Instructions to use akshayjambhulkar/Phi-3-mini-4k-instruct-merged-16bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use akshayjambhulkar/Phi-3-mini-4k-instruct-merged-16bit with Transformers:

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

pipe = pipeline("text-generation", model="akshayjambhulkar/Phi-3-mini-4k-instruct-merged-16bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("akshayjambhulkar/Phi-3-mini-4k-instruct-merged-16bit")
model = AutoModelForCausalLM.from_pretrained("akshayjambhulkar/Phi-3-mini-4k-instruct-merged-16bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use akshayjambhulkar/Phi-3-mini-4k-instruct-merged-16bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "akshayjambhulkar/Phi-3-mini-4k-instruct-merged-16bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "akshayjambhulkar/Phi-3-mini-4k-instruct-merged-16bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/akshayjambhulkar/Phi-3-mini-4k-instruct-merged-16bit

SGLang

How to use akshayjambhulkar/Phi-3-mini-4k-instruct-merged-16bit 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 "akshayjambhulkar/Phi-3-mini-4k-instruct-merged-16bit" \
    --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": "akshayjambhulkar/Phi-3-mini-4k-instruct-merged-16bit",
		"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 "akshayjambhulkar/Phi-3-mini-4k-instruct-merged-16bit" \
        --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": "akshayjambhulkar/Phi-3-mini-4k-instruct-merged-16bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use akshayjambhulkar/Phi-3-mini-4k-instruct-merged-16bit with Docker Model Runner:
```
docker model run hf.co/akshayjambhulkar/Phi-3-mini-4k-instruct-merged-16bit
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

The uploaded model is a fine-tuned version of the Phi-3-mini model, designed for telecom customer support tasks. Here are the key details:

Developer: beingjammy
License: Apache-2.0
Base Model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit

Highlights

Training Efficiency: The model was trained 2x faster using Unsloth and Huggingface's TRL library.
Purpose: Fine-tuned specifically for handling telecom customer support queries.
Model Benefits:
- Efficiency: Optimized for faster training without compromising performance.
- Specialization: Tailored to understand and respond to customer support issues in the telecom sector.

Usage

This model can be integrated into customer support systems to provide automated responses, streamline support processes, and improve customer satisfaction by providing quick and accurate answers to common queries.

License

The model is distributed under the Apache-2.0 license, which allows for both commercial and non-commercial use, modification, and distribution.

Downloads last month: 1