Instructions to use chancharikm/dpo_all_20251113_ep5_lr5e6_qwen3-vl-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chancharikm/dpo_all_20251113_ep5_lr5e6_qwen3-vl-8b 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, "chancharikm/dpo_all_20251113_ep5_lr5e6_qwen3-vl-8b")

Transformers

How to use chancharikm/dpo_all_20251113_ep5_lr5e6_qwen3-vl-8b with Transformers:

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

pipe = pipeline("text-generation", model="chancharikm/dpo_all_20251113_ep5_lr5e6_qwen3-vl-8b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("chancharikm/dpo_all_20251113_ep5_lr5e6_qwen3-vl-8b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use chancharikm/dpo_all_20251113_ep5_lr5e6_qwen3-vl-8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "chancharikm/dpo_all_20251113_ep5_lr5e6_qwen3-vl-8b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "chancharikm/dpo_all_20251113_ep5_lr5e6_qwen3-vl-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/chancharikm/dpo_all_20251113_ep5_lr5e6_qwen3-vl-8b

SGLang

How to use chancharikm/dpo_all_20251113_ep5_lr5e6_qwen3-vl-8b 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 "chancharikm/dpo_all_20251113_ep5_lr5e6_qwen3-vl-8b" \
    --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": "chancharikm/dpo_all_20251113_ep5_lr5e6_qwen3-vl-8b",
		"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 "chancharikm/dpo_all_20251113_ep5_lr5e6_qwen3-vl-8b" \
        --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": "chancharikm/dpo_all_20251113_ep5_lr5e6_qwen3-vl-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use chancharikm/dpo_all_20251113_ep5_lr5e6_qwen3-vl-8b with Docker Model Runner:
```
docker model run hf.co/chancharikm/dpo_all_20251113_ep5_lr5e6_qwen3-vl-8b
```

chancharikm commited on Nov 16, 2025

Commit

1006742

verified ·

1 Parent(s): 0a19c5c

Training in progress, step 39

Browse files

Files changed (3) hide show

adapter_model.safetensors +1 -1
tokenizer_config.json +1 -0
trainer_log.jsonl +20 -0

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba43ed1406b82701ad8960605d745b8c65f9455b8a646346f4f2eb559fcc3c88
 size 178105560

 version https://git-lfs.github.com/spec/v1
+oid sha256:5da2cc47f53d04e801165f0ac586543e0e2f8217546eef4478e1af5c53d1cca9
 size 178105560

tokenizer_config.json CHANGED Viewed

@@ -234,6 +234,7 @@
   "model_max_length": 262144,
   "pad_token": "<|endoftext|>",
   "padding_side": "right",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null

   "model_max_length": 262144,
   "pad_token": "<|endoftext|>",
   "padding_side": "right",
+  "processor_class": "Qwen3VLProcessor",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null

trainer_log.jsonl CHANGED Viewed

@@ -18,3 +18,23 @@
 {"current_steps": 18, "total_steps": 39, "loss": 0.6024, "accuracy": 0.76025390625, "lr": 6.965125158269619e-06, "epoch": 1.4081632653061225, "percentage": 46.15, "elapsed_time": "8:11:24", "remaining_time": "9:33:18"}
 {"current_steps": 19, "total_steps": 39, "loss": 0.5982, "accuracy": 0.74658203125, "lr": 6.545084971874738e-06, "epoch": 1.489795918367347, "percentage": 48.72, "elapsed_time": "8:41:05", "remaining_time": "9:08:30"}
 {"current_steps": 20, "total_steps": 39, "loss": 0.595, "accuracy": 0.76416015625, "lr": 6.112604669781572e-06, "epoch": 1.5714285714285714, "percentage": 51.28, "elapsed_time": "9:11:30", "remaining_time": "8:43:55"}

