Instructions to use MWeste/quantized_MCQA_8_bit_sub2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MWeste/quantized_MCQA_8_bit_sub2 with Transformers:

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

pipe = pipeline("text-generation", model="MWeste/quantized_MCQA_8_bit_sub2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MWeste/quantized_MCQA_8_bit_sub2")
model = AutoModelForCausalLM.from_pretrained("MWeste/quantized_MCQA_8_bit_sub2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MWeste/quantized_MCQA_8_bit_sub2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MWeste/quantized_MCQA_8_bit_sub2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MWeste/quantized_MCQA_8_bit_sub2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MWeste/quantized_MCQA_8_bit_sub2

SGLang

How to use MWeste/quantized_MCQA_8_bit_sub2 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 "MWeste/quantized_MCQA_8_bit_sub2" \
    --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": "MWeste/quantized_MCQA_8_bit_sub2",
		"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 "MWeste/quantized_MCQA_8_bit_sub2" \
        --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": "MWeste/quantized_MCQA_8_bit_sub2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MWeste/quantized_MCQA_8_bit_sub2 with Docker Model Runner:
```
docker model run hf.co/MWeste/quantized_MCQA_8_bit_sub2
```

MWeste commited on Jun 10, 2025

Commit

0c2b83d

verified ·

1 Parent(s): 0deac5d

Upload Qwen3ForCausalLM

Browse files

Files changed (2) hide show

config.json +7 -7
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -18,18 +18,18 @@
   "num_key_value_heads": 8,
   "pad_token_id": 151654,
   "quantization_config": {
-    "_load_in_4bit": true,
-    "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_storage": "uint8",
-    "bnb_4bit_quant_type": "nf4",
-    "bnb_4bit_use_double_quant": true,
     "llm_int8_enable_fp32_cpu_offload": false,
     "llm_int8_has_fp16_weight": false,
     "llm_int8_skip_modules": null,
     "llm_int8_threshold": 6.0,
-    "load_in_4bit": true,
-    "load_in_8bit": false,
     "quant_method": "bitsandbytes"
   },
   "rms_norm_eps": 1e-06,

   "num_key_value_heads": 8,
   "pad_token_id": 151654,
   "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": false,
     "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,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b92f5914bbffb90fde667b22be6f85cb92902ee46bfab69bf656793f5c246de
-size 538883105

 version https://git-lfs.github.com/spec/v1
+oid sha256:530b76ca39eca8f8eb7d22195c3b397f1af8a5ebbe3bcccbb93e02660c224da3
+size 753150052