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

Libraries

How to use MostafaDorrah/magicadllama with Transformers:

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

pipe = pipeline("text-generation", model="MostafaDorrah/magicadllama")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MostafaDorrah/magicadllama")
model = AutoModelForCausalLM.from_pretrained("MostafaDorrah/magicadllama")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MostafaDorrah/magicadllama with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/MostafaDorrah/magicadllama

SGLang

How to use MostafaDorrah/magicadllama 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 "MostafaDorrah/magicadllama" \
    --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": "MostafaDorrah/magicadllama",
		"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 "MostafaDorrah/magicadllama" \
        --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": "MostafaDorrah/magicadllama",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

magicadllama / README.md

MostafaDorrah

Upload folder using huggingface_hub

21cce27 verified about 2 years ago

preview code

raw

history blame contribute delete

675 Bytes

	---
	license: apache-2.0
	tags:
	- merge
	- mergekit
	- lazymergekit
	- ise-uiuc/Magicoder-S-CL-7B
	- NousResearch/Llama-2-7b-chat-hf
	---

	# magicadllama

	magicadllama is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
	* [ise-uiuc/Magicoder-S-CL-7B](https://huggingface.co/ise-uiuc/Magicoder-S-CL-7B)
	* [NousResearch/Llama-2-7b-chat-hf](https://huggingface.co/NousResearch/Llama-2-7b-chat-hf)

	## 🧩 Configuration

	```yaml
	slices:
	- sources:
	- model: ise-uiuc/Magicoder-S-CL-7B
	layer_range: [0, 32]
	- sources:
	- model: NousResearch/Llama-2-7b-chat-hf
	layer_range: [24, 32]
	merge_method: passthrough
	dtype: bfloat16

	```