幻方开源第二代MoE模型 DeepSeek-V2，魔搭社区推理、微调最佳实践教程

#模型下载from modelscope import snapshot_downloadmodel_dir = snapshot_download('deepseek-ai/DeepSeek-V2-Chat')

import torchfrom modelscope import AutoTokenizer, AutoModelForCausalLM, GenerationConfig, AutoConfig
model_name = "deepseek-ai/DeepSeek-V2-Chat"tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)# `max_memory` should be set based on your devicesmax_memory = {i: "75GB" for i in range(8)}model_config = AutoConfig.from_pretrained(model_name, trust_remote_code=True)model_config._attn_implementation='eager'model = AutoModelForCausalLM.from_pretrained(model_name, config=model_config, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16, max_memory=max_memory)model.generation_config = GenerationConfig.from_pretrained(model_name)model.generation_config.pad_token_id = model.generation_config.eos_token_id
messages = [    {"role": "user", "content": "Write a piece of quicksort code in C++"}]input_tensor = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")outputs = model.generate(input_tensor.to(model.device), max_new_tokens=100)
result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=True)print(result)

  Sure, here is a simple implementation of the quicksort algorithm in C++:
```cpp#include <iostream>#include <vector>
using namespace std;
int partition(vector<int>& arr, int low, int high) {    int pivot = arr[high];    int i = (low - 1);
    for (int j = low; j <= high - 1; j++) {        if (arr[j] < pivot) {            i++;            swap(arr[i], arr[j]);        }    }    swap(arr[i + 1], arr[high]);    return (i + 1);}
void quickSort(vector<int>& arr, int low, int high) {    if (low < high) {        int pi = partition(arr, low, high);        quickSort(arr, low, pi - 1);        quickSort(arr, pi + 1, high);    }}
int main() {    vector<int> arr = {10, 7, 8, 9, 1, 5};    int n = arr.size();    quickSort(arr, 0, n - 1);    cout << "Sorted array: \n";    for(int i = 0; i < n; i++) {        cout << arr[i] << " ";    }    return 0;}```
This code sorts an array of integers using the quicksort algorithm. The `quickSort` function is the main function that recursively sorts the array. The `partition` function is used to partition the array around a pivot element and return the index of the pivot element. The elements smaller than the pivot are moved to its left and the elements larger are moved to its right.

git clone https://github.com/modelscope/swift.gitcd swiftpip install -e .[llm]

# Experimental environment: 8*A100# 8*80GB GPU memorynproc_per_node=8CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \NPROC_PER_NODE=$nproc_per_node \swift sft \    --model_type deepseek-v2-chat \    --sft_type lora \    --tuner_backend peft \    --dtype bf16 \    --output_dir output \    --ddp_backend nccl \    --self_cognition_sample 2000 \    --model_name 小白 'Xiao Bai' \    --model_author 魔搭 'Modelscope' \    --train_dataset_sample -1 \    --num_train_epochs 1 \    --max_length 512 \    --check_dataset_strategy warning \    --lora_rank 8 \    --lora_alpha 32 \    --lora_dropout_p 0.05 \    --lora_dtype AUTO \    --lora_target_modules DEFAULT \    --gradient_checkpointing false \    --batch_size 2 \    --weight_decay 0.1 \    --learning_rate 1e-4 \    --gradient_accumulation_steps $(expr 16 / $nproc_per_node) \    --max_grad_norm 0.5 \    --warmup_ratio 0.03 \    --eval_steps 100 \    --save_steps 100 \    --save_total_limit 10 \    --logging_steps 10 \    --deepspeed default-zero3 \

# Experimental environment: A10, 3090, V100CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \swift infer \    --ckpt_dir output/deepseek-v2-chat/vx-xxx/checkpoint-xxx \    --load_dataset_config true \    --eval_human true \    --max_length 512

<<< 你是谁我是一个由魔搭开发的人工智能程序，被称为小白。我的主要目的是通过文本交流为人们提供帮助、信息和娱乐。如果你有任何疑问或需要帮助，请随时提出。