 {"current_steps": 18, "total_steps": 39, "loss": 0.6024, "accuracy": 0.76025390625, "lr": 6.965125158269619e-06, "epoch": 1.4081632653061225, "percentage": 46.15, "elapsed_time": "8:11:24", "remaining_time": "9:33:18"}
 {"current_steps": 19, "total_steps": 39, "loss": 0.5982, "accuracy": 0.74658203125, "lr": 6.545084971874738e-06, "epoch": 1.489795918367347, "percentage": 48.72, "elapsed_time": "8:41:05", "remaining_time": "9:08:30"}
 {"current_steps": 20, "total_steps": 39, "loss": 0.595, "accuracy": 0.76416015625, "lr": 6.112604669781572e-06, "epoch": 1.5714285714285714, "percentage": 51.28, "elapsed_time": "9:11:30", "remaining_time": "8:43:55"}
+{"current_steps": 21, "total_steps": 39, "loss": 0.5807, "accuracy": 0.77001953125, "lr": 5.671166329088278e-06, "epoch": 1.6530612244897958, "percentage": 53.85, "elapsed_time": "9:43:20", "remaining_time": "8:20:00"}
+{"current_steps": 22, "total_steps": 39, "loss": 0.573, "accuracy": 0.76904296875, "lr": 5.224324151752575e-06, "epoch": 1.7346938775510203, "percentage": 56.41, "elapsed_time": "10:14:02", "remaining_time": "7:54:29"}
+{"current_steps": 23, "total_steps": 39, "loss": 0.5658, "accuracy": 0.7763671875, "lr": 4.775675848247427e-06, "epoch": 1.816326530612245, "percentage": 58.97, "elapsed_time": "10:42:45", "remaining_time": "7:27:08"}
+{"current_steps": 24, "total_steps": 39, "loss": 0.5677, "accuracy": 0.76513671875, "lr": 4.3288336709117246e-06, "epoch": 1.8979591836734695, "percentage": 61.54, "elapsed_time": "11:11:29", "remaining_time": "6:59:41"}
+{"current_steps": 25, "total_steps": 39, "loss": 0.5621, "accuracy": 0.76171875, "lr": 3.887395330218429e-06, "epoch": 1.9795918367346939, "percentage": 64.1, "elapsed_time": "11:45:43", "remaining_time": "6:35:12"}
+{"current_steps": 26, "total_steps": 39, "loss": 0.5472, "accuracy": 0.775390625, "lr": 3.4549150281252635e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "11:54:58", "remaining_time": "5:57:29"}
+{"current_steps": 27, "total_steps": 39, "loss": 0.5549, "accuracy": 0.7685546875, "lr": 3.0348748417303826e-06, "epoch": 2.0816326530612246, "percentage": 69.23, "elapsed_time": "12:26:31", "remaining_time": "5:31:47"}
+{"current_steps": 28, "total_steps": 39, "loss": 0.5487, "accuracy": 0.765625, "lr": 2.6306566876350072e-06, "epoch": 2.163265306122449, "percentage": 71.79, "elapsed_time": "12:56:57", "remaining_time": "5:05:13"}
+{"current_steps": 29, "total_steps": 39, "loss": 0.5534, "accuracy": 0.76171875, "lr": 2.245515092739488e-06, "epoch": 2.2448979591836733, "percentage": 74.36, "elapsed_time": "13:25:45", "remaining_time": "4:37:50"}
+{"current_steps": 30, "total_steps": 39, "loss": 0.5486, "accuracy": 0.7568359375, "lr": 1.8825509907063328e-06, "epoch": 2.326530612244898, "percentage": 76.92, "elapsed_time": "13:53:57", "remaining_time": "4:10:11"}
+{"current_steps": 31, "total_steps": 39, "loss": 0.5394, "accuracy": 0.76904296875, "lr": 1.544686755065677e-06, "epoch": 2.4081632653061225, "percentage": 79.49, "elapsed_time": "14:19:56", "remaining_time": "3:41:55"}
+{"current_steps": 32, "total_steps": 39, "loss": 0.5419, "accuracy": 0.7587890625, "lr": 1.234642669981946e-06, "epoch": 2.489795918367347, "percentage": 82.05, "elapsed_time": "14:48:03", "remaining_time": "3:14:15"}
+{"current_steps": 33, "total_steps": 39, "loss": 0.543, "accuracy": 0.767578125, "lr": 9.549150281252633e-07, "epoch": 2.571428571428571, "percentage": 84.62, "elapsed_time": "15:17:15", "remaining_time": "2:46:46"}
+{"current_steps": 34, "total_steps": 39, "loss": 0.5405, "accuracy": 0.7626953125, "lr": 7.077560319906696e-07, "epoch": 2.6530612244897958, "percentage": 87.18, "elapsed_time": "15:50:39", "remaining_time": "2:19:48"}
+{"current_steps": 35, "total_steps": 39, "loss": 0.5321, "accuracy": 0.779296875, "lr": 4.951556604879049e-07, "epoch": 2.7346938775510203, "percentage": 89.74, "elapsed_time": "16:25:04", "remaining_time": "1:52:34"}
+{"current_steps": 36, "total_steps": 39, "loss": 0.5411, "accuracy": 0.76708984375, "lr": 3.18825646801314e-07, "epoch": 2.816326530612245, "percentage": 92.31, "elapsed_time": "16:56:27", "remaining_time": "1:24:42"}
+{"current_steps": 37, "total_steps": 39, "loss": 0.5361, "accuracy": 0.78076171875, "lr": 1.801856965207338e-07, "epoch": 2.8979591836734695, "percentage": 94.87, "elapsed_time": "17:25:08", "remaining_time": "0:56:29"}
+{"current_steps": 38, "total_steps": 39, "loss": 0.5391, "accuracy": 0.76416015625, "lr": 8.035205700685167e-08, "epoch": 2.979591836734694, "percentage": 97.44, "elapsed_time": "17:57:50", "remaining_time": "0:28:21"}
+{"current_steps": 39, "total_steps": 39, "loss": 0.5331, "accuracy": 0.798828125, "lr": 2.012853002380466e-08, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "18:05:55", "remaining_time": "0:00:00"}
+{"current_steps": 39, "total_steps": 39, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "18:05:56", "remaining_time": "0:00:00"}