Update README.md

README.md

@@ -27,4 +27,84 @@ select best ckpt by the evaluation loss
 
 The following is an evaluation on the FinerBen dataset metrci. Since there are too many samples in the dataset, I randomly selected 500 samples from each dataset for evaluation.
 
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/642f6c64f945a8a5c9ee5b5d/shSgSkQ7nQqiBAl6IwBy5.png)
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/642f6c64f945a8a5c9ee5b5d/shSgSkQ7nQqiBAl6IwBy5.png)
+
+
+## how to use
+
+```python
+
+# !/usr/bin/env python
+# -*- coding:utf-8 -*-
+# ==================================================================
+# [Author]       : xiaofeng
+# [Descriptions] :
+# ==================================================================
+
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import transformers
+import torch
+
+
+llama3_jinja = """{% if messages[0]['role'] == 'system' %}
+    {% set offset = 1 %}
+{% else %}
+    {% set offset = 0 %}
+{% endif %}
+
+{{ bos_token }}
+{% for message in messages %}
+    {% if (message['role'] == 'user') != (loop.index0 % 2 == offset) %}
+        {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}
+    {% endif %}
+
+    {{ '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' + message['content'] | trim + '<|eot_id|>' }}
+{% endfor %}
+
+{% if add_generation_prompt %}
+    {{ '<|start_header_id|>' + 'assistant' + '<|end_header_id|>\n\n' }}
+{% endif %}"""
+
+
+dtype = torch.bfloat16
+
+model_dir = "MonteXiaofeng/Finance-llama3_1_8B_instruct"
+model = AutoModelForCausalLM.from_pretrained(
+    model_dir,
+    device_map="cuda",
+    torch_dtype=dtype,
+)
+
+tokenizer = AutoTokenizer.from_pretrained(model_dir)
+tokenizer.chat_template = llama3_jinja # update template
+
+message = [
+    {"role": "system", "content": "You are a helpful assistant"},
+    {"role": "user", "content": "天气如何"},
+]
+prompt = tokenizer.apply_chat_template(
+    message, tokenize=False, add_generation_prompt=True
+)
+print(prompt)
+inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
+prompt_length = len(inputs[0])
+print(f"prompt_length:{prompt_length}")
+
+generating_args = {
+    "do_sample": True,
+    "temperature": 1.0,
+    "top_p": 0.5,
+    "top_k": 15,
+    "max_new_tokens": 150,
+}
+
+
+generate_output = model.generate(input_ids=inputs.to(model.device), **generating_args)
+
+response_ids = generate_output[:, prompt_length:]
+response = tokenizer.batch_decode(
+    response_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True
+)
+print(response)
+
+```