Update README.md

README.md

@@ -103,50 +103,46 @@ base_url = "https://api.sarvam.ai/v1"
 model_name = "sarvam-m"
 api_key = "Your-API-Key"  # get it from https://dashboard.sarvam.ai/
 
-
 client = OpenAI(
     base_url=base_url,
     api_key=api_key,
 ).with_options(max_retries=1)
 
-response = client.chat.completions.create(
+messages = [
+    {"role": "system", "content": "You're a helpful AI assistant"},
+    {"role": "user", "content": "Explain quantum computing in simple terms"},
+]
+
+response1 = client.chat.completions.create(
     model=model_name,
-    messages=[
-        {"role": "system", "content": "say hi"},
-        {"role": "user", "content": "say hi"},
-    ],
-    stream=False,
-    max_completion_tokens=2048,
-    # reasoning_effort="low",  # set either of 3 values to enable reasoning
-)
-print(response.choices[0].message.content)
-
-response1 = client.chat.completions.create(  
-    model=model_name,  
-    messages=[  
-        {"role": "system", "content": "You're a helpful AI assistant"},  
-        {"role": "user", "content": "Explain quantum computing in simple terms"}  
-    ],
+    messages=messages,
+    reasoning_effort="medium",  # Optional reasoning mode
     max_completion_tokens=4096,
-    reasoning_effort="medium"  # Optional reasoning mode  
-)  
-print("First response:", response1.choices[0].message.content)  
-  
-# Second turn (using previous response as context)  
-response2 = client.chat.completions.create(  
-    model=model_name,  
-    messages=[  
-        {"role": "system", "content": "You're a helpful AI assistant"},  
-        {"role": "user", "content": "Explain quantum computing in simple terms"},  
-        {"role": "assistant", "content": response1.choices[0].message.content},  # Previous response  
-        {"role": "user", "content": "Can you give an analogy for superposition?"}  
-    ],  
+)
+print("First response:", response1.choices[0].message.content)
+
+# Building messages for the second turn (using previous response as context)
+messages.extend(
+    [
+        {
+            "role": "assistant",
+            "content": response1.choices[0].message.content,
+        },
+        {"role": "user", "content": "Can you give an analogy for superposition?"},
+    ]
+)
+
+response2 = client.chat.completions.create(
+    model=model_name,
+    messages=messages,
     reasoning_effort="high",
     max_completion_tokens=8192,
-)  
+)
 print("Follow-up response:", response2.choices[0].message.content)
 ```
 
+Refer to API docs here: [sarvam API docs](https://docs.sarvam.ai/api-reference-docs/introduction)
+
 # VLLM Deployment
 
 For easy deployment, we can use `vllm>=0.8.5` and create an OpenAI-compatible API endpoint with `vllm serve sarvamai/sarvam-m`
@@ -190,4 +186,16 @@ print("content:", content)
 messages.append(
     {"role": "assistant", "content": output_text}
 )
-```
+```
+
+# Running the model on a CPU
+
+The repo contains bf16 and q8 gguf files built using https://github.com/ggml-org/llama.cpp/blob/master/docs/build.md#cpu-build
+
+You can use the model using cli as explained in docs https://github.com/ggml-org/llama.cpp/tree/master/tools/main
+
+Example Command:
+
+`./build/bin/llama-cli -i -m /projects/data/romit_sarvam_ai/models/gguf/sarvam-m-q8_0.gguf -c 8192 -t 16`
+
+We got about 4 tokens per second on 16 cores.