Chartgpt Llama3

from transformers import (
    AutoTokenizer,
    AutoModelForCausalLM,
)
tokenizer = AutoTokenizer.from_pretrained("yuan-tian/chartgpt-llama3")
model = AutoModelForCausalLM.from_pretrained("yuan-tian/chartgpt-llama3", device_map="auto")
input_text = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
Your response should follow the following format:
Step 1. Select the columns:
Step 2. Filter the data:
Step 3. Add aggregate functions:
Step 4. Choose chart type:
Step 5. Select encodings:
Step 6. Sort the data:

### Instruction:
Give me a visual representation of the faculty members by their professional status.

### Input:
Table Name: Faculty
Table Header: FacID,Lname,Fname,Rank,Sex,Phone,Room,Building
Table Header Type: quantitative,nominal,nominal,nominal,nominal,quantitative,nominal,nominal
Table Data Example:
1082,Giuliano,Mark,Instructor,M,2424,224,NEB
1121,Goodrich,Michael,Professor,M,3593,219,NEB
Previous Answer:


### Response:"""
inputs = tokenizer(input_text, return_tensors="pt", padding=True).to("cuda")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens = True))

步骤 x 的模型输入。

Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
Your response should follow the following format:
{Step 1 prompt}

{Step x-1 prompt}
{Step x prompt}

### Instruction:
{instruction}

### Input:
Table Name: {table name}
Table Header: {column names}
Table Header Type: {column types}
Table Data Example:
{data row 1}
{data row 2}
Previous Answer:
{previous answer}

### Response:

模型应输出对应步骤 x 的答案。

步骤 1 - 6 的提示如下：

Step 1. Select the columns:
Step 2. Filter the data:
Step 3. Add aggregate functions:
Step 4. Choose chart type:
Step 5. Select encodings:
Step 6. Sort the data: