Instructions to use medimed/quantized_model_W8A8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use medimed/quantized_model_W8A8 with Transformers:

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

pipe = pipeline("text-generation", model="medimed/quantized_model_W8A8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("medimed/quantized_model_W8A8")
model = AutoModelForCausalLM.from_pretrained("medimed/quantized_model_W8A8")
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 medimed/quantized_model_W8A8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "medimed/quantized_model_W8A8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "medimed/quantized_model_W8A8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/medimed/quantized_model_W8A8

SGLang

How to use medimed/quantized_model_W8A8 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 "medimed/quantized_model_W8A8" \
    --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": "medimed/quantized_model_W8A8",
		"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 "medimed/quantized_model_W8A8" \
        --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": "medimed/quantized_model_W8A8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use medimed/quantized_model_W8A8 with Docker Model Runner:
```
docker model run hf.co/medimed/quantized_model_W8A8
```

medimed commited on Jun 3, 2025

Commit

e01a4f6

verified ·

1 Parent(s): ef1bcf9

Upload Qwen3ForCausalLM

Browse files

Files changed (3) hide show

config.json +3 -2
generation_config.json +2 -0
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -4,7 +4,6 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 151643,
   "eos_token_id": 151643,
   "head_dim": 128,
   "hidden_act": "silu",
@@ -17,7 +16,7 @@
   "num_attention_heads": 16,
   "num_hidden_layers": 28,
   "num_key_value_heads": 8,
-  "pad_token_id": 151643,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 1000000,
@@ -25,6 +24,8 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.52.3",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936

   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "eos_token_id": 151643,
   "head_dim": 128,
   "hidden_act": "silu",
   "num_attention_heads": 16,
   "num_hidden_layers": 28,
   "num_key_value_heads": 8,
+  "pad_token_id": 151654,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 1000000,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.52.3",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.5.8",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936

generation_config.json CHANGED Viewed

@@ -1,6 +1,8 @@
 {
   "bos_token_id": 151643,
   "eos_token_id": 151643,
   "max_new_tokens": 2048,
   "transformers_version": "4.52.3"
 }

 {
   "bos_token_id": 151643,
   "eos_token_id": 151643,
+  "max_length": 32768,
   "max_new_tokens": 2048,
+  "pad_token_id": 151654,
   "transformers_version": "4.52.3"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4209e36b926e7eaafd4088b089fd7bc03be7f734a97d84cc1f87b72084aa4171
 size 1192135096

 version https://git-lfs.github.com/spec/v1
+oid sha256:5b029b92cf10cf3e463e88008965acc598524d47d5e20672fbe1c8f9f4e7e098
 size 1192135096