commit bc389a97f2218c9da2f7359366e03f0f6436b58c Author: ModelHub XC Date: Fri Jul 17 03:30:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: ratulsur/multi-format-finance-parser Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/Dockerfile b/Dockerfile new file mode 100644 index 0000000..421eb55 --- /dev/null +++ b/Dockerfile @@ -0,0 +1,22 @@ +FROM python:3.11-slim + +ENV PYTHONDONTWRITEBYTECODE=1 \ + PYTHONUNBUFFERED=1 + +RUN apt-get update && apt-get install -y --no-install-recommends \ + curl \ + && rm -rf /var/lib/apt/lists/* + +WORKDIR /app + +COPY requirements.txt . +RUN pip install --no-cache-dir -r requirements.txt + +COPY app.py . + +EXPOSE 7860 + +HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \ + CMD curl -f http://localhost:7860/ || exit 1 + +CMD ["python", "app.py"] diff --git a/README.md b/README.md new file mode 100644 index 0000000..9328251 --- /dev/null +++ b/README.md @@ -0,0 +1,306 @@ +--- +license: apache-2.0 +language: +- en +base_model: Qwen/Qwen2.5-7B-Instruct +pipeline_tag: text-generation +tags: +- finance +- document-parsing +- qlora +- qwen2.5 +- invoice +- sap +- structured-extraction +- json +--- + +# 🏦 Multi-Format Finance Document Parser + +A production-grade financial document parser fine-tuned on **Qwen2.5-7B-Instruct** using **QLoRA (4-bit NF4 quantization)**. Given raw text from any financial document, it outputs structured JSON — ready for downstream processing, ERP integration, or analytics pipelines. + +--- + +## 🚀 Live Demo + +👉 [Try it on HuggingFace Spaces](https://huggingface.co/spaces/ratulsur/finance-parser-demo) + +--- + +## 📄 Supported Document Types + +| Format | Examples | +|---|---| +| **Invoice** | Vendor invoices, GST bills, service bills | +| **SAP Report** | ALV exports, FI vendor payment reports | +| **Income Statement** | P&L statements, quarterly earnings | +| **Balance Sheet** | Assets, liabilities, equity statements | +| **Bank Statement** | Transaction records, account summaries | +| **Purchase Order** | PO documents, procurement records | +| **SQL Result** | Query outputs from finance databases | +| **CSV / Excel** | Tabular finance data | + +--- + +## 🧠 Model Details + +| Property | Value | +|---|---| +| **Base model** | Qwen/Qwen2.5-7B-Instruct | +| **Model size** | 8B parameters | +| **Fine-tuning method** | QLoRA (PEFT) | +| **Quantization** | 4-bit NF4 + double quantization | +| **Compute dtype** | bfloat16 | +| **LoRA rank** | r=8, alpha=16 | +| **Max sequence length** | 512 tokens | +| **Training hardware** | L40S 48GB GPU (Lightning AI) | +| **Training time** | ~1 hour | +| **License** | Apache 2.0 | + +--- + +## 📊 Training Data + +| Dataset | Samples | Type | +|---|---|---| +| [CORD-v2](https://huggingface.co/datasets/naver-clova-ix/cord-v2) | 454 | Real receipt images + structured JSON | +| Synthetic invoices | 300 | Generated with realistic Indian/global vendors | +| Synthetic SAP reports | 100 | ALV-style pipe-delimited exports | +| Synthetic income statements | 100 | P&L with revenue, COGS, EBIT, net income | +| **Total** | **954** | Train: 812 · Eval: 95 · Test: 47 | + +--- + +## ⚙️ Quantization Techniques + +| Technique | Purpose | +|---|---| +| **NF4 4-bit quantization** | Stores weights in 4-bit NormalFloat format — ~4x model size reduction | +| **Double quantization** | Quantizes the quantization constants — additional ~0.4 bits/param saving | +| **bfloat16 compute** | Full precision operations, 4-bit storage | +| **LoRA adapters (r=8)** | Only 0.5% of parameters trained — 99.5% frozen | +| **Paged AdamW 8-bit** | Optimizer state memory reduction | +| **Gradient checkpointing** | ~40% activation memory reduction | + +--- + +## 📤 Output Schema + +```json +{ + "document_type": "invoice|balance_sheet|income_stmt|sap_report|sql_result|bank_statement|purchase_order", + "vendor": "string or null", + "client": "string or null", + "date": "YYYY-MM-DD or null", + "due_date": "YYYY-MM-DD or null", + "document_id": "string or null", + "currency": "USD|EUR|INR|GBP|...", + "subtotal": "float or null", + "tax_amount": "float or null", + "tax_rate_pct": "float or null", + "total_amount": "float or null", + "line_items": [ + { + "description": "string", + "quantity": "float or null", + "unit_price": "float or null", + "amount": "float" + } + ], + "payment_terms": "string or null", + "notes": "string or null", + "metadata": {} +} +``` + +--- + +## 💻 Usage + +### Via HuggingFace Inference API + +```python +import requests +import json +import re + +API_URL = "https://api-inference.huggingface.co/models/ratulsur/multi-format-finance-parser" +HF_TOKEN = "hf_xxxxxxxxxxxx" + +SYSTEM_PROMPT = """You are a production financial document parser. +Given raw text from any financial document, output ONLY a single valid JSON object. +Schema: {document_type, vendor, client, date (YYYY-MM-DD), due_date, document_id, +currency, subtotal, tax_amount, tax_rate_pct, total_amount, +line_items:[{description,quantity,unit_price,amount}], payment_terms, notes, metadata}. +All monetary values must be floats. Unknown fields → null. No explanation.""" + +def parse_document(text: str) -> dict: + prompt = ( + f"<|im_start|>system\n{SYSTEM_PROMPT}<|im_end|>\n" + f"<|im_start|>user\nParse this financial document:\n\n{text}<|im_end|>\n" + f"<|im_start|>assistant\n" + ) + headers = {"Authorization": f"Bearer {HF_TOKEN}"} + payload = { + "inputs": prompt, + "parameters": { + "max_new_tokens": 512, + "temperature": 0.05, + "return_full_text": False, + "do_sample": False, + } + } + resp = requests.post(API_URL, headers=headers, json=payload, timeout=120) + raw = resp.json()[0]["generated_text"].strip() + raw = re.sub(r"```json\s*|```\s*", "", raw).strip() + return json.loads(raw) + +# Example +invoice = """ +INVOICE +Vendor: Tata Consultancy Services Ltd. +Invoice No: TCS-2024-8821 +Date: 2024-11-15 +Service: Cloud Infrastructure Management INR 42,500.00 +GST @ 18%: INR 7,650.00 +TOTAL DUE: INR 50,150.00 +Payment Terms: Net 30 +""" + +result = parse_document(invoice) +print(json.dumps(result, indent=2)) +``` + +### Expected output + +```json +{ + "document_type": "invoice", + "vendor": "Tata Consultancy Services Ltd.", + "client": null, + "date": "2024-11-15", + "due_date": null, + "document_id": "TCS-2024-8821", + "currency": "INR", + "subtotal": 42500.0, + "tax_amount": 7650.0, + "tax_rate_pct": 18.0, + "total_amount": 50150.0, + "line_items": [ + { + "description": "Cloud Infrastructure Management", + "quantity": 1, + "unit_price": 42500.0, + "amount": 42500.0 + } + ], + "payment_terms": "Net 30", + "notes": null, + "metadata": {} +} +``` + +### Load locally with transformers + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig +import torch + +bnb_config = BitsAndBytesConfig( + load_in_4bit=True, + bnb_4bit_quant_type="nf4", + bnb_4bit_use_double_quant=True, + bnb_4bit_compute_dtype=torch.bfloat16, +) + +model = AutoModelForCausalLM.from_pretrained( + "ratulsur/multi-format-finance-parser", + quantization_config=bnb_config, + device_map="auto", + trust_remote_code=True, +) +tokenizer = AutoTokenizer.from_pretrained( + "ratulsur/multi-format-finance-parser", + trust_remote_code=True, +) +``` + +--- + +## 🏗️ Training Setup + +```python +# QLoRA config +bnb_config = BitsAndBytesConfig( + load_in_4bit=True, + bnb_4bit_quant_type="nf4", + bnb_4bit_use_double_quant=True, + bnb_4bit_compute_dtype=torch.bfloat16, +) + +lora_config = LoraConfig( + r=8, + lora_alpha=16, + target_modules=["q_proj","k_proj","v_proj","o_proj", + "gate_proj","up_proj","down_proj"], + lora_dropout=0.05, + bias="none", + task_type=TaskType.CAUSAL_LM, +) + +# Training args +SFTConfig( + num_train_epochs=3, + per_device_train_batch_size=1, + gradient_accumulation_steps=8, + learning_rate=2e-4, + lr_scheduler_type="cosine", + optim="paged_adamw_8bit", + bf16=True, + gradient_checkpointing=True, + max_length=512, +) +``` + +--- + +## 📁 Repository Structure + +``` +ratulsur/multi-format-finance-parser/ +├── model.safetensors # Merged model weights (15.2 GB) +├── config.json # Model configuration +├── tokenizer.json # Tokenizer +├── tokenizer_config.json # Tokenizer configuration +├── chat_template.jinja # Chat template +└── generation_config.json # Generation configuration +``` + +--- + +## ⚠️ Limitations + +- Trained primarily on English financial documents +- Best performance on structured text (not handwritten documents) +- OCR quality affects accuracy for scanned documents +- SAP reports tested on ALV-style exports only +- 954 training samples — production use should involve more data + +--- + +## 🔗 Links + +- **Live Demo:** [HuggingFace Spaces](https://huggingface.co/spaces/ratulsur/finance-parser-demo) +- **Base Model:** [Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) +- **Training Dataset:** [CORD-v2](https://huggingface.co/datasets/naver-clova-ix/cord-v2) + +--- + +## 👤 Author + +**Ratul Sur** +- HuggingFace: [ratulsur](https://huggingface.co/ratulsur) + +--- + +*If you find this model useful, please give it a ⭐ like on HuggingFace!* \ No newline at end of file diff --git a/app.py b/app.py new file mode 100644 index 0000000..3938011 --- /dev/null +++ b/app.py @@ -0,0 +1,233 @@ +import gradio as gr +import requests +import json +import re +import os + +# ── Config ───────────────────────────────────────────────────── +MODEL_ID = "ratulsur/multi-format-finance-parser" +API_URL = f"https://api-inference.huggingface.co/models/{MODEL_ID}" +HF_TOKEN = os.environ.get("HF_TOKEN", "") + +SYSTEM_PROMPT = """You are a production financial document parser. +Given raw text from any financial document, output ONLY a single valid JSON object. +Schema: {document_type, vendor, client, date (YYYY-MM-DD), due_date, document_id, +currency, subtotal, tax_amount, tax_rate_pct, total_amount, +line_items:[{description,quantity,unit_price,amount}], payment_terms, notes, metadata}. +All monetary values must be floats. Unknown fields → null. No explanation.""" + +# ── Inference ────────────────────────────────────────────────── +def call_api(text: str) -> dict: + prompt = ( + f"<|im_start|>system\n{SYSTEM_PROMPT}<|im_end|>\n" + f"<|im_start|>user\nParse this financial document:\n\n{text}<|im_end|>\n" + f"<|im_start|>assistant\n" + ) + headers = { + "Authorization": f"Bearer {HF_TOKEN}", + "Content-Type": "application/json", + } + payload = { + "inputs": prompt, + "parameters": { + "max_new_tokens": 512, + "temperature": 0.05, + "return_full_text": False, + "do_sample": False, + }, + } + resp = requests.post(API_URL, headers=headers, json=payload, timeout=120) + resp.raise_for_status() + raw = resp.json()[0]["generated_text"].strip() + raw = re.sub(r"```json\s*|```\s*", "", raw).strip() + + # JSON repair heuristics + try: + return json.loads(raw) + except json.JSONDecodeError: + raw = (raw + .replace("'", '"') + .replace("None", "null") + .replace("True", "true") + .replace("False", "false") + .replace(",\n}", "\n}") + .replace(",\n]", "\n]")) + match = re.search(r"\{.