Update README with inference config

README.md

@@ -14,6 +14,7 @@ datasets:
 language:
 - en
 pipeline_tag: text-generation
+library_name: transformers
 inference: true
 ---
 
@@ -40,44 +41,47 @@ This merged model can be loaded directly without needing PEFT.
 
 ## Usage
 
+### Direct Loading
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
-# Load merged model directly (no PEFT needed!)
 model = AutoModelForCausalLM.from_pretrained(
     "sainikhiljuluri/DeepSeek-R1-Cybersecurity-8B-Merged",
     torch_dtype=torch.bfloat16,
-    device_map="auto"
+    device_map="auto",
+    trust_remote_code=True
+)
+tokenizer = AutoTokenizer.from_pretrained(
+    "sainikhiljuluri/DeepSeek-R1-Cybersecurity-8B-Merged",
+    trust_remote_code=True
 )
-tokenizer = AutoTokenizer.from_pretrained("sainikhiljuluri/DeepSeek-R1-Cybersecurity-8B-Merged")
 
-# Generate
-prompt = "Explain how to detect SQL injection attacks in web server logs."
+prompt = "Explain how to detect SQL injection attacks."
 inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
 outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.7)
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
 
-## Inference API
-
-This model is deployed on HuggingFace Inference Endpoints.
-
+### Via Inference API
 ```python
-from huggingface_hub import InferenceClient
+import requests
 
-client = InferenceClient("sainikhiljuluri/DeepSeek-R1-Cybersecurity-8B-Merged")
-response = client.text_generation(
-    "What are the indicators of a ransomware attack?",
-    max_new_tokens=256
-)
-print(response)
+API_URL = "https://api-inference.huggingface.co/models/sainikhiljuluri/DeepSeek-R1-Cybersecurity-8B-Merged"
+headers = {"Authorization": "Bearer YOUR_HF_TOKEN"}
+
+response = requests.post(API_URL, headers=headers, json={
+    "inputs": "What are the indicators of a ransomware attack?",
+    "parameters": {"max_new_tokens": 256, "temperature": 0.7}
+})
+print(response.json())
 ```
 
-## Cybersecurity Tasks
+## Cybersecurity Capabilities
 
 - 🔍 Threat analysis and classification
-- 🚨 Security alert triage
+- 🚨 Security alert triage  
 - 📋 Incident response guidance
 - 🦠 Malware analysis
 - 📊 MITRE ATT&CK mapping
+- 🔐 Vulnerability assessment