Instructions to use sajal09/MNLP_M3_quantized_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sajal09/MNLP_M3_quantized_model with Transformers:

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

pipe = pipeline("text-generation", model="sajal09/MNLP_M3_quantized_model")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sajal09/MNLP_M3_quantized_model")
model = AutoModelForCausalLM.from_pretrained("sajal09/MNLP_M3_quantized_model", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sajal09/MNLP_M3_quantized_model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sajal09/MNLP_M3_quantized_model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sajal09/MNLP_M3_quantized_model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/sajal09/MNLP_M3_quantized_model

SGLang

How to use sajal09/MNLP_M3_quantized_model 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 "sajal09/MNLP_M3_quantized_model" \
    --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": "sajal09/MNLP_M3_quantized_model",
		"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 "sajal09/MNLP_M3_quantized_model" \
        --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": "sajal09/MNLP_M3_quantized_model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sajal09/MNLP_M3_quantized_model with Docker Model Runner:
```
docker model run hf.co/sajal09/MNLP_M3_quantized_model
```

sajal09 commited on Jun 10, 2025

Commit

6c0dd4b

verified ·

1 Parent(s): 0efb7b1

Upload recipe.yaml

Browse files

Files changed (1) hide show

recipe.yaml +12 -0

recipe.yaml ADDED Viewed

	@@ -0,0 +1,12 @@

+default_stage:
+  default_modifiers:
+    SmoothQuantModifier: {smoothing_strength: 0.7}
+    GPTQModifier:
+      config_groups:
+        group_0:
+          targets: [Linear]
+          weights: {num_bits: 4, type: int, symmetric: true, strategy: channel, dynamic: false,
+            observer: minmax}
+          input_activations: {num_bits: 8, type: int, symmetric: true, strategy: token, dynamic: true,
+            observer: null}
+      ignore: [lm_head]