jinaai
/

reader-lm-1.5b

@@ -1,61 +1,68 @@
 ---
-license: apache-2.0
-base_model: jinaai/qwen2-1.5b-reader
-tags:
-- sft
-- reader-lm
-- transformers
-- generated_from_trainer
-model-index:
-- name: qwen2-1.5b-final-v1
-  results: []
 ---
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-# qwen2-1.5b-final-v1
-This model is a fine-tuned version of [jinaai/qwen2-1.5b-reader](https://huggingface.co/jinaai/qwen2-1.5b-reader) on an unknown dataset.
-## Model description
-More information needed
-## Intended uses & limitations
-More information needed
-## Training and evaluation data
-More information needed
-## Training procedure
-### Training hyperparameters
-The following hyperparameters were used during training:
-- learning_rate: 3e-05
-- train_batch_size: 1
-- eval_batch_size: 8
-- seed: 42
-- distributed_type: multi-GPU
-- num_devices: 4
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 8
-- total_eval_batch_size: 32
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 1000
-- training_steps: 25000
-### Training results
-### Framework versions
-- Transformers 4.43.3
-- Pytorch 2.1.0+cu121-with-pypi-cudnn
-- Datasets 2.21.0
-- Tokenizers 0.19.0

 ---
+pipeline_tag: text-generation
+language:
+- multilingual
+inference: false
+license: cc-by-nc-4.0
+library_name: transformers
 ---
+<br><br>
+<p align="center">
+<img src="https://aeiljuispo.cloudimg.io/v7/https://cdn-uploads.huggingface.co/production/uploads/603763514de52ff951d89793/AFoybzd5lpBQXEBrQHuTt.png?w=200&h=200&f=face" alt="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." width="150px">
+</p>
+<p align="center">
+<b>Trained by <a href="https://jina.ai/"><b>Jina AI</b></a>.</b>
+</p>
+# 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](https://huggingface.co/jinaai/reader-lm-0.5b)       |
+| reader-lm-1.5b  |  256K             | [🤗 Hugging Face](https://huggingface.co/jinaai/reader-lm-1.5b)       |
+|                 |
+# Evaluation
+TBD
+# Quick Start
+To use this model, you need to install `transformers`:
+```bash
+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/qwen2-1.5b-reader"
+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]))
+```