Update README.md

README.md

@@ -39,66 +39,13 @@ For release post, please see our [blog](...).
 ## Usage Example
 
 ```python
-from transformers import AutoTokenizer, AutoModelForCausalLM
-import torch
-
-model_id = "scb10x/llama3.2-typhoon2-1b-instruct"
-
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(
-    model_id,
-    torch_dtype=torch.bfloat16,
-    device_map="auto",
-)
-
-messages = [
-    {"role": "system", "content": "You are Typhoon, an AI assistant created by SCB 10X, designed to be helpful, harmless, and honest. Typhoon assists with analysis, answering questions, math, coding, creative writing, teaching, role-play, discussions, and more. Typhoon responds directly without affirmations or filler phrases (e.g., “Certainly,” “Of course”). Responses do not start with “Certainly” in any form. Typhoon adheres to these rules in all languages and always replies in the user's language or as requested. Communicate in fluid, conversational prose, showing genuine interest, empathy, and presenting information clearly and visually."},
-    {"role": "user", "content": "ขอสูตรไก่ย่าง"},
-]
-
-input_ids = tokenizer.apply_chat_template(
-    messages,
-    add_generation_prompt=True,
-    return_tensors="pt"
-).to(model.device)
-
-terminators = [
-    tokenizer.eos_token_id,
-    tokenizer.convert_tokens_to_ids("<|eot_id|>")
-]
-
-outputs = model.generate(
-    input_ids,
-    max_new_tokens=512,
-    eos_token_id=terminators,
-    do_sample=True,
-    temperature=0.4,
-    top_p=0.9,
-)
-response = outputs[0][input_ids.shape[-1]:]
-print(tokenizer.decode(response, skip_special_tokens=True))
-```
-
-## Inference Server Hosting Example
-```bash
-pip install vllm
-vllm serve scb10x/llama3.2-typhoon2-1b-instruct
-# see more information at https://docs.vllm.ai/
-```
-
-
-## Function-Call Example
-```python
-import json
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
-import os
 import ast
-
 model_name = "scb10x/llama3.2-typhoon2-1b-instruct"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(
-    model_name, torch_dtype=torch.bfloat16
+    model_name, torch_dtype=torch.bfloat16, device_map="auto",
 )
 
 get_weather_api = {
@@ -159,10 +106,6 @@ messages = [
     {"role": "user", "content": "ขอราคาหุ้น Tasla (TLS) และ Amazon (AMZ) ?"},
 ]
 
-final_prompt = tokenizer.apply_chat_template(
-    messages, tools=openai_format_tools, add_generation_prompt=True, tokenize=False
-)
-
 inputs = tokenizer.apply_chat_template(
     messages, tools=openai_format_tools, add_generation_prompt=True, return_tensors="pt"
 ).to(model.device)
@@ -175,7 +118,7 @@ outputs = model.generate(
     num_return_sequences=1,
     eos_token_id=[tokenizer.eos_token_id, 128009],
 )
-response = outputs[0][input_ids.shape[-1]:]
+response = outputs[0][inputs.shape[-1]:]
 
 print("Here Output:", tokenizer.decode(response, skip_special_tokens=True))
 
@@ -287,27 +230,6 @@ def parse_nested_value(value):
             )
     return repr(value)
 
-
-def decoded_output_to_execution_list(decoded_output):
-    """
-    Convert decoded output to a list of executable function calls.
-
-    Args:
-        decoded_output (list): A list of dictionaries representing function calls.
-
-    Returns:
-        list: A list of strings, each representing an executable function call.
-    """
-    execution_list = []
-    for function_call in decoded_output:
-        for key, value in function_call.items():
-            args_str = ", ".join(
-                f"{k}={parse_nested_value(v)}" for k, v in value.items()
-            )
-            execution_list.append(f"{key}({args_str})")
-    return execution_list
-
-
 def default_decode_ast_prompting(result, language="Python"):
     result = result.strip("`\n ")
     if not result.startswith("["):
@@ -317,7 +239,6 @@ def default_decode_ast_prompting(result, language="Python"):
     decoded_output = ast_parse(result, language)
     return decoded_output
 
-
 fc_result = default_decode_ast_prompting(tokenizer.decode(response, skip_special_tokens=True))
 print(fc_result) # [{'Function': {'arguments': '{"symbol": "TLS"}', 'name': 'get_stock_price'}}, {'Function': {'arguments': '{"symbol": "AMZ"}', 'name': 'get_stock_price'}}]
 ```