Instructions to use xunker/CodeLens-7B-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xunker/CodeLens-7B-MLX with Transformers:

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

pipe = pipeline("text-generation", model="xunker/CodeLens-7B-MLX")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("xunker/CodeLens-7B-MLX", dtype="auto")

MLX

How to use xunker/CodeLens-7B-MLX 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("xunker/CodeLens-7B-MLX")

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

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

How to use xunker/CodeLens-7B-MLX with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/xunker/CodeLens-7B-MLX

SGLang

How to use xunker/CodeLens-7B-MLX 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 "xunker/CodeLens-7B-MLX" \
    --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": "xunker/CodeLens-7B-MLX",
		"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 "xunker/CodeLens-7B-MLX" \
        --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": "xunker/CodeLens-7B-MLX",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

MLX LM

How to use xunker/CodeLens-7B-MLX with MLX LM:

Generate or start a chat session

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

Docker Model Runner
How to use xunker/CodeLens-7B-MLX with Docker Model Runner:
```
docker model run hf.co/xunker/CodeLens-7B-MLX
```

CodeLens-7B-MLX

MLX version of sriksven/CodeLens-7B in various oQ levels and dtypes.

Directory	oQ Level	dtype	size
CodeLens-7B-oQ4-bf16	4-bit	bfloat16	4.2GB
CodeLens-7B-oQ4-fp16	4-bit	fp16	4.2GB
CodeLens-7B-oQ5-bf16	5-bit	bfloat16	5.1GB
CodeLens-7B-oQ5-fp16	5-bit	fp16	5.1GB
CodeLens-7B-oQ6-bf16	6-bit	bfloat16	5.9GB
CodeLens-7B-oQ6-fp16	6-bit	fp16	5.9GB
CodeLens-7B-oQ8-bf16	8-bit	bfloat16	7.5GB
CodeLens-7B-oQ8-fp16	8-bit	fp16	7.5GB

Why choose FP16 over BFLOAT16/BF16?

On older Apple Silicon (M1 and M2), fp16 can be faster. Here are the details from Muhammad Raza:

A lot of MLX builds ship as bf16, and on the M1 and M2 that data type does not get the accelerated path that fp16 does. During prefill those weights run un-accelerated and the penalty multiplies across every input token, which is part of why some “MLX is slow” reports come from older hardware. [...]

If you are on an M1 or M2 and MLX feels sluggish, check this before you blame the format.

Test Results

Using oQ6, here are the results from oMLX 0.4.4 on a Macbook Pro 2021 (M1 Pro).

tl;dr:

Time to First Token (TTFT) and Prompt Processing Tokens Per Second (ppTPS, aka "prefill speed") are about 60% faster when using FP16.

However, Token Generation (tgTPS) only increases moderately, around 1-2%.

BFLOAT16

Single request results

Test	TTFT(ms)	TPOT(ms)	ppTPS	tgTPS	E2E(s)	Throughput	PeakMem
pp 4096 / tg 128	24727.9	39.3	165.6	25.7	29.7	142.1	6.84 GB
pp 16384 / tg 128	111811.1	48.4	146.5	20.8	118.0	140.0	7.69 GB

Batch results

Batch	tgTPS	ppTPS	avgTTFT(ms)	E2E(s)	Speedup
1x baseline	25.7	165.6	24727.9	29.7	1.00x
2x	30.0	164.0	12487.3	21.0	1.17x
4x	31.9	239.7	16885.7	33.1	1.24x

FP16

Single request results

Test	TTFT(ms)	TPOT(ms)	ppTPS	tgTPS	E2E(s)	Throughput	PeakMem
pp 4096 / tg 128	15226.8	37.3	269.0	27.0	20.0	211.6	6.84 GB
pp 16384 / tg 128	69595.4	45.6	235.4	22.1	75.4	219.0	7.69 GB

Batch results

Batch	tgTPS	ppTPS	avgTTFT(ms)	E2E(s)	Speedup
1x baseline	27.0	269.0	15226.8	20.0	1.00x
2x	36.9	266.6	7681.4	14.6	1.37x
4x	38.0	363.3	11084.7	24.8	1.41x

Hardware and Software

These were converted to MLX using oMLX 0.4.4 on a 32GB Macbook Pro 2021 (M1 Pro). I cleared all my RAM so you don't have to.

License

Apache 2.0, as per original model.

Downloads last month: -; Downloads are not tracked for this model. How to track

MLX

Hardware compatibility

Quantized

Model tree for xunker/CodeLens-7B-MLX

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Finetuned

(2639)

this model

xunker
/

CodeLens-7B-MLX

CodeLens-7B-MLX

Why choose FP16 over BFLOAT16/BF16?

Test Results

BFLOAT16

Single request results

Batch results

FP16

Single request results

Batch results

Hardware and Software

License

Model tree for xunker/CodeLens-7B-MLX

Dataset used to train xunker/CodeLens-7B-MLX