Instructions to use internlm/internlm2-math-base-20b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use internlm/internlm2-math-base-20b with Transformers:

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

pipe = pipeline("text-generation", model="internlm/internlm2-math-base-20b", 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-math-base-20b", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use internlm/internlm2-math-base-20b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "internlm/internlm2-math-base-20b"
# 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-math-base-20b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/internlm/internlm2-math-base-20b

SGLang

How to use internlm/internlm2-math-base-20b 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-math-base-20b" \
    --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-math-base-20b",
		"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-math-base-20b" \
        --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-math-base-20b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use internlm/internlm2-math-base-20b with Docker Model Runner:
```
docker model run hf.co/internlm/internlm2-math-base-20b
```

InternLM-Math commited on Jan 23, 2024

Commit

f491935

verified ·

1 Parent(s): fdc6633

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -13

README.md CHANGED Viewed

@@ -87,18 +87,8 @@ We suggest using [LMDeploy](https://github.com/InternLM/LMDeploy)(>=0.2.1) for i
 from lmdeploy import pipeline, TurbomindEngineConfig, ChatTemplateConfig
 backend_config = TurbomindEngineConfig(model_name='internlm2-chat-7b', tp=1, cache_max_entry_count=0.3)
-chat_template = ChatTemplateConfig(model_name='internlm2-chat-7b',
-                                system='',
-                                eosys='',
-                                meta_instruction='',
-                                user='<|im_start|>user\n',
-                                assistant='<|im_start|>assistant\n',
-                                eoh='<|im_end|>\n',
-                                eoa='<|im_end|>\n',
-                                stop_words=['<|im_end|>', '<|action_end|>'])
-pipe = pipeline(model_path='internlm/internlm2-math-7b',
-                chat_template_config=chat_template,
-                backend_config=backend_config)
 problem = '1+1='
 result = pipe([problem], request_output_len=1024, top_k=1)
@@ -112,7 +102,7 @@ tokenizer = AutoTokenizer.from_pretrained("internlm/internlm2-math-7b", trust_re
 # 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("internlm/internlm2-math-7b", trust_remote_code=True, torch_dtype=torch.float16).cuda()
 model = model.eval()
-response, history = model.chat(tokenizer, "1+1=", history=[])
 print(response)
 ```

 from lmdeploy import pipeline, TurbomindEngineConfig, ChatTemplateConfig
 backend_config = TurbomindEngineConfig(model_name='internlm2-chat-7b', tp=1, cache_max_entry_count=0.3)
+chat_template = ChatTemplateConfig(model_name='internlm2-chat-7b', system='', eosys='', meta_instruction='')
+pipe = pipeline(model_path='internlm/internlm2-math-7b', chat_template_config=chat_template, backend_config=backend_config)
 problem = '1+1='
 result = pipe([problem], request_output_len=1024, top_k=1)
 # 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("internlm/internlm2-math-7b", trust_remote_code=True, torch_dtype=torch.float16).cuda()
 model = model.eval()
+response, history = model.chat(tokenizer, "1+1=", history=[], meta_instruction="")
 print(response)
 ```