Instructions to use cnfusion/Mellum-4b-sft-python-mlx-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cnfusion/Mellum-4b-sft-python-mlx-fp16 with Transformers:

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

pipe = pipeline("text-generation", model="cnfusion/Mellum-4b-sft-python-mlx-fp16")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cnfusion/Mellum-4b-sft-python-mlx-fp16")
model = AutoModelForCausalLM.from_pretrained("cnfusion/Mellum-4b-sft-python-mlx-fp16")

MLX

How to use cnfusion/Mellum-4b-sft-python-mlx-fp16 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("cnfusion/Mellum-4b-sft-python-mlx-fp16")

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 cnfusion/Mellum-4b-sft-python-mlx-fp16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cnfusion/Mellum-4b-sft-python-mlx-fp16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cnfusion/Mellum-4b-sft-python-mlx-fp16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/cnfusion/Mellum-4b-sft-python-mlx-fp16

SGLang

How to use cnfusion/Mellum-4b-sft-python-mlx-fp16 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 "cnfusion/Mellum-4b-sft-python-mlx-fp16" \
    --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": "cnfusion/Mellum-4b-sft-python-mlx-fp16",
		"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 "cnfusion/Mellum-4b-sft-python-mlx-fp16" \
        --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": "cnfusion/Mellum-4b-sft-python-mlx-fp16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

MLX LM

How to use cnfusion/Mellum-4b-sft-python-mlx-fp16 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Generate some text
mlx_lm.generate --model "cnfusion/Mellum-4b-sft-python-mlx-fp16" --prompt "Once upon a time"

Docker Model Runner
How to use cnfusion/Mellum-4b-sft-python-mlx-fp16 with Docker Model Runner:
```
docker model run hf.co/cnfusion/Mellum-4b-sft-python-mlx-fp16
```

Mellum-4b-sft-python-mlx-fp16 / README.md

cnfusion

Upload README.md with huggingface_hub

a079dda verified about 1 year ago

preview code

raw

history blame contribute delete

2.63 kB

metadata

license: apache-2.0
datasets:
  - bigcode/the-stack
  - bigcode/the-stack-v2
  - bigcode/starcoderdata
  - bigcode/commitpack
library_name: transformers
tags:
  - code
  - mlx
  - mlx-my-repo
base_model: JetBrains/Mellum-4b-sft-python
model-index:
  - name: Mellum-4b-sft-python
    results:
      - task:
          type: text-generation
        dataset:
          name: RepoBench 1.1 (Python)
          type: tianyang/repobench_python_v1.1
        metrics:
          - type: exact_match
            value: 0.2837
            name: EM
            verified: false
          - type: exact_match
            value: 0.2987
            name: EM ≤ 8k
            verified: false
          - type: exact_match
            value: 0.2924
            name: EM
            verified: false
          - type: exact_match
            value: 0.306
            name: EM
            verified: false
          - type: exact_match
            value: 0.2977
            name: EM
            verified: false
          - type: exact_match
            value: 0.268
            name: EM
            verified: false
          - type: exact_match
            value: 0.2543
            name: EM
            verified: false
      - task:
          type: text-generation
        dataset:
          name: SAFIM
          type: gonglinyuan/safim
        metrics:
          - type: pass@1
            value: 0.4212
            name: pass@1
            verified: false
          - type: pass@1
            value: 0.3316
            name: pass@1
            verified: false
          - type: pass@1
            value: 0.3611
            name: pass@1
            verified: false
          - type: pass@1
            value: 0.571
            name: pass@1
            verified: false
      - task:
          type: text-generation
        dataset:
          name: HumanEval Infilling (Single-Line)
          type: loubnabnl/humaneval_infilling
        metrics:
          - type: pass@1
            value: 0.8045
            name: pass@1
            verified: false
          - type: pass@1
            value: 0.4819
            name: pass@1
            verified: false
          - type: pass@1
            value: 0.3768
            name: pass@1
            verified: false

cnfusion/Mellum-4b-sft-python-mlx-fp16

The Model cnfusion/Mellum-4b-sft-python-mlx-fp16 was converted to MLX format from JetBrains/Mellum-4b-sft-python using mlx-lm version 0.22.3.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("cnfusion/Mellum-4b-sft-python-mlx-fp16")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)