Instructions to use bartowski/Magicoder-DS-6.7B-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bartowski/Magicoder-DS-6.7B-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="bartowski/Magicoder-DS-6.7B-exl2")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("bartowski/Magicoder-DS-6.7B-exl2", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use bartowski/Magicoder-DS-6.7B-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bartowski/Magicoder-DS-6.7B-exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bartowski/Magicoder-DS-6.7B-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bartowski/Magicoder-DS-6.7B-exl2

SGLang

How to use bartowski/Magicoder-DS-6.7B-exl2 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 "bartowski/Magicoder-DS-6.7B-exl2" \
    --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": "bartowski/Magicoder-DS-6.7B-exl2",
		"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 "bartowski/Magicoder-DS-6.7B-exl2" \
        --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": "bartowski/Magicoder-DS-6.7B-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bartowski/Magicoder-DS-6.7B-exl2 with Docker Model Runner:
```
docker model run hf.co/bartowski/Magicoder-DS-6.7B-exl2
```

Magicoder-DS-6.7B-exl2 / README.md

bartowski

measurement.json

ae4b0b1 verified over 2 years ago

preview code

raw

history blame contribute delete

2.75 kB

	---
	license: other
	license_name: deepseek
	datasets:
	- ise-uiuc/Magicoder-OSS-Instruct-75K
	library_name: transformers
	pipeline_tag: text-generation
	quantized_by: bartowski
	---

	## Exllama v2 Quantizations of Magicoder-DS-6.7B

	Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.11">turboderp's ExLlamaV2 v0.0.11</a> for quantization.

	# The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)

	Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.

	Original model: https://huggingface.co/ise-uiuc/Magicoder-DS-6.7B/

	No GQA - VRAM requirements will be higher

	\| Branch \| Bits \| lm_head bits \| Size (4k) \| Size (16k) \| Description \|
	\| -------------------------------------------------------------- \| ---- \| ------------ \| --------- \| ---------- \| ----------- \|
	\| [8_0](https://huggingface.co/Bartowski/Magicoder-DS-6.7B-exl2/tree/8_0) \| 8.0 \| 8.0 \| 9.4 GB \| 15.6 GB \| Maximum quality that ExLlamaV2 can produce, near unquantized performance. \|
	\| [6_5](https://huggingface.co/Bartowski/Magicoder-DS-6.7B-exl2/tree/6_5) \| 6.5 \| 8.0 \| 8.6 GB \| 14.8 GB \| Near unquantized performance at vastly reduced size, recommended. \|
	\| [5_0](https://huggingface.co/Bartowski/Magicoder-DS-6.7B-exl2/tree/5_0) \| 5.0 \| 6.0 \| 7.2 GB \| 13.4 GB \| Slightly lower quality vs 6.5, but usable on 8GB cards with 4k context. \|
	\| [4_25](https://huggingface.co/Bartowski/Magicoder-DS-6.7B-exl2/tree/4_25) \| 4.25 \| 6.0 \| 6.5 GB \| 12.7 GB \| GPTQ equivalent bits per weight. \|
	\| [3_5](https://huggingface.co/Bartowski/Magicoder-DS-6.7B-exl2/tree/3_5) \| 3.5 \| 6.0 \| 5.9 GB \| 12.1 GB \| Lower quality, not recommended. \|

	VRAM requirements listed for both 4k context and 16k context since without GQA the differences are massive (6.2 GB)

	## Download instructions

	With git:

	```shell
	git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Magicoder-DS-6.7B-exl2 Magicoder-DS-6.7B-exl2-6_5
	```

	With huggingface hub (credit to TheBloke for instructions):

	```shell
	pip3 install huggingface-hub
	```

	To download the `main` (only useful if you only care about measurement.json) branch to a folder called `Magicoder-DS-6.7B-exl2`:

	```shell
	mkdir Magicoder-DS-6.7B-exl2
	huggingface-cli download bartowski/Magicoder-DS-6.7B-exl2 --local-dir Magicoder-DS-6.7B-exl2 --local-dir-use-symlinks False
	```

	To download from a different branch, add the `--revision` parameter:

	```shell
	mkdir Magicoder-DS-6.7B-exl2-6_5
	huggingface-cli download bartowski/Magicoder-DS-6.7B-exl2 --revision 6_5 --local-dir Magicoder-DS-6.7B-exl2-6_5 --local-dir-use-symlinks False
	```