Instructions to use huangang/Arch-Agent-7B-mlx-4Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use huangang/Arch-Agent-7B-mlx-4Bit with Transformers:

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

pipe = pipeline("text-generation", model="huangang/Arch-Agent-7B-mlx-4Bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("huangang/Arch-Agent-7B-mlx-4Bit")
model = AutoModelForCausalLM.from_pretrained("huangang/Arch-Agent-7B-mlx-4Bit")

MLX

How to use huangang/Arch-Agent-7B-mlx-4Bit 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("huangang/Arch-Agent-7B-mlx-4Bit")

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 huangang/Arch-Agent-7B-mlx-4Bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "huangang/Arch-Agent-7B-mlx-4Bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "huangang/Arch-Agent-7B-mlx-4Bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/huangang/Arch-Agent-7B-mlx-4Bit

SGLang

How to use huangang/Arch-Agent-7B-mlx-4Bit 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 "huangang/Arch-Agent-7B-mlx-4Bit" \
    --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": "huangang/Arch-Agent-7B-mlx-4Bit",
		"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 "huangang/Arch-Agent-7B-mlx-4Bit" \
        --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": "huangang/Arch-Agent-7B-mlx-4Bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

MLX LM

How to use huangang/Arch-Agent-7B-mlx-4Bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Generate some text
mlx_lm.generate --model "huangang/Arch-Agent-7B-mlx-4Bit" --prompt "Once upon a time"

Docker Model Runner
How to use huangang/Arch-Agent-7B-mlx-4Bit with Docker Model Runner:
```
docker model run hf.co/huangang/Arch-Agent-7B-mlx-4Bit
```

huangang commited on Jun 26, 2025

Commit

e2dc2bb

verified ·

1 Parent(s): 05bcfa5

Upload special_tokens_map.json with huggingface_hub

Browse files

Files changed (1) hide show

special_tokens_map.json +31 -0

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,31 @@

+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}