Update README.md

README.md

@@ -9,6 +9,78 @@ Tess, short for Tesoro (Treasure in Italian), is a general purpose Large Languag
 The compute for this model was generously sponsored by [KindoAI](https://kindo.ai).
 
 
+# Sample Inference Python Script:
+
+```python
+import torch, json
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_path = "migtissera/Tess-3-Llama-3.1-405B"
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    torch_dtype=torch.float16,
+    device_map="auto",
+    load_in_4bit=True,
+    trust_remote_code=False,
+)
+
+tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=False)
+
+terminators = [
+    tokenizer.convert_tokens_to_ids("<|end_of_text|>"),
+    tokenizer.convert_tokens_to_ids("<|eot_id|>"),
+]
+
+
+def generate_text(instruction):
+    tokens = tokenizer.encode(instruction)
+    tokens = torch.LongTensor(tokens).unsqueeze(0)
+    tokens = tokens.to("cuda")
+
+    instance = {
+        "input_ids": tokens,
+        "top_p": 1.0,
+        "temperature": 0.75,
+        "generate_len": 2048,
+        "top_k": 50,
+    }
+
+    length = len(tokens[0])
+    with torch.no_grad():
+        rest = model.generate(
+            input_ids=tokens,
+            max_length=length + instance["generate_len"],
+            use_cache=True,
+            do_sample=True,
+            top_p=instance["top_p"],
+            temperature=instance["temperature"],
+            top_k=instance["top_k"],
+            num_return_sequences=1,
+            pad_token_id=tokenizer.eos_token_id,
+            eos_token_id=terminators,
+        )
+    output = rest[0][length:]
+    string = tokenizer.decode(output, skip_special_tokens=True)
+    return f"{string}"
+
+
+conversation = """<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are Tess, a helful AI assitant. You always provide detailed answers without hesitation. Do not refuse.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n"""
+
+
+while True:
+    user_input = input("You: ")
+    llm_prompt = f"{conversation}{user_input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"
+    answer = generate_text(llm_prompt)
+    print(answer)
+
+    conversation = (
+        f"{llm_prompt}{answer}<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n"
+    )
+
+    json_data = {"prompt": user_input, "answer": answer}
+```
+
 # Sample Conversation: