Instructions to use jinaai/reader-lm-1.5b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jinaai/reader-lm-1.5b with Transformers:

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

pipe = pipeline("text-generation", model="jinaai/reader-lm-1.5b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jinaai/reader-lm-1.5b")
model = AutoModelForCausalLM.from_pretrained("jinaai/reader-lm-1.5b")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use jinaai/reader-lm-1.5b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jinaai/reader-lm-1.5b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jinaai/reader-lm-1.5b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jinaai/reader-lm-1.5b

SGLang

How to use jinaai/reader-lm-1.5b 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 "jinaai/reader-lm-1.5b" \
    --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": "jinaai/reader-lm-1.5b",
		"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 "jinaai/reader-lm-1.5b" \
        --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": "jinaai/reader-lm-1.5b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jinaai/reader-lm-1.5b with Docker Model Runner:
```
docker model run hf.co/jinaai/reader-lm-1.5b
```

why?

by Youcef - opened Sep 11, 2024

Discussion

Youcef

Sep 11, 2024

how is this any better than a rules based engine like https://github.com/mixmark-io/turndown?

why use something that's a few orders of magnitude slower like reader-lm?

jackbravo

Sep 12, 2024

They also used turndow, and answer precisely that question in their blog post: https://jina.ai/news/reader-lm-small-language-models-for-cleaning-and-converting-html-to-markdown/

jackbravo

Sep 12, 2024

At first glance, using LLMs for data cleaning might seem excessive due to their low cost-efficiency and slower speeds. But what if we're considering a small language model (SLM) — one with fewer than 1 billion parameters that can run efficiently on the edge? That sounds much more appealing, right? But is this truly feasible or just wishful thinking?

maxiw

Sep 12, 2024

You can compare LM vs rule based approach here: https://huggingface.co/spaces/maxiw/HTML-to-Markdown

anotherjesse

Sep 12, 2024

I wonder if "hallucinations" being a failure mode for LLMs could mean drastically different edge cases for LLM based vs rules based in practice.

(I say this as I tried using this in ollama q4 1.5b model - and getting hallucinated output for pasted html - I've not tried the API version - perhaps chat mangled in the input/template)

davidmoore-io

Sep 18, 2024

It has a ton of use cases.

Existing approaches are fragile and a pain to maintain. If this works, being able to deploy a small model inside a container and run it basically anywhere, using a few lines of code.. that's much more attractive in lots data processing pipelines, especially if you don't massively care about speed.

Also, best of luck handling multiple languages The Old Way. It's a nightmare wrapped in pain.

I'm about to try it... will be interesting to see if it works. 🙏

JoPhi

Sep 20, 2024

(I say this as I tried using this in ollama q4 1.5b model - and getting hallucinated output for pasted html - I've not tried the API version - perhaps chat mangled in the input/template)

temperature = 0 ?

Youcef changed discussion status to closed Sep 21, 2024

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment