Instructions to use mlx-community/Pearl-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/Pearl-7B with Transformers:

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

pipe = pipeline("text-generation", model="mlx-community/Pearl-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mlx-community/Pearl-7B")
model = AutoModelForCausalLM.from_pretrained("mlx-community/Pearl-7B")

MLX

How to use mlx-community/Pearl-7B with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm
# if on a CUDA device, also pip install mlx[cuda]

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Pearl-7B")

prompt = "Once upon a time in"
text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps
LM Studio

vLLM

How to use mlx-community/Pearl-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlx-community/Pearl-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/Pearl-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mlx-community/Pearl-7B

SGLang

How to use mlx-community/Pearl-7B 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 "mlx-community/Pearl-7B" \
    --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": "mlx-community/Pearl-7B",
		"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 "mlx-community/Pearl-7B" \
        --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": "mlx-community/Pearl-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

MLX LM

How to use mlx-community/Pearl-7B with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Generate some text
mlx_lm.generate --model "mlx-community/Pearl-7B" --prompt "Once upon a time"

Docker Model Runner
How to use mlx-community/Pearl-7B with Docker Model Runner:
```
docker model run hf.co/mlx-community/Pearl-7B
```

mlx-community/Pearl-7B

This model was converted to MLX format from louisbrulenaudet/Pearl-7B-0211-ties using mlx-vlm version 0.15.2. Refer to the original model card for more details on the model.

Use with mlx

pip install -U mlx-vlm
python -m mlx_vlm.generate --model  mlx-community/Pearl-7B --max-tokens 100 --temp 0.0

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Pearl-7B")
response = generate(model, tokenizer, prompt="hello", verbose=True)

Citing & Authors

If you use this code in your research, please use the following BibTeX entry.

@misc{louisbrulenaudet2024,
  author =       {Louis Brulé Naudet},
  title =        {Pearl-7B-0211-ties, an xtraordinary 7B model},
  year =         {2024}
  howpublished = {\url{https://huggingface.co/louisbrulenaudet/Pearl-7B-0211-ties}},
}

Feedback

If you have any feedback, please reach out at louisbrulenaudet@icloud.com.

Downloads last month: 5

MLX

Hardware compatibility

Quantized

Model tree for mlx-community/Pearl-7B

Base model

louisbrulenaudet/Pearl-7B-0211-ties

Finetuned

(1)

this model

Datasets used to train mlx-community/Pearl-7B

Evaluation results

Average
Open LLM Leaderboard

75.110
ARC
Open LLM Leaderboard

71.420
GSM8K
Open LLM Leaderboard

70.660
Winogrande
Open LLM Leaderboard

84.370
TruthfulQA
Open LLM Leaderboard

71.460
HellaSwag
Open LLM Leaderboard

88.860