Instructions to use deepanshdj/zephyr-7b-dj with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepanshdj/zephyr-7b-dj with Transformers:

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

pipe = pipeline("text-generation", model="deepanshdj/zephyr-7b-dj")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deepanshdj/zephyr-7b-dj")
model = AutoModelForCausalLM.from_pretrained("deepanshdj/zephyr-7b-dj", device_map="auto")
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 Settings

vLLM

How to use deepanshdj/zephyr-7b-dj with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepanshdj/zephyr-7b-dj"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepanshdj/zephyr-7b-dj",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepanshdj/zephyr-7b-dj

SGLang

How to use deepanshdj/zephyr-7b-dj 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 "deepanshdj/zephyr-7b-dj" \
    --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": "deepanshdj/zephyr-7b-dj",
		"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 "deepanshdj/zephyr-7b-dj" \
        --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": "deepanshdj/zephyr-7b-dj",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepanshdj/zephyr-7b-dj with Docker Model Runner:
```
docker model run hf.co/deepanshdj/zephyr-7b-dj
```

deepanshdj commited on May 9, 2024

Commit

90d09c7

verified ·

1 Parent(s): f442deb

Update README.md

Browse files

Files changed (1) hide show

README.md +28 -8

README.md CHANGED Viewed

@@ -5,19 +5,39 @@ license: apache-2.0
 tags:
 - text-generation-inference
 - transformers
-- unsloth
-- mistral
 - trl
 - sft
 base_model: HuggingFaceH4/zephyr-7b-beta
 ---
-# Uploaded  model
-- **Developed by:** deepanshdj
-- **License:** apache-2.0
-- **Finetuned from model :** HuggingFaceH4/zephyr-7b-beta
-This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

 tags:
 - text-generation-inference
 - transformers
+- llama
 - trl
 - sft
 base_model: HuggingFaceH4/zephyr-7b-beta
 ---
+---
+## model name: zephyr-7b-dj-F16
+## model creator: Deepansh Jha
+## huggingface id: deepanshdj
+## finetuned dataset: osaat1 (https://huggingface.co/datasets/deepanshdj/ossat1_8k_llama3)
+---
+# 🦙 Welcome to the zephyr-7b-dj-F16 Wonderland! 🌟
+## Unleash the Power of Conversation with zephyr-7b-dj-F16
+Dive into the enchanting world of zephyr-7b-dj-F16, a marvel crafted by the ingenious Deepansh Jha! 🚀 Licensed under the Apache License 2.0, this model is your passport to the realms of captivating dialogue and spellbinding text generation. 🎩✨
+## Discover the Magic
+Envisioned with creativity and nurtured with passion, zephyr-7b-dj-F16 is your companion for all things conversational! 💬 Whether you're weaving stories, sparking conversations, or crafting dialogues, this model is your trusty guide through the wonders of language. 📚🌈
+## Model Maven
+- **Model Creator:** Deepansh Jha
+- **License:** Apache License 2.0
+## Embark on Your Journey
+Unleash the potential of zephyr-7b-dj-F16 in your projects and endeavors! Let its charm and versatility illuminate your path to linguistic greatness. 🌟✨
+## Join the Adventure
+Come, be a part of this magical journey! 🎉 Contribute, explore, and create with zephyr-7b-dj-F16. The possibilities are as endless as the imagination itself! 🌌🚀