Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,189 @@
+---
+license: mit
+language:
+- multilingual
+tags:
+- nlp
+base_model:
+- numind/NuExtract-1.5-tiny
+pipeline_tag: text-generation
+library_name: transformers.js
+---
+
+
+
+# NuExtract-1.5-tiny (ONNX)
+
+
+This is an ONNX version of [numind/NuExtract-1.5-tiny](https://huggingface.co/numind/NuExtract-1.5-tiny). It was automatically converted and uploaded using [this Hugging Face Space](https://huggingface.co/spaces/onnx-community/convert-to-onnx).
+
+
+## Usage with Transformers.js
+
+
+See the pipeline documentation for `text-generation`: https://huggingface.co/docs/transformers.js/api/pipelines#module_pipelines.TextGenerationPipeline
+
+
+---
+
+
+# NuExtract-tiny-v1.5 by NuMind 🔥
+
+NuExtract-tiny-v1.5 is a fine-tuning of [Qwen/Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B), trained on a private high-quality dataset for structured information extraction. It supports long documents and several languages (English, French, Spanish, German, Portuguese, and Italian).
+To use the model, provide an input text and a JSON template describing the information you need to extract.
+
+Note: This model is trained to prioritize pure extraction, so in most cases all text generated by the model is present as is in the original text.
+
+We also provide a 3.8B version which is based on Phi-3.5-mini-instruct: [NuExtract-v1.5](https://huggingface.co/numind/NuExtract-v1.5)
+
+Check out the [blog post](https://numind.ai/blog/nuextract-1-5---multilingual-infinite-context-still-small-and-better-than-gpt-4o).
+
+Try the 3.8B model here: [Playground](https://huggingface.co/spaces/numind/NuExtract-v1.5)
+
+⚠️ We recommend using NuExtract with a temperature at or very close to 0. Some inference frameworks, such as Ollama, use a default of 0.7 which is not well suited to pure extraction tasks.
+
+## Benchmark
+
+Zero-shot performance (English):
+
+<p align="left">
+<img src="english_bench.png" style="width: 600; height: auto;">
+</p>
+
+Few-shot fine-tuning:
+
+<p align="left">
+<img src="fewshot_bench.png" style="width: 750; height: auto;">
+</p>
+
+
+## Usage
+
+To use the model:
+
+```python
+import json
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+def predict_NuExtract(model, tokenizer, texts, template, batch_size=1, max_length=10_000, max_new_tokens=4_000):
+    template = json.dumps(json.loads(template), indent=4)
+    prompts = [f"""<|input|>\n### Template:\n{template}\n### Text:\n{text}\n\n<|output|>""" for text in texts]
+    
+    outputs = []
+    with torch.no_grad():
+        for i in range(0, len(prompts), batch_size):
+            batch_prompts = prompts[i:i+batch_size]
+            batch_encodings = tokenizer(batch_prompts, return_tensors="pt", truncation=True, padding=True, max_length=max_length).to(model.device)
+
+            pred_ids = model.generate(**batch_encodings, max_new_tokens=max_new_tokens)
+            outputs += tokenizer.batch_decode(pred_ids, skip_special_tokens=True)
+
+    return [output.split("<|output|>")[1] for output in outputs]
+
+model_name = "numind/NuExtract-tiny-v1.5"
+device = "cuda"
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, trust_remote_code=True).to(device).eval()
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+
+text = """We introduce Mistral 7B, a 7–billion-parameter language model engineered for
+superior performance and efficiency. Mistral 7B outperforms the best open 13B
+model (Llama 2) across all evaluated benchmarks, and the best released 34B
+model (Llama 1) in reasoning, mathematics, and code generation. Our model
+leverages grouped-query attention (GQA) for faster inference, coupled with sliding
+window attention (SWA) to effectively handle sequences of arbitrary length with a
+reduced inference cost. We also provide a model fine-tuned to follow instructions,
+Mistral 7B – Instruct, that surpasses Llama 2 13B – chat model both on human and
+automated benchmarks. Our models are released under the Apache 2.0 license.
+Code: <https://github.com/mistralai/mistral-src>
+Webpage: <https://mistral.ai/news/announcing-mistral-7b/>"""
+
+template = """{
+    "Model": {
+        "Name": "",
+        "Number of parameters": "",
+        "Number of max token": "",
+        "Architecture": []
+    },
+    "Usage": {
+        "Use case": [],
+        "Licence": ""
+    }
+}"""
+
+prediction = predict_NuExtract(model, tokenizer, [text], template)[0]
+print(prediction)
+
+```
+
+Sliding window prompting:
+
+```python
+import json
+
+MAX_INPUT_SIZE = 20_000
+MAX_NEW_TOKENS = 6000
+
+def clean_json_text(text):
+    text = text.strip()
+    text = text.replace("\#", "#").replace("\&", "&")
+    return text
+
+def predict_chunk(text, template, current, model, tokenizer):
+    current = clean_json_text(current)
+
+    input_llm =  f"<|input|>\n### Template:\n{template}\n### Current:\n{current}\n### Text:\n{text}\n\n<|output|>" + "{"
+    input_ids = tokenizer(input_llm, return_tensors="pt", truncation=True, max_length=MAX_INPUT_SIZE).to("cuda")
+    output = tokenizer.decode(model.generate(**input_ids, max_new_tokens=MAX_NEW_TOKENS)[0], skip_special_tokens=True)
+
+    return clean_json_text(output.split("<|output|>")[1])
+
+def split_document(document, window_size, overlap):
+    tokens = tokenizer.tokenize(document)
+    print(f"\tLength of document: {len(tokens)} tokens")
+
+    chunks = []
+    if len(tokens) > window_size:
+        for i in range(0, len(tokens), window_size-overlap):
+            print(f"\t{i} to {i + len(tokens[i:i + window_size])}")
+            chunk = tokenizer.convert_tokens_to_string(tokens[i:i + window_size])
+            chunks.append(chunk)
+
+            if i + len(tokens[i:i + window_size]) >= len(tokens):
+                break
+    else:
+        chunks.append(document)
+    print(f"\tSplit into {len(chunks)} chunks")
+
+    return chunks
+
+def handle_broken_output(pred, prev):
+    try:
+        if all([(v in ["", []]) for v in json.loads(pred).values()]):
+            # if empty json, return previous
+            pred = prev
+    except:
+        # if broken json, return previous
+        pred = prev
+
+    return pred
+
+def sliding_window_prediction(text, template, model, tokenizer, window_size=4000, overlap=128):
+    # split text into chunks of n tokens
+    tokens = tokenizer.tokenize(text)
+    chunks = split_document(text, window_size, overlap)
+
+    # iterate over text chunks
+    prev = template
+    for i, chunk in enumerate(chunks):
+        print(f"Processing chunk {i}...")
+        pred = predict_chunk(chunk, template, prev, model, tokenizer)
+
+        # handle broken output
+        pred = handle_broken_output(pred, prev)
+            
+        # iterate
+        prev = pred
+
+    return pred
+```

