Instructions to use pradeepannepu/slm02-mlx-2Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pradeepannepu/slm02-mlx-2Bit with Transformers:

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

pipe = pipeline("text-generation", model="pradeepannepu/slm02-mlx-2Bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pradeepannepu/slm02-mlx-2Bit")
model = AutoModelForCausalLM.from_pretrained("pradeepannepu/slm02-mlx-2Bit")

MLX

How to use pradeepannepu/slm02-mlx-2Bit 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("pradeepannepu/slm02-mlx-2Bit")

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 pradeepannepu/slm02-mlx-2Bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pradeepannepu/slm02-mlx-2Bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pradeepannepu/slm02-mlx-2Bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pradeepannepu/slm02-mlx-2Bit

SGLang

How to use pradeepannepu/slm02-mlx-2Bit 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 "pradeepannepu/slm02-mlx-2Bit" \
    --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": "pradeepannepu/slm02-mlx-2Bit",
		"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 "pradeepannepu/slm02-mlx-2Bit" \
        --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": "pradeepannepu/slm02-mlx-2Bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

MLX LM

How to use pradeepannepu/slm02-mlx-2Bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Generate some text
mlx_lm.generate --model "pradeepannepu/slm02-mlx-2Bit" --prompt "Once upon a time"

Docker Model Runner
How to use pradeepannepu/slm02-mlx-2Bit with Docker Model Runner:
```
docker model run hf.co/pradeepannepu/slm02-mlx-2Bit
```

pradeepannepu commited on Mar 7

Commit

e2032ad

verified ·

1 Parent(s): 9f835d5

Upload config.json with huggingface_hub

Browse files

Files changed (1) hide show

config.json +38 -0

config.json ADDED Viewed

	@@ -0,0 +1,38 @@

+{
+    "architectures": [
+        "GemmaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 2,
+    "dtype": "float32",
+    "eos_token_id": 1,
+    "head_dim": 256,
+    "hidden_act": "gelu",
+    "hidden_activation": null,
+    "hidden_size": 256,
+    "initializer_range": 0.02,
+    "intermediate_size": 1024,
+    "max_position_embeddings": 512,
+    "model_type": "gemma",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 4,
+    "num_key_value_heads": 1,
+    "pad_token_id": 0,
+    "quantization": {
+        "group_size": 64,
+        "bits": 2,
+        "mode": "affine"
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 2,
+        "mode": "affine"
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 10000.0,
+    "transformers_version": "4.57.6",
+    "use_cache": true,
+    "vocab_size": 50257
+}