Instructions to use JoshuaWong/Nanonets-OCR-s-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JoshuaWong/Nanonets-OCR-s-AWQ with Transformers:

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

pipe = pipeline("image-text-to-text", model="JoshuaWong/Nanonets-OCR-s-AWQ")
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("JoshuaWong/Nanonets-OCR-s-AWQ")
model = AutoModelForMultimodalLM.from_pretrained("JoshuaWong/Nanonets-OCR-s-AWQ", 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 JoshuaWong/Nanonets-OCR-s-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JoshuaWong/Nanonets-OCR-s-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JoshuaWong/Nanonets-OCR-s-AWQ",
		"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/JoshuaWong/Nanonets-OCR-s-AWQ

SGLang

How to use JoshuaWong/Nanonets-OCR-s-AWQ 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 "JoshuaWong/Nanonets-OCR-s-AWQ" \
    --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": "JoshuaWong/Nanonets-OCR-s-AWQ",
		"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 "JoshuaWong/Nanonets-OCR-s-AWQ" \
        --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": "JoshuaWong/Nanonets-OCR-s-AWQ",
		"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 JoshuaWong/Nanonets-OCR-s-AWQ 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 JoshuaWong/Nanonets-OCR-s-AWQ 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 JoshuaWong/Nanonets-OCR-s-AWQ to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for JoshuaWong/Nanonets-OCR-s-AWQ to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="JoshuaWong/Nanonets-OCR-s-AWQ",
    max_seq_length=2048,
)

Docker Model Runner
How to use JoshuaWong/Nanonets-OCR-s-AWQ with Docker Model Runner:
```
docker model run hf.co/JoshuaWong/Nanonets-OCR-s-AWQ
```

JoshuaWong commited on Aug 13, 2025

Commit

2430e6e

verified ·

1 Parent(s): 851bc3d

Upload folder using huggingface_hub

Browse files

Files changed (6) hide show

.msc +0 -0
.mv +1 -1
config.json +7 -3
generation_config.json +1 -2
model.safetensors +1 -1
recipe.yaml +6 -0

.msc CHANGED Viewed

Binary files a/.msc and b/.msc differ

.mv CHANGED Viewed

	@@ -1 +1 @@
1	- Revision:master,CreatedAt:~~1754460938~~


1	+ Revision:master,CreatedAt:1755062608

config.json CHANGED Viewed

@@ -3,6 +3,7 @@
     "Qwen2_5_VLForConditionalGeneration"
   ],
   "attention_dropout": 0.0,
   "eos_token_id": 151645,
   "hidden_act": "silu",
   "hidden_size": 2048,
@@ -15,7 +16,6 @@
   "num_attention_heads": 16,
   "num_hidden_layers": 36,
   "num_key_value_heads": 2,
-  "pad_token_id": 151654,
   "quantization_config": {
     "config_groups": {
       "group_0": {
@@ -207,7 +207,12 @@
     ],
     "kv_cache_scheme": null,
     "quant_method": "compressed-tensors",
-    "quantization_status": "compressed"
   },
   "rms_norm_eps": 1e-06,
   "rope_scaling": {
@@ -263,7 +268,6 @@
   },
   "torch_dtype": "bfloat16",
   "transformers_version": "4.52.4",
-  "unsloth_fixed": true,
   "use_cache": true,
   "use_sliding_window": false,
   "video_token_id": 151656,

     "Qwen2_5_VLForConditionalGeneration"
   ],
   "attention_dropout": 0.0,
+  "bos_token_id": 151643,
   "eos_token_id": 151645,
   "hidden_act": "silu",
   "hidden_size": 2048,
   "num_attention_heads": 16,
   "num_hidden_layers": 36,
   "num_key_value_heads": 2,
   "quantization_config": {
     "config_groups": {
       "group_0": {
     ],
     "kv_cache_scheme": null,
     "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+          "bits": 4,
+      "group_size": 128,
+      "quant_method": "awq",
+      "version": "gemm",
+      "zero_point": true
   },
   "rms_norm_eps": 1e-06,
   "rope_scaling": {
   },
   "torch_dtype": "bfloat16",
   "transformers_version": "4.52.4",
   "use_cache": true,
   "use_sliding_window": false,
   "video_token_id": 151656,

generation_config.json CHANGED Viewed

@@ -5,8 +5,7 @@
     151645,
     151643
   ],
-  "max_length": 128000,
-  "pad_token_id": 151654,
   "repetition_penalty": 1.05,
   "temperature": 1e-06,
   "transformers_version": "4.52.4"

     151645,
     151643
   ],
+  "pad_token_id": 151643,
   "repetition_penalty": 1.05,
   "temperature": 1e-06,
   "transformers_version": "4.52.4"

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f65f3268ec0558c314408747fd87e1f9b51373c2743ed46deeb117c89793d97e
 size 4024151208

 version https://git-lfs.github.com/spec/v1
+oid sha256:1eaa4f6b735db4f9aad9d1bfab7f027476780c1162da9291e1e412d9d57b936f
 size 4024151208

recipe.yaml ADDED Viewed

	@@ -0,0 +1,6 @@

+default_stage:
+  default_modifiers:
+    AWQModifier:
+      targets: [Linear]
+      ignore: [lm_head, 're:visual.*', 're:model.visual.*']
+      scheme: W4A16_ASYM