Instructions to use Ba2han/augment-multi-qwen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ba2han/augment-multi-qwen with Transformers:

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

pipe = pipeline("image-text-to-text", model="Ba2han/augment-multi-qwen")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Ba2han/augment-multi-qwen")
model = AutoModelForMultimodalLM.from_pretrained("Ba2han/augment-multi-qwen", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Ba2han/augment-multi-qwen with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ba2han/augment-multi-qwen"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ba2han/augment-multi-qwen",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Ba2han/augment-multi-qwen

SGLang

How to use Ba2han/augment-multi-qwen 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 "Ba2han/augment-multi-qwen" \
    --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": "Ba2han/augment-multi-qwen",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "Ba2han/augment-multi-qwen" \
        --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": "Ba2han/augment-multi-qwen",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Unsloth Studio

How to use Ba2han/augment-multi-qwen with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Ba2han/augment-multi-qwen to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Ba2han/augment-multi-qwen to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Ba2han/augment-multi-qwen to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Ba2han/augment-multi-qwen",
    max_seq_length=2048,
)

Docker Model Runner
How to use Ba2han/augment-multi-qwen with Docker Model Runner:
```
docker model run hf.co/Ba2han/augment-multi-qwen
```

Ba2han commited on 24 days ago

Commit

899104a

verified ·

1 Parent(s): b137307

Training in progress, step 500

Browse files

Files changed (5) hide show

README.md +4 -4
chat_template.jinja +3 -3
config.json +8 -16
model.safetensors +2 -2
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -1,18 +1,18 @@
 ---
-base_model: unsloth/Qwen3.5-4B-Base
 library_name: transformers
 model_name: augment-multi-qwen
 tags:
 - generated_from_trainer
 - unsloth
 - sft
-- trl
 licence: license
 ---
 # Model Card for augment-multi-qwen
-This model is a fine-tuned version of [unsloth/Qwen3.5-4B-Base](https://huggingface.co/unsloth/Qwen3.5-4B-Base).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
@@ -28,7 +28,7 @@ print(output["generated_text"])
 ## Training procedure
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/batuhan409/huggingface/runs/d2zulkmg)
 This model was trained with SFT.

 ---
+base_model: unsloth/Qwen3.5-2B-Base
 library_name: transformers
 model_name: augment-multi-qwen
 tags:
 - generated_from_trainer
+- trl
 - unsloth
 - sft
 licence: license
 ---
 # Model Card for augment-multi-qwen
+This model is a fine-tuned version of [unsloth/Qwen3.5-2B-Base](https://huggingface.co/unsloth/Qwen3.5-2B-Base).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
 ## Training procedure
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/batuhan409/huggingface/runs/61dp66cf)
 This model was trained with SFT.

chat_template.jinja CHANGED Viewed

@@ -149,10 +149,10 @@
 {%- endfor %}
 {%- if add_generation_prompt %}
     {{- '<|im_start|>assistant\n' }}
-    {%- if enable_thinking is defined and enable_thinking is false %}
-        {{- '<think>\n\n</think>\n\n' }}
-    {%- else %}
         {{- '<think>\n' }}
     {%- endif %}
 {%- endif %}
 {#- Unsloth fixes - developer role, tool calling #}

 {%- endfor %}
 {%- if add_generation_prompt %}
     {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
         {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
     {%- endif %}
 {%- endif %}
 {#- Unsloth fixes - developer role, tool calling #}

config.json CHANGED Viewed

@@ -5,7 +5,7 @@
   "dtype": "bfloat16",
   "eos_token_id": 248044,
   "image_token_id": 248056,
-  "model_name": "unsloth/Qwen3.5-4B-Base",
   "model_type": "qwen3_5",
   "pad_token_id": 248055,
   "text_config": {
@@ -18,9 +18,9 @@
     "full_attention_interval": 4,
     "head_dim": 256,
     "hidden_act": "silu",
-    "hidden_size": 2560,
     "initializer_range": 0.02,
-    "intermediate_size": 9216,
     "layer_types": [
       "linear_attention",
       "linear_attention",
@@ -45,20 +45,12 @@
       "linear_attention",
       "linear_attention",
       "linear_attention",
-      "full_attention",
-      "linear_attention",
-      "linear_attention",
-      "linear_attention",
-      "full_attention",
-      "linear_attention",
-      "linear_attention",
-      "linear_attention",
       "full_attention"
     ],
     "linear_conv_kernel_dim": 4,
     "linear_key_head_dim": 128,
     "linear_num_key_heads": 16,
-    "linear_num_value_heads": 32,
     "linear_value_head_dim": 128,
     "mamba_ssm_dtype": "float32",
     "max_position_embeddings": 262144,
@@ -66,9 +58,9 @@
     "model_type": "qwen3_5_text",
     "mtp_num_hidden_layers": 1,
     "mtp_use_dedicated_embeddings": false,
-    "num_attention_heads": 16,
-    "num_hidden_layers": 32,
-    "num_key_value_heads": 4,
     "pad_token_id": null,
     "partial_rotary_factor": 0.25,
     "rms_norm_eps": 1e-06,
@@ -105,7 +97,7 @@
     "model_type": "qwen3_5",
     "num_heads": 16,
     "num_position_embeddings": 2304,
-    "out_hidden_size": 2560,
     "patch_size": 16,
     "spatial_merge_size": 2,
     "temporal_patch_size": 2

   "dtype": "bfloat16",
   "eos_token_id": 248044,
   "image_token_id": 248056,
+  "model_name": "unsloth/Qwen3.5-2B-Base",
   "model_type": "qwen3_5",
   "pad_token_id": 248055,
   "text_config": {
     "full_attention_interval": 4,
     "head_dim": 256,
     "hidden_act": "silu",
+    "hidden_size": 2048,
     "initializer_range": 0.02,
+    "intermediate_size": 6144,
     "layer_types": [
       "linear_attention",
       "linear_attention",
       "linear_attention",
       "linear_attention",
       "linear_attention",
       "full_attention"
     ],
     "linear_conv_kernel_dim": 4,
     "linear_key_head_dim": 128,
     "linear_num_key_heads": 16,
+    "linear_num_value_heads": 16,
     "linear_value_head_dim": 128,
     "mamba_ssm_dtype": "float32",
     "max_position_embeddings": 262144,
     "model_type": "qwen3_5_text",
     "mtp_num_hidden_layers": 1,
     "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 8,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 2,
     "pad_token_id": null,
     "partial_rotary_factor": 0.25,
     "rms_norm_eps": 1e-06,
     "model_type": "qwen3_5",
     "num_heads": 16,
     "num_position_embeddings": 2304,
+    "out_hidden_size": 2048,
     "patch_size": 16,
     "spatial_merge_size": 2,
     "temporal_patch_size": 2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad37fbb1ddb6fb65e603dbd401eaefe6d8ff342961fe7b4405241ef4283be759
-size 9079183800

 version https://git-lfs.github.com/spec/v1
+oid sha256:f9d7dc46d599cf286ba68d2e794f8c3e5ffd29ddd33efbe976203e0401d7ac4b
+size 4426983440

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ae3ccc52bc9f93528e8f46aae3537216dab67a557a313fa59046ba75eeb9185
 size 5713

 version https://git-lfs.github.com/spec/v1
+oid sha256:203650bea988f3f34ce73d678d87d9717e4df8feef71208ad0d37a3fcb6ae426
 size 5713