Update README.md

README.md

@@ -66,3 +66,65 @@ EOF
 # Upload the README
 huggingface-cli upload davidfred/gpt-oss-20b-f16-gguf /tmp/README.md README.md
 
+./llama-cli -m gpt-oss-20B-F16.gguf --prompt "Your prompt here" -n 128 --threads 8
+
+
+
+## Hardware Requirements
+
+- **Minimum RAM**: 16 GB (recommended: 24 GB+)
+- **CPU**: Multi-core recommended (tested on 8 vCPU)
+- **Storage**: ~13 GB free space
+- **OS**: Compatible with llama.cpp (Linux, Windows, macOS)
+
+## Performance Notes
+
+- Efficiently runs on CPU-only setups
+- Utilizes mixture of experts for optimal parameter efficiency
+- Supports both interactive and batch inference modes
+- Compatible with llama.cpp server mode for API access
+
+## Model Origin
+
+Converted from the original GPT-OSS 20B model using llama.cpp conversion tools. This F16 GGUF preserves all model capabilities while providing efficient inference performance.
+
+## License
+
+Apache 2.0 - Same as the original GPT-OSS model.
+EOF
+
+# Upload the README
+huggingface-cli upload davidfred/gpt-oss-20b-f16-gguf /tmp/README.md README.md
+Quick Upload Script (Alternative)
+If you prefer a single script approach:
+
+cat > /tmp/upload_model.py << 'EOF'
+from huggingface_hub import HfApi, create_repo
+import os
+
+# Configuration
+repo_id = "davidfred/gpt-oss-20b-f16-gguf"
+model_path = os.path.expanduser("~/openai/gpt-oss-20b/gpt-oss-20B-F16.gguf")
+
+# Create repository
+create_repo(repo_id, exist_ok=True)
+
+# Initialize API
+api = HfApi()
+
+# Upload main model file
+print("Uploading main model file...")
+api.upload_file(
+    path_or_fileobj=model_path,
+    path_in_repo="gpt-oss-20B-F16.gguf",
+    repo_id=repo_id,
+    commit_message="Add GPT-OSS 20B F16 GGUF model"
+)
+
+print(f"✅ Model uploaded successfully!")
+print(f"🔗 Repository: https://huggingface.co/{repo_id}")
+print(f"📁 Direct download: https://huggingface.co/{repo_id}/resolve/main/gpt-oss-20B-F16.gguf")
+EOF
+
+python /tmp/upload_model.py
+