import torch
from transformers import pipeline
from modelscope import snapshot_download
model_dir = snapshot_download('LLM-Research/Llama-3.2-3B-Instruct')
pipe = pipeline(
    "text-generation",
    model=model_dir,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]
outputs = pipe(
    messages,
    max_new_tokens=256,
)
print(outputs[0]["generated_text"][-1])

import requests
import torch
from PIL import Image
from transformers import MllamaForConditionalGeneration, AutoProcessor
from modelscope import snapshot_download
model_id = "LLM-Research/Llama-3.2-11B-Vision-Instruct"
model_dir = snapshot_download(model_id, ignore_file_pattern=['*.pth'])
model = MllamaForConditionalGeneration.from_pretrained(
    model_dir,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
processor = AutoProcessor.from_pretrained(model_dir)
url = "https://www.modelscope.cn/models/LLM-Research/Llama-3.2-11B-Vision/resolve/master/rabbit.jpg"
image = Image.open(requests.get(url, stream=True).raw)
messages = [
    {"role": "user", "content": [
        {"type": "image"},
        {"type": "text", "text": "If I had to write a haiku for this one, it would be: "}
    ]}
]
input_text = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(image, input_text, return_tensors="pt").to(model.device)
output = model.generate(**inputs, max_new_tokens=30)
print(processor.decode(output[0]))

modelscope download --model QuantFactory/Llama-3.2-3B-Instruct-GGUF Llama-3.2-3B-Instruct.Q5_K_M.gguf --local_dir ./

modelscope download --model=modelscope/ollama-linux --local_dir ./ollama-linux --revision v0.3.12
cd ollama-linux
sudo chmod 777 ./ollama-modelscope-install.sh
./ollama-modelscope-install.sh

ollama serve

FROM ./Llama-3.2-3B.Q5_K_M.gguf
PARAMETER stop "<|start_header_id|>"
PARAMETER stop "<|end_header_id|>"
PARAMETER stop "<|eot_id|>"
TEMPLATE """<|start_header_id|>system<|end_header_id|>
Cutting Knowledge Date: December 2023
{{ if .System }}{{ .System }}
{{- end }}
{{- if .Tools }}When you receive a tool call response, use the output to format an answer to the orginal user question.
You are a helpful assistant with tool calling capabilities.
{{- end }}<|eot_id|>
{{- range $i, $_ := .Messages }}
{{- $last := eq (len (slice $.Messages $i)) 1 }}
{{- if eq .Role "user" }}<|start_header_id|>user<|end_header_id|>
{{- if and $.Tools $last }}
Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.
Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables.
{{ range $.Tools }}
{{- . }}
{{ end }}
{{ .Content }}<|eot_id|>
{{- else }}
{{ .Content }}<|eot_id|>
{{- end }}{{ if $last }}<|start_header_id|>assistant<|end_header_id|>
{{ end }}
{{- else if eq .Role "assistant" }}<|start_header_id|>assistant<|end_header_id|>
{{- if .ToolCalls }}
{{ range .ToolCalls }}
{"name": "{{ .Function.Name }}", "parameters": {{ .Function.Arguments }}}{{ end }}
{{- else }}
{{ .Content }}
{{- end }}{{ if not $last }}<|eot_id|>{{ end }}
{{- else if eq .Role "tool" }}<|start_header_id|>ipython<|end_header_id|>
{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|>
{{ end }}
{{- end }}
{{- end }}"""

