Instructions to use internlm/internlm2-chat-1_8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use internlm/internlm2-chat-1_8b with Transformers:

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

pipe = pipeline("text-generation", model="internlm/internlm2-chat-1_8b", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("internlm/internlm2-chat-1_8b", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use internlm/internlm2-chat-1_8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "internlm/internlm2-chat-1_8b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "internlm/internlm2-chat-1_8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/internlm/internlm2-chat-1_8b

SGLang

How to use internlm/internlm2-chat-1_8b 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 "internlm/internlm2-chat-1_8b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "internlm/internlm2-chat-1_8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "internlm/internlm2-chat-1_8b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "internlm/internlm2-chat-1_8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use internlm/internlm2-chat-1_8b with Docker Model Runner:
```
docker model run hf.co/internlm/internlm2-chat-1_8b
```

Update README.md

by kmno4 - opened Feb 8, 2024

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-3

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -142,9 +142,9 @@ InternLM2 模型具备以下的技术特点
 ```python
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
-tokenizer = AutoTokenizer.from_pretrained("internlm/internlm2-chat-1_8b-sft", trust_remote_code=True)
 # `torch_dtype=torch.float16` 可以令模型以 float16 精度加载，否则 transformers 会将模型加载为 float32，导致显存不足
-model = AutoModelForCausalLM.from_pretrained("internlm/internlm2-chat-1_8b-sft", torch_dtype=torch.float16, trust_remote_code=True).cuda()
 model = model.eval()
 response, history = model.chat(tokenizer, "你好", history=[])
 print(response)
@@ -159,7 +159,7 @@ print(response)
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
-model_path = "internlm/internlm2-chat-1_8b-sft"
 model = AutoModelForCausalLM.from_pretrained(model_path, torch_dype=torch.float16, trust_remote_code=True).cuda()
 tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

 ```python
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("internlm/internlm2-chat-1_8b", trust_remote_code=True)
 # `torch_dtype=torch.float16` 可以令模型以 float16 精度加载，否则 transformers 会将模型加载为 float32，导致显存不足
+model = AutoModelForCausalLM.from_pretrained("internlm/internlm2-chat-1_8b", torch_dtype=torch.float16, trust_remote_code=True).cuda()
 model = model.eval()
 response, history = model.chat(tokenizer, "你好", history=[])
 print(response)
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
+model_path = "internlm/internlm2-chat-1_8b"
 model = AutoModelForCausalLM.from_pretrained(model_path, torch_dype=torch.float16, trust_remote_code=True).cuda()
 tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)