Instructions to use internlm/internlm-chat-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use internlm/internlm-chat-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="internlm/internlm-chat-7b", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("internlm/internlm-chat-7b", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use internlm/internlm-chat-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "internlm/internlm-chat-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "internlm/internlm-chat-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/internlm/internlm-chat-7b
- SGLang
How to use internlm/internlm-chat-7b 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/internlm-chat-7b" \ --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": "internlm/internlm-chat-7b", "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 "internlm/internlm-chat-7b" \ --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": "internlm/internlm-chat-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use internlm/internlm-chat-7b with Docker Model Runner:
docker model run hf.co/internlm/internlm-chat-7b
AttributeError: 'InternLMConfig' object has no attribute 'rotary'
#8
by kosung - opened
v1.0.3 : AttributeError: 'InternLMConfig' object has no attribute 'rotary'
hello, why is "rotary" removed from InternLMConfig, but InternLMAttention is still called?
def _init_rope(self):
if self.config.rotary["type"] == "origin":
self.rotary_emb = InternLMRotaryEmbedding(
self.head_dim,
max_position_embeddings=self.max_position_embeddings,
base=self.config.rotary["base"],
)
elif self.config.rotary["type"] == "dynamic":
self.rotary_emb = InternLMDynamicNTKScalingRotaryEmbedding(
self.head_dim,
max_position_embeddings=self.max_position_embeddings,
base=self.config.rotary["base"],
scaling_factor=self.config.rotary.get("scaling_factor", 1.0),
)
else:
raise ValueError("Currently we only support rotary embedding's type being one of ('origin', 'dynamic').")
return self.rotary_emb
v1.0.3 : AttributeError: 'InternLMConfig' object has no attribute 'rotary'
hello, why is "rotary" removed from InternLMConfig, but InternLMAttention is still called?
def _init_rope(self): if self.config.rotary["type"] == "origin": self.rotary_emb = InternLMRotaryEmbedding( self.head_dim, max_position_embeddings=self.max_position_embeddings, base=self.config.rotary["base"], ) elif self.config.rotary["type"] == "dynamic": self.rotary_emb = InternLMDynamicNTKScalingRotaryEmbedding( self.head_dim, max_position_embeddings=self.max_position_embeddings, base=self.config.rotary["base"], scaling_factor=self.config.rotary.get("scaling_factor", 1.0), ) else: raise ValueError("Currently we only support rotary embedding's type being one of ('origin', 'dynamic').") return self.rotary_emb
You can add this to the config.json.
"rotary": {
"base": 10000,
"type": "dynamic"
}
It seems the maintainer delete it incorrectly.
