Instructions to use trollek/SmolImagePromptHelper-135M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trollek/SmolImagePromptHelper-135M with Transformers:

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

pipe = pipeline("text-generation", model="trollek/SmolImagePromptHelper-135M")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("trollek/SmolImagePromptHelper-135M")
model = AutoModelForCausalLM.from_pretrained("trollek/SmolImagePromptHelper-135M")
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 trollek/SmolImagePromptHelper-135M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "trollek/SmolImagePromptHelper-135M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trollek/SmolImagePromptHelper-135M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/trollek/SmolImagePromptHelper-135M

SGLang

How to use trollek/SmolImagePromptHelper-135M 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 "trollek/SmolImagePromptHelper-135M" \
    --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": "trollek/SmolImagePromptHelper-135M",
		"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 "trollek/SmolImagePromptHelper-135M" \
        --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": "trollek/SmolImagePromptHelper-135M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use trollek/SmolImagePromptHelper-135M with Docker Model Runner:
```
docker model run hf.co/trollek/SmolImagePromptHelper-135M
```

trollek commited on Apr 4, 2025

Commit

c19e1e3

verified ·

1 Parent(s): 27ccfad

Upload 8 files

Browse files

Files changed (3) hide show

config.json +2 -2
model.safetensors +2 -2
tokenizer_config.json +2 -2

config.json CHANGED Viewed

@@ -24,8 +24,8 @@
   "rope_scaling": null,
   "rope_theta": 100000,
   "tie_word_embeddings": true,
-  "torch_dtype": "float32",
   "transformers_version": "4.50.0",
-  "use_cache": false,
   "vocab_size": 49152
 }

   "rope_scaling": null,
   "rope_theta": 100000,
   "tie_word_embeddings": true,
+  "torch_dtype": "float16",
   "transformers_version": "4.50.0",
+  "use_cache": true,
   "vocab_size": 49152
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:483e6ff13080f53d44183411b34193fe6269ceb0eb44b32473ba9ddf93d2b3a9
-size 538090408

 version https://git-lfs.github.com/spec/v1
+oid sha256:970dcb377ce12f0073e05f00f01dc40b211317e8a03489527617fde332f6420a
+size 269060280

tokenizer_config.json CHANGED Viewed

@@ -158,13 +158,13 @@
     "<empty_output>"
   ],
   "bos_token": "<|im_start|>",
-  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>\n' }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "extra_special_tokens": {},
   "model_max_length": 8192,
   "pad_token": "<|im_end|>",
-  "padding_side": "right",
   "split_special_tokens": false,
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>",

     "<empty_output>"
   ],
   "bos_token": "<|im_start|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "extra_special_tokens": {},
   "model_max_length": 8192,
   "pad_token": "<|im_end|>",
+  "padding_side": "left",
   "split_special_tokens": false,
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>",