Text Generation
Transformers
PyTorch
English
infimm-vicuna
multimodal
text
image
image-to-text
conversational
custom_code
Instructions to use Infi-MM/infimm-vicuna13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Infi-MM/infimm-vicuna13b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Infi-MM/infimm-vicuna13b", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Infi-MM/infimm-vicuna13b", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Infi-MM/infimm-vicuna13b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Infi-MM/infimm-vicuna13b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Infi-MM/infimm-vicuna13b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Infi-MM/infimm-vicuna13b
- SGLang
How to use Infi-MM/infimm-vicuna13b 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 "Infi-MM/infimm-vicuna13b" \ --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": "Infi-MM/infimm-vicuna13b", "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 "Infi-MM/infimm-vicuna13b" \ --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": "Infi-MM/infimm-vicuna13b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Infi-MM/infimm-vicuna13b with Docker Model Runner:
docker model run hf.co/Infi-MM/infimm-vicuna13b
| def extend_instance(obj, mixin): | |
| """Apply mixins to a class instance after creation""" | |
| base_cls = obj.__class__ | |
| base_cls_name = obj.__class__.__name__ | |
| obj.__class__ = type( | |
| base_cls_name, (mixin, base_cls), {} | |
| ) # mixin needs to go first for our forward() logic to work | |
| def getattr_recursive(obj, att): | |
| """ | |
| Return nested attribute of obj | |
| Example: getattr_recursive(obj, 'a.b.c') is equivalent to obj.a.b.c | |
| """ | |
| if att == "": | |
| return obj | |
| i = att.find(".") | |
| if i < 0: | |
| return getattr(obj, att) | |
| else: | |
| return getattr_recursive(getattr(obj, att[:i]), att[i + 1 :]) | |
| def setattr_recursive(obj, att, val): | |
| """ | |
| Set nested attribute of obj | |
| Example: setattr_recursive(obj, 'a.b.c', val) is equivalent to obj.a.b.c = val | |
| """ | |
| if "." in att: | |
| obj = getattr_recursive(obj, ".".join(att.split(".")[:-1])) | |
| setattr(obj, att.split(".")[-1], val) | |
| def _infer_decoder_layers_attr_name(model): | |
| for k in __KNOWN_DECODER_LAYERS_ATTR_NAMES: | |
| if k.lower() in model.__class__.__name__.lower(): | |
| return __KNOWN_DECODER_LAYERS_ATTR_NAMES[k] | |
| raise ValueError( | |
| "We require the attribute name for the nn.ModuleList in the decoder storing" | |
| " the transformer block layers. Please supply this string manually." | |
| ) | |
| __KNOWN_DECODER_LAYERS_ATTR_NAMES = { | |
| "llama": "model.layers", | |
| "mistral": "model.layers", | |
| } | |