Instructions to use quin210/Qwen3-VL-8B-KD-MMMU-Pro-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use quin210/Qwen3-VL-8B-KD-MMMU-Pro-LoRA with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-VL-8B-Instruct")
model = PeftModel.from_pretrained(base_model, "quin210/Qwen3-VL-8B-KD-MMMU-Pro-LoRA")

Transformers

How to use quin210/Qwen3-VL-8B-KD-MMMU-Pro-LoRA with Transformers:

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

pipe = pipeline("text-generation", model="quin210/Qwen3-VL-8B-KD-MMMU-Pro-LoRA")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("quin210/Qwen3-VL-8B-KD-MMMU-Pro-LoRA", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use quin210/Qwen3-VL-8B-KD-MMMU-Pro-LoRA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "quin210/Qwen3-VL-8B-KD-MMMU-Pro-LoRA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "quin210/Qwen3-VL-8B-KD-MMMU-Pro-LoRA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/quin210/Qwen3-VL-8B-KD-MMMU-Pro-LoRA

SGLang

How to use quin210/Qwen3-VL-8B-KD-MMMU-Pro-LoRA 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 "quin210/Qwen3-VL-8B-KD-MMMU-Pro-LoRA" \
    --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": "quin210/Qwen3-VL-8B-KD-MMMU-Pro-LoRA",
		"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 "quin210/Qwen3-VL-8B-KD-MMMU-Pro-LoRA" \
        --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": "quin210/Qwen3-VL-8B-KD-MMMU-Pro-LoRA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use quin210/Qwen3-VL-8B-KD-MMMU-Pro-LoRA with Docker Model Runner:
```
docker model run hf.co/quin210/Qwen3-VL-8B-KD-MMMU-Pro-LoRA
```

quin210 commited on Mar 10

Commit

3a91cdb

verified ·

1 Parent(s): 0210b41

KD checkpoint step=27500, ep=0, loss=0.1513

Browse files

Files changed (5) hide show

README.md +12 -4
adapter_config.json +4 -4
adapter_model.safetensors +1 -1
processor_config.json +2 -0
training_state.json +1 -0

README.md CHANGED Viewed

@@ -1,6 +1,11 @@
 ---
-library_name: transformers
-tags: []
 ---
 # Model Card for Model ID
@@ -15,7 +20,7 @@ tags: []
 <!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
 - **Developed by:** [More Information Needed]
 - **Funded by [optional]:** [More Information Needed]
@@ -196,4 +201,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 ## Model Card Contact
-[More Information Needed]

 ---
+base_model: Qwen/Qwen3-VL-8B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-VL-8B-Instruct
+- lora
+- transformers
 ---
 # Model Card for Model ID
 <!-- Provide a longer summary of what this model is. -->
 - **Developed by:** [More Information Needed]
 - **Funded by [optional]:** [More Information Needed]
 ## Model Card Contact
+[More Information Needed]
+### Framework versions
+- PEFT 0.18.1

adapter_config.json CHANGED Viewed

@@ -29,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "up_proj",
-    "q_proj",
     "o_proj",
     "k_proj",
-    "v_proj",
-    "down_proj",
-    "gate_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
+    "gate_proj",
     "up_proj",
     "o_proj",
     "k_proj",
+    "q_proj",
+    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adec210700593786f3992640c3bc44a05fde8558b63f14e4b60caff00d63e303
 size 174663096

 version https://git-lfs.github.com/spec/v1
+oid sha256:7d71e544d7e62dd04a5b42be5d6025e809dd418be518be8e64d9062d099fb131
 size 174663096

processor_config.json CHANGED Viewed

@@ -16,7 +16,9 @@
       0.5,
       0.5
     ],
     "merge_size": 2,
     "patch_size": 16,
     "resample": 3,
     "rescale_factor": 0.00392156862745098,

       0.5,
       0.5
     ],
+    "max_pixels": 401408,
     "merge_size": 2,
+    "min_pixels": 3136,
     "patch_size": 16,
     "resample": 3,
     "rescale_factor": 0.00392156862745098,

training_state.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"step": 27500, "ep": 0, "loss": 0.15126445889472961}