Commit
•
4575b79
1
Parent(s):
f3290f3
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
language:
|
| 6 |
+
- multilingual
|
| 7 |
+
inference: false
|
| 8 |
+
license: cc-by-nc-4.0
|
| 9 |
+
library_name: transformers
|
| 10 |
+
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
[](https://hf.co/QuantFactory)
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
# QuantFactory/reader-lm-0.5b-GGUF
|
| 17 |
+
This is quantized version of [jinaai/reader-lm-0.5b](https://huggingface.co/jinaai/reader-lm-0.5b) created using llama.cpp
|
| 18 |
+
|
| 19 |
+
# Original Model Card
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
<br><br>
|
| 23 |
+
|
| 24 |
+
<p align="center">
|
| 25 |
+
<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">
|
| 26 |
+
</p>
|
| 27 |
+
|
| 28 |
+
<p align="center">
|
| 29 |
+
<b>Trained by <a href="https://jina.ai/"><b>Jina AI</b></a>.</b>
|
| 30 |
+
</p>
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
# Intro
|
| 34 |
+
|
| 35 |
+
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.
|
| 36 |
+
|
| 37 |
+
# Models
|
| 38 |
+
|
| 39 |
+
| Name | Context Length | Download |
|
| 40 |
+
|-----------------|-------------------|-----------------------------------------------------------------------|
|
| 41 |
+
| reader-lm-0.5b | 256K | [🤗 Hugging Face](https://huggingface.co/jinaai/reader-lm-0.5b) |
|
| 42 |
+
| reader-lm-1.5b | 256K | [🤗 Hugging Face](https://huggingface.co/jinaai/reader-lm-1.5b) |
|
| 43 |
+
| |
|
| 44 |
+
|
| 45 |
+
# Evaluation
|
| 46 |
+
|
| 47 |
+
TBD
|
| 48 |
+
|
| 49 |
+
# Quick Start
|
| 50 |
+
|
| 51 |
+
To use this model, you need to install `transformers`:
|
| 52 |
+
|
| 53 |
+
```bash
|
| 54 |
+
pip install transformers<=4.43.4
|
| 55 |
+
```
|
| 56 |
+
|
| 57 |
+
Then, you can use the model as follows:
|
| 58 |
+
|
| 59 |
+
```python
|
| 60 |
+
# pip install transformers
|
| 61 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 62 |
+
checkpoint = "jinaai/reader-lm-0.5b"
|
| 63 |
+
|
| 64 |
+
device = "cuda" # for GPU usage or "cpu" for CPU usage
|
| 65 |
+
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
|
| 66 |
+
model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)
|
| 67 |
+
|
| 68 |
+
# example html content
|
| 69 |
+
html_content = "<html><body><h1>Hello, world!</h1></body></html>"
|
| 70 |
+
|
| 71 |
+
messages = [{"role": "user", "content": html_content}]
|
| 72 |
+
input_text=tokenizer.apply_chat_template(messages, tokenize=False)
|
| 73 |
+
|
| 74 |
+
print(input_text)
|
| 75 |
+
|
| 76 |
+
inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
|
| 77 |
+
outputs = model.generate(inputs, max_new_tokens=1024, temperature=0, do_sample=False, repetition_penalty=1.08)
|
| 78 |
+
|
| 79 |
+
print(tokenizer.decode(outputs[0]))
|
| 80 |
+
```
|
| 81 |
+
|