Upload 8 files

Browse files

Files changed (8) hide show

README.md +78 -0
added_tokens.json +5 -0
config.json +28 -0
generation_config.json +17 -0
merges.txt +0 -0
special_tokens_map.json +20 -0
tokenizer_config.json +43 -0
vocab.json +0 -0

README.md ADDED Viewed

	@@ -0,0 +1,78 @@

+---
+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>
+[Blog](https://jina.ai/news/reader-lm-small-language-models-for-cleaning-and-converting-html-to-markdown) | [Colab](https://colab.research.google.com/drive/1wXWyj5hOxEHY6WeHbOwEzYAC0WB1I5uA)
+# 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)       |
+|                 |
+# Get Started
+## On Google Colab
+The easiest way to experience reader-lm is by running [our Colab notebook](https://colab.research.google.com/drive/1wXWyj5hOxEHY6WeHbOwEzYAC0WB1I5uA),
+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`:
+```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/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](https://aws.amazon.com/marketplace/pp/prodview-nli7b6dueo424?sr=0-1&ref_=beagle&applicationId=AWSMPContessa)
+[AWS 1.5b](https://aws.amazon.com/marketplace/pp/prodview-ms27ixcwq3wjk?sr=0-2&ref_=beagle&applicationId=AWSMPContessa)
+[Azure 0.5b](https://azuremarketplace.microsoft.com/en-us/marketplace/apps/jinaai.reader-lm-500m)
+[Azure 1.5b](https://azuremarketplace.microsoft.com/en-us/marketplace/apps/jinaai.reader-lm-1500m)

added_tokens.json ADDED Viewed

	@@ -0,0 +1,5 @@

+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json ADDED Viewed

	@@ -0,0 +1,28 @@

+{
+  "_name_or_path": "jinaai/qwen2-1.5b-reader",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 256000,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 2000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,17 @@

+{
+  "attn_implementation": "flash_attention_2",
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "rope_theta": 2000000,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.43.3",
+  "use_cache": false
+}

merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,20 @@

+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,43 @@

+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|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|>",
+  "errors": "replace",
+  "model_max_length": 256000,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff