Instructions to use FBondi/phi3-mr-lora-weights with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FBondi/phi3-mr-lora-weights with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
model = PeftModel.from_pretrained(base_model, "FBondi/phi3-mr-lora-weights")

Transformers

How to use FBondi/phi3-mr-lora-weights with Transformers:

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

pipe = pipeline("text-generation", model="FBondi/phi3-mr-lora-weights")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("FBondi/phi3-mr-lora-weights", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use FBondi/phi3-mr-lora-weights with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FBondi/phi3-mr-lora-weights"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FBondi/phi3-mr-lora-weights",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FBondi/phi3-mr-lora-weights

SGLang

How to use FBondi/phi3-mr-lora-weights 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 "FBondi/phi3-mr-lora-weights" \
    --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": "FBondi/phi3-mr-lora-weights",
		"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 "FBondi/phi3-mr-lora-weights" \
        --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": "FBondi/phi3-mr-lora-weights",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FBondi/phi3-mr-lora-weights with Docker Model Runner:
```
docker model run hf.co/FBondi/phi3-mr-lora-weights
```

phi3-mr-lora-fixed-v3 (LoRA adapter)

This repository contains LoRA (PEFT) adapter weights only.
It does not include the base model weights.

Base model

microsoft/Phi-3-mini-4k-instruct

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_id = "microsoft/Phi-3-mini-4k-instruct"
adapter_id = "TUO_USERNAME/phi3-mr-lora-fixed-v3"

tokenizer = AutoTokenizer.from_pretrained(base_id)

base_model = AutoModelForCausalLM.from_pretrained(
    base_id,
    load_in_4bit=True,
    device_map="auto",
    torch_dtype="auto",
)

model = PeftModel.from_pretrained(base_model, adapter_id, device_map="auto")

Downloads last month: -

Model tree for FBondi/phi3-mr-lora-weights

Base model

microsoft/Phi-3-mini-4k-instruct

Adapter

(836)

this model