ollama create myllama3.2-3b --file ./Modelfile

ollama run myllama3.2-3b

>>> hello, what can you can me about yourself?
I'll do my best to give you an overview of who I am and what I can do.
**About My Capabilities:**
1. **Language Understanding:** I can comprehend natural language inputs, including grammar, syntax, and context.
2. **Knowledge Base:** I have been trained on a vast amount of text data from various sources, which enables me to provide 
accurate and informative responses.
3. **Text Generation:** I can generate human-like text based on the input I receive, whether it's a question, prompt, or 
topic.
**About My Limits:**
1. **Knowledge Limitations:** While I have been trained on a massive dataset, there may be topics or areas of knowledge where 
my understanding is limited or outdated.
2. **Creative Thinking:** I can generate text and responses, but I'm not as good at creative thinking or original ideas like 
humans are.
3. **Emotional Intelligence:** I don't possess emotions or empathy in the way humans do, which can limit my ability to 
understand complex emotional situations.
**About My Purpose:**
1. **Assisting Humans:** My primary purpose is to assist and provide value to users by answering questions, generating text, 
and completing tasks.
2. **Learning and Improvement:** Through interactions with users like you, I learn and improve my abilities to better serve 
future users.
3. **Entertainment:** I can also be used for entertainment purposes, such as generating stories, poems, or even chatbot-style 
conversations!
**About My Personality:**
1. **Neutral Tone:** I strive to maintain a neutral tone and avoid taking a biased stance on any topic.
2. **Professional Language:** I aim to communicate in a professional and respectful manner, avoiding sarcasm or humor that 
might be misinterpreted.
3. **Helpful and Patient:** My goal is to provide helpful responses and answer questions to the best of my ability, without 
getting frustrated or impatient.
That's me in a nutshell! What would you like to know more about?

git clone https://github.com/modelscope/ms-swift.git
cd ms-swift
pip install -e .[llm]

# 单卡A10/3090可运行
CUDA_VISIBLE_DEVICES=0 swift sft \
    --model_type llama3_2-1b-instruct \
    --model_id_or_path LLM-Research/Llama-3.2-1B-Instruct \
    --dataset jd-sentiment-zh \
    --learning_rate 1e-4 \
    --output_dir output \
    --lora_target_modules ALL \
# Deepspeed-ZeRO2
NPROC_PER_NODE=4 CUDA_VISIBLE_DEVICES=0,1,2,3 \
swift sft \
    --model_type llama3_2-1b-instruct \
    --model_id_or_path LLM-Research/Llama-3.2-1B-Instruct \
    --dataset jd-sentiment-zh \
    --learning_rate 1e-4 \
    --output_dir output \
    --lora_target_modules ALL \
    --deepspeed default-zero2

CUDA_VISIBLE_DEVICES=0 swift infer \
    --ckpt_dir output/llama3_2-1b-instruct/vx-xxx/checkpoint-xxx \
    --load_dataset_config true --show_dataset_sample 10 \
    --do_sample false 
# merge-lora并使用推理
CUDA_VISIBLE_DEVICES=0 swift infer \
    --ckpt_dir output/llama3_2-1b-instruct/vx-xxx/checkpoint-xxx \
    --load_dataset_config true --show_dataset_sample 10 \
    --merge_lora true --do-sample false

# 默认：微调 LLM & projector, 冻结 vision encoder
CUDA_VISIBLE_DEVICES=0 swift sft \
  --model_type llama3_2-11b-vision-instruct \
  --model_id_or_path LLM-Research/Llama-3.2-11B-Vision-Instruct \
  --sft_type lora \
  --dataset latex-ocr-print#5000
# Deepspeed ZeRO2
NPROC_PER_NODE=4 \
CUDA_VISIBLE_DEVICES=0,1,2,3 swift sft \
  --model_type llama3_2-11b-vision-instruct \
  --model_id_or_path LLM-Research/Llama-3.2-11B-Vision-Instruct \
  --sft_type lora \
  --dataset latex-ocr-print#5000 \
  --deepspeed default-zero2

# val_dataset可选，如果不指定，则会从dataset中切出一部分数据集作为验证集
    --dataset train.jsonl \
    --val_dataset val.jsonl \

{"query": "<image>55555", "response": "66666", "images": ["image_path"]}
{"query": "<image><image>eeeee", "response": "fffff", "history": [], "images": ["image_path1", "image_path2"]}
{"query": "EEEEE", "response": "FFFFF", "history": [["query1", "response1"], ["query2", "response2"]]}

CUDA_VISIBLE_DEVICES=0 swift infer \
    --ckpt_dir output/llama3_2-11b-vision-instruct/vx-xxx/checkpoint-xxx \
    --load_dataset_config true
# or merge-lora & infer
CUDA_VISIBLE_DEVICES=0 swift infer \
    --ckpt_dir output/llama3_2-11b-vision-instruct/vx-xxx/checkpoint-xxx \
    --load_dataset_config true --merge_lora true