Instructions to use yuanzhoulvpi/intermlm-7b-lml_001 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yuanzhoulvpi/intermlm-7b-lml_001 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="yuanzhoulvpi/intermlm-7b-lml_001", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("yuanzhoulvpi/intermlm-7b-lml_001", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yuanzhoulvpi/intermlm-7b-lml_001 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yuanzhoulvpi/intermlm-7b-lml_001"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yuanzhoulvpi/intermlm-7b-lml_001",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/yuanzhoulvpi/intermlm-7b-lml_001

SGLang

How to use yuanzhoulvpi/intermlm-7b-lml_001 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "yuanzhoulvpi/intermlm-7b-lml_001" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yuanzhoulvpi/intermlm-7b-lml_001",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "yuanzhoulvpi/intermlm-7b-lml_001" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yuanzhoulvpi/intermlm-7b-lml_001",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use yuanzhoulvpi/intermlm-7b-lml_001 with Docker Model Runner:
```
docker model run hf.co/yuanzhoulvpi/intermlm-7b-lml_001
```

使用lora，给internlm模型做训练
训练的时候，如何让模型知道自己的身份，并且对相关问题进行拒绝回答。这里给到相关解决方案。

模型效果

这里给大家看一下，使用我这个方法训练的模型效果：

可以看得出来：

模型有非常明显的自我认知能力；
模型懂得拒绝回答；
模型对于别的问题，回答的也还可以；

训练脚本介绍

GitHub训练代码:https://github.com/yuanzhoulvpi2017/zero_nlp/tree/main/internlm-sft

Downloads last month: 23

Safetensors

Model size

7B params

Tensor type

F32

F16

yuanzhoulvpi
/

intermlm-7b-lml_001

模型效果

训练脚本介绍

Dataset used to train yuanzhoulvpi/intermlm-7b-lml_001