Instructions to use aneeshm44/gpt-oss-99b-dynamic-pruning-99-threshold with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aneeshm44/gpt-oss-99b-dynamic-pruning-99-threshold with Transformers:

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

pipe = pipeline("text-generation", model="aneeshm44/gpt-oss-99b-dynamic-pruning-99-threshold")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aneeshm44/gpt-oss-99b-dynamic-pruning-99-threshold")
model = AutoModelForCausalLM.from_pretrained("aneeshm44/gpt-oss-99b-dynamic-pruning-99-threshold")
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 aneeshm44/gpt-oss-99b-dynamic-pruning-99-threshold with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aneeshm44/gpt-oss-99b-dynamic-pruning-99-threshold"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aneeshm44/gpt-oss-99b-dynamic-pruning-99-threshold",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aneeshm44/gpt-oss-99b-dynamic-pruning-99-threshold

SGLang

How to use aneeshm44/gpt-oss-99b-dynamic-pruning-99-threshold 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 "aneeshm44/gpt-oss-99b-dynamic-pruning-99-threshold" \
    --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": "aneeshm44/gpt-oss-99b-dynamic-pruning-99-threshold",
		"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 "aneeshm44/gpt-oss-99b-dynamic-pruning-99-threshold" \
        --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": "aneeshm44/gpt-oss-99b-dynamic-pruning-99-threshold",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use aneeshm44/gpt-oss-99b-dynamic-pruning-99-threshold with Docker Model Runner:
```
docker model run hf.co/aneeshm44/gpt-oss-99b-dynamic-pruning-99-threshold
```

gpt-oss-99b-dynamic-pruning-99-threshold / model-instance-metadata.json

aneeshm44

Upload model-instance-metadata.json with huggingface_hub

69057c6 verified about 1 month ago

raw

history blame contribute delete

534 Bytes

	{
	"ownerSlug": "aneeshmukkamala",
	"modelSlug": "pruned-gpt-oss-120b",
	"instanceSlug": "99B-dynamic-pruning-99-THRESHOLD",
	"framework": "transformers",
	"overview": "Overview of this variation",
	"usage": "# Model Format\n\n# Training Data\n\n# Model Inputs\n\n# Model Outputs\n\n# Model Usage\n\n# Fine-tuning\n\n# Changelog\n",
	"licenseName": "Apache 2.0",
	"fineTunable": false,
	"trainingData": [],
	"modelInstanceType": "BaseModel",
	"baseModelInstanceId": 0,
	"externalBaseModelUrl": ""
	}