Instructions to use recogna-nlp/internlm-chatbode-20b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use recogna-nlp/internlm-chatbode-20b with Transformers:

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

pipe = pipeline("text-generation", model="recogna-nlp/internlm-chatbode-20b", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("recogna-nlp/internlm-chatbode-20b", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use recogna-nlp/internlm-chatbode-20b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/recogna-nlp/internlm-chatbode-20b

SGLang

How to use recogna-nlp/internlm-chatbode-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 "recogna-nlp/internlm-chatbode-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": "recogna-nlp/internlm-chatbode-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 "recogna-nlp/internlm-chatbode-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": "recogna-nlp/internlm-chatbode-20b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use recogna-nlp/internlm-chatbode-20b with Docker Model Runner:
```
docker model run hf.co/recogna-nlp/internlm-chatbode-20b
```

phpaiola commited on May 7, 2024

Commit

169e02b

verified ·

1 Parent(s): 5c1a80f

Update modeling_internlm2.py

Browse files

Files changed (1) hide show

modeling_internlm2.py +3 -3

modeling_internlm2.py CHANGED Viewed

@@ -1156,9 +1156,9 @@ class InternLM2ForCausalLM(InternLM2PreTrainedModel):
         do_sample: bool = True,
         temperature: float = 0.8,
         top_p: float = 0.8,
-        meta_instruction: str = "You are an AI assistant whose name is InternLM (书生·浦语).\n"
-        "- 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.\n"
-        "- InternLM (书生·浦语) can understand and communicate fluently in the language chosen by the user such as English and 中文.",
         **kwargs,
     ):
         inputs = self.build_inputs(tokenizer, query, history, meta_instruction)

         do_sample: bool = True,
         temperature: float = 0.8,
         top_p: float = 0.8,
+        meta_instruction: str = "Você é assistente de IA chamado InternBode.\n\
+        - O InternBode é um modelo de língua conversacional projetado para ser prestativo, honesto e inofensivo.\n\
+        - O InternBode pode entender e se comunicar fluentemente na linguagem escolhida pelo usuário, em especial o Português, o Inglês e o 中文.",
         **kwargs,
     ):
         inputs = self.build_inputs(tokenizer, query, history, meta_instruction)