InternLM3开源发布！4T数据达到18T效果，成本省75%，首度融合深度思考与对话能力！

import torch
from modelscope import AutoTokenizer, AutoModelForCausalLM
model_dir = "Shanghai_AI_Laboratory/internlm3-8b-instruct"
#model = AutoModelForCausalLM(model_dir, trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_dir, trust_remote_code=True)
# Set `torch_dtype=torch.float16` to load model in float16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(model_dir, trust_remote_code=True, torch_dtype=torch.float16)
# (Optional) If on low resource devices, you can load model in 4-bit or 8-bit to further save GPU memory via bitsandbytes.
  # InternLM3 8B in 4bit will cost nearly 8GB GPU memory.
  # pip install -U bitsandbytes
  # 8-bit: model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, load_in_8bit=True)
  # 4-bit: model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, load_in_4bit=True)
model = model.eval()
model = model.cuda()
system_prompt = """You are an AI assistant whose name is InternLM (书生·浦语).
- InternLM (书生·浦语) is a conversational language model that is developed by Shanghai AI Laboratory (上海人工智能实验室). It is designed to be helpful, honest, and harmless.
- InternLM (书生·浦语) can understand and communicate fluently in the language chosen by the user such as English and 中文."""
messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Please tell me five scenic spots in Shanghai"},
 ]
tokenized_chat = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").cuda()
generated_ids = model.generate(tokenized_chat, max_new_tokens=1024, temperature=1, repetition_penalty=1.005, top_k=40, top_p=0.8)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(tokenized_chat, generated_ids)
].cuda()
response = tokenizer.batch_decode(generated_ids)[0]
print(response)

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

CUDA_VISIBLE_DEVICES=0 \
swift sft \
    --model Shanghai_AI_Laboratory/internlm3-8b-instruct \
    --train_type lora \
    --dataset 'AI-ModelScope/alpaca-gpt4-data-zh#500' \
              'AI-ModelScope/alpaca-gpt4-data-en#500' \
              'swift/self-cognition#500' \
    --torch_dtype bfloat16 \
    --num_train_epochs 1 \
    --per_device_train_batch_size 1 \
    --per_device_eval_batch_size 1 \
    --learning_rate 1e-4 \
    --lora_rank 8 \
    --lora_alpha 32 \
    --target_modules all-linear \
    --gradient_accumulation_steps 16 \
    --eval_steps 50 \
    --save_steps 50 \
    --save_total_limit 5 \
    --logging_steps 5 \
    --max_length 2048 \
    --output_dir output \
    --system 'You are a helpful assistant.' \
    --warmup_ratio 0.05 \
    --dataloader_num_workers 4 \
    --model_author 魔搭 \
    --model_name 狗蛋

CUDA_VISIBLE_DEVICES=0 \
swift infer \
    --adapters output/vx-xxx/checkpoint-xxx \
    --stream true \
    --temperature 0 \
    --max_new_tokens 2048