Instructions to use impactframes/ifai_promptmkr_phi3_16bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use impactframes/ifai_promptmkr_phi3_16bit with Transformers:

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

pipe = pipeline("text-generation", model="impactframes/ifai_promptmkr_phi3_16bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("impactframes/ifai_promptmkr_phi3_16bit")
model = AutoModelForCausalLM.from_pretrained("impactframes/ifai_promptmkr_phi3_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 impactframes/ifai_promptmkr_phi3_16bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "impactframes/ifai_promptmkr_phi3_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": "impactframes/ifai_promptmkr_phi3_16bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/impactframes/ifai_promptmkr_phi3_16bit

SGLang

How to use impactframes/ifai_promptmkr_phi3_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 "impactframes/ifai_promptmkr_phi3_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": "impactframes/ifai_promptmkr_phi3_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 "impactframes/ifai_promptmkr_phi3_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": "impactframes/ifai_promptmkr_phi3_16bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use impactframes/ifai_promptmkr_phi3_16bit with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for impactframes/ifai_promptmkr_phi3_16bit to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for impactframes/ifai_promptmkr_phi3_16bit to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for impactframes/ifai_promptmkr_phi3_16bit to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="impactframes/ifai_promptmkr_phi3_16bit",
    max_seq_length=2048,
)

Docker Model Runner
How to use impactframes/ifai_promptmkr_phi3_16bit with Docker Model Runner:
```
docker model run hf.co/impactframes/ifai_promptmkr_phi3_16bit
```

impactframes commited on May 9, 2024

Commit

f095fa2

verified ·

1 Parent(s): a2c6c52

Update README.md

Browse files

Files changed (1) hide show

README.md +26 -1

README.md CHANGED Viewed

@@ -6,11 +6,36 @@ tags:
 - text-generation-inference
 - transformers
 - unsloth
-- mistral
 - trl
 base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
 ---
 # Uploaded  model
 - **Developed by:** impactframes

 - text-generation-inference
 - transformers
 - unsloth
+- phi3
 - trl
 base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
 ---
+![Model Visualization](https://i.imgur.com/8xr5Tz9.jpg)
+## Introduction
+The Phi3 model is equipped to deliver superior results in machine learning applications. This model is particularly effective when used in conjunction with the IF_AI_tools custom node for ComfyUI and the IF_PromptMKr, my extension for A1111 Forge and Next platforms.
+## Model Training
+LLaMA3 has been meticulously trained on a synthetic dataset comprising over 50,000 high-quality, stable diffusion prompts, ensuring robustness and high performance across various tasks.
+## Useful Links
+- [IF Prompt MKR](https://github.com/if-ai/IF_prompt_MKR)
+- [ComfyUI-IF_AI_tools](https://github.com/if-ai/ComfyUI-IF_AI_tools)
+## Support
+Your support is invaluable in continuing the development and enhancement of tools like these. If you find this tool useful, please consider extending your support by:
+- **Starring the repository** on GitHub: [Star ComfyUI-IF_AI_tools](https://github.com/if-ai/ComfyUI-IF_AI_tools)
+- **Subscribing** to my YouTube channel: [Impact Frames on YouTube](https://youtube.com/@impactframes?si=DrBu3tOAC2-YbEvc)
+- **Donating** on Ko-fi: [Support Impact Frames on Ko-fi](https://ko-fi.com/impactframes)
+- **Becoming a patron** on Patreon: [Support via Patreon](https://patreon.com/ImpactFrames)
+Thank you for your interest and support!
+- **Developed by:** impactframes
+- **License:** apache-2.0
 # Uploaded  model
 - **Developed by:** impactframes