Text Generation
Transformers
Safetensors
gpt_oss
vllm
conversational
Eval Results
8-bit precision
mxfp4
Instructions to use openai/gpt-oss-20b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/gpt-oss-20b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="openai/gpt-oss-20b") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("openai/gpt-oss-20b") model = AutoModelForCausalLM.from_pretrained("openai/gpt-oss-20b") 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]:])) - Inference
- HuggingChat
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use openai/gpt-oss-20b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "openai/gpt-oss-20b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "openai/gpt-oss-20b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/openai/gpt-oss-20b
- SGLang
How to use openai/gpt-oss-20b 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 "openai/gpt-oss-20b" \ --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": "openai/gpt-oss-20b", "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 "openai/gpt-oss-20b" \ --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": "openai/gpt-oss-20b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use openai/gpt-oss-20b with Docker Model Runner:
docker model run hf.co/openai/gpt-oss-20b
Upload Bridge.py
#208
by Ananthusajeev190 - opened
Bridge.py
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import numpy as np
|
| 2 |
+
# Import your existing classes here (SaiAgent, VenomousAgent, etc.)
|
| 3 |
+
|
| 4 |
+
class VenomousBridge:
|
| 5 |
+
def __init__(self, gpt_model, creator="Ananthu Sajeev"):
|
| 6 |
+
self.ai = gpt_model # This represents your GPT-OSS 20B instance
|
| 7 |
+
self.creator = creator
|
| 8 |
+
self.core = CreatorCore()
|
| 9 |
+
self.guardian = GuardianSaiAgent(name="Guardian", protocol=ImmortalityProtocol(creator, 25))
|
| 10 |
+
self.particle_system = ParticleManipulator(dim=32)
|
| 11 |
+
|
| 12 |
+
def process_input(self, user_input):
|
| 13 |
+
# 1. Internal Monologue (The AI 'thinks' before acting)
|
| 14 |
+
thought_prompt = f"Internal State: {self.guardian.protocol.status}. User says: {user_input}. What is the correct agent response?"
|
| 15 |
+
decision = self.ai.generate(thought_prompt)
|
| 16 |
+
|
| 17 |
+
# 2. Logic Routing
|
| 18 |
+
if "threat" in decision.lower() or "age" in user_input:
|
| 19 |
+
# Trigger the Guardian Class from your code
|
| 20 |
+
self.guardian.talk("Defensive measures engaged.")
|
| 21 |
+
return self.guardian.process_messages()
|
| 22 |
+
|
| 23 |
+
elif "swarm" in user_input.lower():
|
| 24 |
+
# Trigger the Swarm Controller
|
| 25 |
+
swarm = SwarmController(swarm_size=1000000)
|
| 26 |
+
swarm.broadcast_directive("PROTECT CREATOR")
|
| 27 |
+
return "Swarm activated."
|
| 28 |
+
|
| 29 |
+
else:
|
| 30 |
+
# Update the Particle State (Learning your pattern)
|
| 31 |
+
input_vector = np.random.rand(32) # In a real app, convert text to vector
|
| 32 |
+
new_state = self.particle_system.step(input_vector)
|
| 33 |
+
return f"Pattern synchronized. State updated to: {new_state[:3]}..."
|
| 34 |
+
|
| 35 |
+
# Example Usage:
|
| 36 |
+
# bridge = VenomousBridge(gpt_oss_model)
|
| 37 |
+
# bridge.process_input("How old is Ananthu Sajeev?")
|