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "numind/NuExtract-1.5-tiny",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.49.0"
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4907385241b9dd262afb2be946862c7c936828fdf8136b8a51947b6f654af2c
+size 1976804169

onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d719c1fab248db16d4afc0b8b202f9252d45a6c03411f698bb937fa6d2830146
+size 746801380

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d93b69976f9efe39f9241106ca712f0c2b6fc08c21402df1ed8d417a8246dd04
+size 988749741

onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2449fa00c80bb3a5632763b166a02954f74f465b2052904d25057a65d393139
+size 495103963

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16bbf6fc5fad5e19ee08f4ed2698002575ba1260b1ae4e807041516de2f583a2
+size 769164196

onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f24ad7ac7e86e33a55b25ab48d62ac3a11ef5b8773e104d4fc7e6f7c3022fd8
+size 474398824

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2449fa00c80bb3a5632763b166a02954f74f465b2052904d25057a65d393139
+size 495103963

onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af61c25e6c6e2f6784d71999d743d2728c4d435c506c535cf0bc3197b6b3b8b8
+size 495104043

quantize_config.json

@@ -0,0 +1,18 @@
+{
+    "modes": [
+        "fp16",
+        "q8",
+        "int8",
+        "uint8",
+        "q4",
+        "q4f16",
+        "bnb4"
+    ],
+    "per_channel": false,
+    "reduce_range": false,
+    "block_size": null,
+    "is_symmetric": true,
+    "accuracy_level": null,
+    "quant_type": 1,
+    "op_block_list": null
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15706fc8309d8e7119027503bd135bbb216b283f2d6d2e6efeaf5871d88f650e
+size 11421995

tokenizer_config.json

@@ -0,0 +1,213 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "max_length": 2500,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": null
+}