Issue with converting to ONNX format for LLM models about turnkeyml HOT 3 CLOSED

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")

messages = [
    {"role": "user", "content": "What is your favourite condiment?"},
    {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
    {"role": "user", "content": "Do you have mayonnaise recipes?"}
]

encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")

result = model(encodeds)

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# This is minimum setup required to convert LLM models (PyTorch) into ONNX Formats
# This converted ONNXR format can be viewed into Netron app

# Load the tokenizer and model
torch.set_default_device("cpu")
model_id = "mistralai/Mistral-7B-Instruct-v0.2"
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float32, device_map="cpu", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)

text_prompt = [
    {"role": "user", "content": "What is your favourite condiment?"},
    {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
    {"role": "user", "content": "Do you have mayonnaise recipes?"}
]

# Tokenize the prompt and convert to PyTorch tensors
inputs = tokenizer.apply_chat_template(text_prompt, return_tensors="pt")

# Generate text using the model
# Replace model.generate() call with a model() to reduce the call to auto-regressive models
# https://github.com/onnx/turnkeyml/issues/95

outputs = model(inputs)

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# This is minimum setup required to convert LLM models (PyTorch) into ONNX Formats
# This converted ONNXR format can be viewed into Netron app

# Load the tokenizer and model
torch.set_default_device("cpu")
model_id = "adept/fuyu-8b"
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float32, device_map="cpu", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)

text_prompt = "<s> <|sys_start|> You are an AI assistant. You will be given a task. You must generate a detailed and long answer. <|sys_end|> <|im_start|> Write a python function that takes a list of integers and returns the squared sum of the list. <|im_end|>"

# Tokenize the prompt and convert to PyTorch tensors
inputs = tokenizer(text_prompt, return_tensors="pt")

# Generate text using the model
# Replace model.generate() call with a model() to reduce the call to auto-regressive models
# https://github.com/onnx/turnkeyml/issues/95

outputs = model(**inputs)