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

Libraries

How to use clejordan/MNLP_M3_quantized_model with Transformers:

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

pipe = pipeline("text-generation", model="clejordan/MNLP_M3_quantized_model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("clejordan/MNLP_M3_quantized_model")
model = AutoModelForCausalLM.from_pretrained("clejordan/MNLP_M3_quantized_model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use clejordan/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 "clejordan/MNLP_M3_quantized_model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "clejordan/MNLP_M3_quantized_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/clejordan/MNLP_M3_quantized_model

SGLang

How to use clejordan/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 "clejordan/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/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "clejordan/MNLP_M3_quantized_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "clejordan/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/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "clejordan/MNLP_M3_quantized_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

clejordan commited on Jun 10, 2025

Commit

0c4c937

verified ·

1 Parent(s): d7713bb

Upload Qwen3ForCausalLM

Browse files

Files changed (2) hide show

config.json +13 -41
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -18,47 +18,19 @@
   "num_hidden_layers": 28,
   "num_key_value_heads": 8,
   "quantization_config": {
-    "config_groups": {
-      "group_0": {
-        "input_activations": {
-          "actorder": null,
-          "block_structure": null,
-          "dynamic": true,
-          "group_size": null,
-          "num_bits": 8,
-          "observer": null,
-          "observer_kwargs": {},
-          "strategy": "token",
-          "symmetric": true,
-          "type": "int"
-        },
-        "output_activations": null,
-        "targets": [
-          "Linear"
-        ],
-        "weights": {
-          "actorder": null,
-          "block_structure": null,
-          "dynamic": false,
-          "group_size": null,
-          "num_bits": 8,
-          "observer": "minmax",
-          "observer_kwargs": {},
-          "strategy": "channel",
-          "symmetric": true,
-          "type": "int"
-        }
-      }
-    },
-    "format": "int-quantized",
-    "global_compression_ratio": null,
-    "ignore": [
-      "lm_head"
-    ],
-    "kv_cache_scheme": null,
-    "quant_method": "compressed-tensors",
-    "quantization_status": "compressed",
-    "sparsity_config": {}
   },
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,

   "num_hidden_layers": 28,
   "num_key_value_heads": 8,
   "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": true,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
   },
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8c19ad8e113c43534366a5d690503837cddccad3c893944aa49f48a40b0a543
-size 752443408

 version https://git-lfs.github.com/spec/v1
+oid sha256:f5bcef2db084183a3646a9088fc365da380f36c4b117f69456e1542b41947ba1
+size 753150052