初始化项目，由ModelHub XC社区提供模型

Model: numind/NuExtract-1.5-smol
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,172 @@
+---
+license: mit
+language:
+- multilingual
+tags:
+- nlp
+base_model: HuggingFaceTB/SmolLM2-1.7B
+new_version: numind/NuExtract3
+pipeline_tag: text-generation
+inference: true
+---
+
+# NuExtract-1.5-smol by NuMind 🔥
+
+NuExtract-1.5-smol is a fine-tuning of Hugging Face's [SmolLM2-1.7B](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B), intended for structured information extraction. It uses the same training data as [NuExtract-1.5](https://huggingface.co/numind/NuExtract-1.5) and supports multiple languages, while being less than half the size (1.7B vs 3.8B).
+
+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.
+
+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 also provide a tiny (0.5B) version which is based on Qwen2.5-0.5B: [NuExtract-tiny-v1.5](https://huggingface.co/numind/NuExtract-tiny-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="height: auto;">
+</p>
+
+Zero-shot performance (Multilingual):
+
+<p align="left">
+<img src="multilingual_bench.png" style="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-1.5-smol"
+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
+```

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "numind/NuExtract-1.5-smol",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 130000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 49152
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "pad_token_id": 0,
+  "transformers_version": "4.45.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19a928d7e27479c06c6fb6f2e9c4276a78874b94eeb16fa59b51b25a34decb6a
+size 3422777952

special_tokens_map.json

@@ -0,0 +1,43 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,169 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}