*\}", raw, re.DOTALL) + try: + return json.loads(match.group() if match else raw) + except Exception: + return {"error": "Could not parse model output", "raw": raw} + + +# ── Main processing function ─────────────────────────────────── +def process(text_input: str, doc_hint: str): + if not text_input.strip(): + return "⚠️ Please paste some document text.", "" + + try: + text = text_input.strip() + if doc_hint and doc_hint != "Auto-detect": + text = f"[Document type: {doc_hint}]\n\n{text}" + + result = call_api(text) + + # Build summary + summary = [] + if result.get("error"): + return f"❌ Error: {result['error']}", json.dumps(result, indent=2) + if result.get("document_type"): + summary.append(f"**Type:** {result['document_type']}") + if result.get("vendor"): + summary.append(f"**Vendor:** {result['vendor']}") + if result.get("client"): + summary.append(f"**Client:** {result['client']}") + if result.get("date"): + summary.append(f"**Date:** {result['date']}") + if result.get("due_date"): + summary.append(f"**Due date:** {result['due_date']}") + if result.get("document_id"): + summary.append(f"**Document ID:** {result['document_id']}") + if result.get("currency") and result.get("total_amount") is not None: + summary.append(f"**Total:** {result['currency']} {result['total_amount']:,.2f}") + if result.get("tax_amount") is not None: + summary.append(f"**Tax:** {result.get('currency','')} {result['tax_amount']:,.2f}") + if result.get("line_items"): + summary.append(f"**Line items:** {len(result['line_items'])}") + if result.get("payment_terms"): + summary.append(f"**Payment terms:** {result['payment_terms']}") + + return "\n\n".join(summary), json.dumps(result, indent=2, ensure_ascii=False) + + except requests.exceptions.Timeout: + return "⚠️ Model is loading, please wait 20 seconds and try again.", "" + except requests.exceptions.HTTPError as e: + return f"❌ API Error: {e}", "" + except Exception as e: + return f"❌ Error: {e}", "" + + +# ── Examples ─────────────────────────────────────────────────── +EXAMPLES = [ + ["""INVOICE +Vendor: Tata Consultancy Services Ltd. +Invoice No: TCS-2024-8821 +Date: 2024-11-15 +Due Date: 2024-12-15 +Bill To: Reliance Industries Ltd. + +Service: Cloud Infrastructure Management (Oct 2024) INR 42,500.00 +Service: SAP Integration Support INR 18,000.00 +GST @ 18%: INR 10,890.00 +TOTAL DUE: INR 71,390.00 +Payment Terms: Net 30""", "Invoice"], + + ["""SAP FI - VENDOR PAYMENT REPORT +Company Code: 1000 | Fiscal Year: 2024 +Run Date: 2024-09-30 + +|DocNo |Vendor |Amount |Curr|Status | +|----------|--------------------|--------------|----|--------| +|1900045621|Wipro Limited | 4,25,000.00 |INR |Open | +|1900045622|HCL Technologies | 2,10,500.00 |INR |Cleared | +|1900045623|Infosys BPO | 8,75,200.00 |INR |Open | + +Total: 15,10,700.00 INR""", "SAP Report"], + + ["""INCOME STATEMENT +Reliance Industries Ltd. +Period ending: 2024-09-30 +(in INR) + +Revenue: 50,000,000.00 +Cost of Revenue: (22,000,000.00) +Gross Profit: 28,000,000.00 +Operating Expenses: (12,000,000.00) +EBIT: 16,000,000.00 +Income Tax 25%: (4,000,000.00) +Net Income: 12,000,000.00""", "Income Statement"], + + ["""PURCHASE ORDER +PO Number: PO-2024-00456 +Date: 2024-10-01 +Vendor: Amazon Web Services India +Ship To: HDFC Bank Ltd., Mumbai + +Item 1: EC2 Reserved Instances (1yr) USD 12,000.00 +Item 2: S3 Storage 50TB USD 1,800.00 +Item 3: RDS Multi-AZ USD 4,200.00 +Subtotal: USD 18,000.00 +Tax: USD 0.00 +Total: USD 18,000.00 +Payment Terms: Net 45""", "Purchase Order"], +] + + +# ── UI ───────────────────────────────────────────────────────── +with gr.Blocks( + title="Multi-Format Finance Parser", + theme=gr.themes.Soft(), + css=".json-output { font-family: monospace; font-size: 13px; }" +) as demo: + + gr.Markdown(""" +# 🏦 Multi-Format Finance Document Parser +**Production-grade** financial document extraction → structured JSON. + +Supports: **Invoice · SAP Report · Income Statement · Bank Statement · Purchase Order · SQL results** + +*Fine-tuned Qwen2.5-7B-Instruct · QLoRA 4-bit NF4 · Trained on CORD-v2 + synthetic finance data* + """) + + with gr.Row(): + with gr.Column(scale=1): + text_in = gr.Textbox( + label="Paste document text", + lines=16, + placeholder="Paste your invoice, SAP export, income statement, or any financial document here...", + ) + hint_in = gr.Dropdown( + choices=[ + "Auto-detect", + "Invoice", + "SAP Report", + "Balance Sheet", + "Income Statement", + "Bank Statement", + "Purchase Order", + "SQL Result", + ], + value="Auto-detect", + label="Document type hint (optional)", + ) + parse_btn = gr.Button("Parse Document", variant="primary", size="lg") + + with gr.Column(scale=1): + summary_out = gr.Markdown(label="Summary") + json_out = gr.Code( + label="Structured JSON output", + language="json", + lines=18, + ) + + gr.Markdown("### Try an example") + gr.Examples( + examples=EXAMPLES, + inputs=[text_in, hint_in], + label="Click any example to load it", + ) + + gr.Markdown(""" +--- +**Model:** [ratulsur/multi-format-finance-parser](https://huggingface.co/ratulsur/multi-format-finance-parser) +**Training:** QLoRA (4-bit NF4 double quantization) on Qwen2.5-7B-Instruct +**Dataset:** CORD-v2 receipts + synthetic invoices, SAP reports, income statements + """) + + parse_btn.click( + fn=process, + inputs=[text_in, hint_in], + outputs=[summary_out, json_out], + ) + +if __name__ == "__main__": + demo.launch() diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..bdf7919 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }} + {%- endif %} + {{- "\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 XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..089f5f8 --- /dev/null +++ b/config.json @@ -0,0 +1,61 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float16", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 18944, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen2", + "num_attention_heads": 28, + "num_hidden_layers": 28, + "num_key_value_heads": 4, + "pad_token_id": null, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "5.10.2", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..e0029cc --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.05, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.10.2" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..8357ac6 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8c36f07dea54d4b86453fcee15314516ccd721a781a8a741824d25e649977c5 +size 15231271816 diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..868ad04 --- /dev/null +++ b/requirements.txt @@ -0,0 +1,3 @@ +gradio>=4.36.0 +requests>=2.31.0 +uvicorn>=0.30.0 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..34510ff --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8 +size 11421892 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..5668a4a --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,30 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_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|>" + ], + "is_local": true, + "local_files_only": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}