You can deploy this model and start earning money today!

RichardErkhov/
jinaai_-_reader-lm-1.5b-gguf

Name: jinaai_-_reader-lm-1.5b-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

reader-lm-1.5b - GGUF

Model creator: https://huggingface.co/jinaai/
Original model: https://huggingface.co/jinaai/reader-lm-1.5b/

Name	Quant method	Size
reader-lm-1.5b.Q2_K.gguf	Q2_K	0.63GB
reader-lm-1.5b.IQ3_XS.gguf	IQ3_XS	0.68GB
reader-lm-1.5b.IQ3_S.gguf	IQ3_S	0.71GB
reader-lm-1.5b.Q3_K_S.gguf	Q3_K_S	0.71GB
reader-lm-1.5b.IQ3_M.gguf	IQ3_M	0.72GB
reader-lm-1.5b.Q3_K.gguf	Q3_K	0.77GB
reader-lm-1.5b.Q3_K_M.gguf	Q3_K_M	0.77GB
reader-lm-1.5b.Q3_K_L.gguf	Q3_K_L	0.82GB
reader-lm-1.5b.IQ4_XS.gguf	IQ4_XS	0.84GB
reader-lm-1.5b.Q4_0.gguf	Q4_0	0.87GB
reader-lm-1.5b.IQ4_NL.gguf	IQ4_NL	0.88GB
reader-lm-1.5b.Q4_K_S.gguf	Q4_K_S	0.88GB
reader-lm-1.5b.Q4_K.gguf	Q4_K	0.92GB
reader-lm-1.5b.Q4_K_M.gguf	Q4_K_M	0.92GB
reader-lm-1.5b.Q4_1.gguf	Q4_1	0.95GB
reader-lm-1.5b.Q5_0.gguf	Q5_0	1.02GB
reader-lm-1.5b.Q5_K_S.gguf	Q5_K_S	1.02GB
reader-lm-1.5b.Q5_K.gguf	Q5_K	1.05GB
reader-lm-1.5b.Q5_K_M.gguf	Q5_K_M	1.05GB
reader-lm-1.5b.Q5_1.gguf	Q5_1	1.1GB
reader-lm-1.5b.Q6_K.gguf	Q6_K	1.19GB
reader-lm-1.5b.Q8_0.gguf	Q8_0	1.53GB

Original model description:

pipeline_tag: text-generation language:

multilingual inference: false license: cc-by-nc-4.0 library_name: transformers

Finetuner logo: Finetuner helps you to create experiments in order to improve embeddings on search tasks. It accompanies you to deliver the last mile of performance-tuning for neural search applications.

Trained by Jina AI.

Blog | Colab

Intro

Jina Reader-LM is a series of models that convert HTML content to Markdown content, which is useful for content conversion tasks. The model is trained on a curated collection of HTML content and its corresponding Markdown content.

Models

Name	Context Length	Download
reader-lm-0.5b	256K	🤗 Hugging Face
reader-lm-1.5b	256K	🤗 Hugging Face

Get Started

On Google Colab

The easiest way to experience reader-lm is by running our Colab notebook, where we demonstrate how to use reader-lm-1.5b to convert the HackerNews website into markdown. The notebook is optimized to run smoothly on Google Colab’s free T4 GPU tier. You can also load reader-lm-0.5b or change the URL to any website and explore the output. Note that the input (i.e., the prompt) to the model is the raw HTML—no prefix instruction is required.

Local

To use this model, you need to install transformers:

pip install transformers<=4.43.4

Then, you can use the model as follows:

python

# pip install transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
checkpoint = "jinaai/reader-lm-1.5b"

device = "cuda" # for GPU usage or "cpu" for CPU usage
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)

# example html content
html_content = "<html><body><h1>Hello, world!</h1></body></html>"

messages = [{"role": "user", "content": html_content}]
input_text=tokenizer.apply_chat_template(messages, tokenize=False)

print(input_text)

inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
outputs = model.generate(inputs, max_new_tokens=1024, temperature=0, do_sample=False, repetition_penalty=1.08)

print(tokenizer.decode(outputs[0]))

AWS Sagemaker & Azure Marketplace

AWS 0.5b AWS 1.5b Azure 0.5b Azure 1.5b

RichardErkhov/jinaai_-_reader-lm-1.5b-gguf