radiology Reasoning**
+This repository provides a **LoRA adapter** fine-tuned on radiology cases from the **Eurorad** dataset to enhance differential diagnosis and structured medical reasoning. The adapter attaches to the base model **`openai/gpt-oss-20b`**, enabling stronger radiology-focused performance while remaining lightweight and deployable on a single GPU.
 **Highlights**
+- Improved **differential diagnosis accuracy** on Eurorad cases (exact match boost from 78.6% → **86.2%**)
 - Trained with **structured chain-of-thought** derived from gpt-oss-120b
 - Adapter-only; the base model remains unchanged
 - Works with **Unsloth**, **PEFT**, and **Transformers**
 - **Framework:** Unsloth + PEFT (4-bit training)
 - **Precision:** bfloat16 mixed precision
 - **Training schedule:** 3 epochs, AdamW, LR = 1e-4 with cosine decay and warmup
+- **Result:** Improved exact-match diagnostic accuracy on Eurorad cases (base 78.6% → fine-tuned **86.2%**)