commit 1053c5178f1cac054c0de11b4762e00dbb5b2967 Author: ModelHub XC Date: Sun May 10 22:25:55 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: tarun7r/Finance-Llama-8B 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/README.md b/README.md new file mode 100644 index 0000000..c327c0c --- /dev/null +++ b/README.md @@ -0,0 +1,324 @@ +--- +license: apache-2.0 +tags: +- text-generation-inference +- finance +- economics +datasets: +- Josephgflowers/Finance-Instruct-500k +language: +- en +base_model: +- unsloth/Meta-Llama-3.1-8B +pipeline_tag: text-generation +library_name: transformers +--- + +# Model Card for Finance-Llama-8B + +This model is a fine-tuned version of `unsloth/Meta-Llama-3.1-8B` on the `Josephgflowers/Finance-Instruct-500k` dataset. It's designed for financial tasks, reasoning, and multi-turn conversations. + +## Key Features + +* **Extensive Coverage:** Trained on over 500,000 entries spanning financial QA, reasoning, sentiment analysis, topic classification, multilingual NER, and conversational AI.📚 +* **Multi-Turn Conversations:** Capable of rich dialogues emphasizing contextual understanding and reasoning. +* **Diverse Data Sources:** Includes entries from Cinder, Sujet-Finance-Instruct-177k, Phinance Dataset, BAAI/IndustryInstruction_Finance-Economics, Josephgflowers/Financial-NER-NLP, and many other high-quality datasets. +* **Financial Specialization:** Tailored for financial reasoning, question answering, entity recognition, sentiment analysis, and more. + +## Dataset Details 💾 + +### Finance-Instruct-500k Dataset + +**Overview** +Finance-Instruct-500k is a comprehensive and meticulously curated dataset designed to train advanced language models for financial tasks, reasoning, and multi-turn conversations. Combining data from numerous high-quality financial datasets, this corpus provides over 500,000 entries, offering unparalleled depth and versatility for finance-related instruction tuning and fine-tuning. + +The dataset includes content tailored for financial reasoning, question answering, entity recognition, sentiment analysis, address parsing, and multilingual natural language processing (NLP). Its diverse and deduplicated entries make it suitable for a wide range of financial AI applications, including domain-specific assistants, conversational agents, and information extraction systems. + +**Key Features of the Dataset** +* **Extensive Coverage:** Over 500,000 entries spanning financial QA, reasoning, sentiment analysis, topic classification, multilingual NER, and conversational AI.🌍 +* **Multi-Turn Conversations:** Rich dialogues emphasizing contextual understanding and reasoning.🗣️ +* **Diverse Data Sources:** Includes entries from Cinder, Sujet-Finance-Instruct-177k, Phinance Dataset, BAAI/IndustryInstruction_Finance-Economics, Josephgflowers/Financial-NER-NLP, and many other high-quality datasets. 📖 + +## CFA Level 1 Mock Exam Results + +The CFA (Chartered Financial Analyst) exam is widely recognized as one of the most challenging professional certifications in the financial industry, typically requiring over 1000 hours of study across all three levels. The evaluation concept for the CFA Level 1 mock exam was inspired by the work on [mukaj/Llama-3.1-Hawkish-8B](https://huggingface.co/mukaj/Llama-3.1-Hawkish-8B). Below is a comparison of different models on a sample Level 1 CFA Mock Exam, demonstrating how Finance-Llama-8B performs on the exam. The same prompt was used for all models. The results presented are approximated and have been tested across multiple mock exam papers to ensure consistency. A sample mock exam with a comparison to other models is shown below. + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
CFA Level 1GPT-4o-mini (%)Finance-Llama-8B (%)Meta-Llama Instruct 8B (%)Meta-Llama Instruct 70B (%)
Ethical and Professional Standards80765668
Quantitative Methods74736485
Economics69745959
Financial Reporting81776771
Corporate Finance82715180
Equity Investments53674366
Fixed Income80722951
Derivatives54723435
Alternative Investments1008974100
Portfolio Management857552100
Weighted Average75735370
ResultPASSPASSFAILPASS
+ +The mock exams are designed to challenge candidates with varying levels of difficulty, reflecting the rigorous nature of the CFA Level 1 exam. Pass rates for these mock exams typically range from 64% to 72%, with an average pass rate of around 67%. This average is notably higher than the 12-year average Minimum Passing Score (MPS) of 65% for all CFA years, indicating the effectiveness of the preparation materials. For more detailed insights, visit [300hours.com/cfa-passing-score](https://300hours.com/cfa-passing-score/). + + +## Usage + +### Ollama + +You can also use this model with Ollama. Pre-built GGUF versions (FP16 and Q4_K_M) are available at: +[ollama.com/martain7r/finance-llama-8b](https://ollama.com/martain7r/finance-llama-8b) + +To run the FP16 version: +```bash +ollama run martain7r/finance-llama-8b:fp16 +``` + +To run the Q4_K_M quantized version (smaller and faster, with a slight trade-off in quality): +```bash +ollama run martain7r/finance-llama-8b:q4_k_m +``` + +This model can be used with the `transformers` library pipeline for text generation. + +First, make sure you have the `transformers` and `torch` libraries installed: + +````bash +pip install transformers torch +```` + +**Usage 🚀** +**Transformers Pipeline** + +````bash +from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer +import torch + +# Alternative memory-efficient loading options without bitsandbytes + +model_id = "tarun7r/Finance-Llama-8B" + +print("Loading model with memory optimizations...") + +# Option 1: Use FP16 (half precision) - reduces memory by ~50% +try: + print("Trying FP16 loading...") + model = AutoModelForCausalLM.from_pretrained( + model_id, + torch_dtype=torch.float16, # Half precision + device_map="auto", # Automatic device placement + low_cpu_mem_usage=True, # Efficient CPU memory usage during loading + trust_remote_code=True + ) + print("✓ Model loaded with FP16") + +except Exception as e: + print(f"FP16 loading failed: {e}") + + # Option 2: CPU offloading - some layers on GPU, some on CPU + try: + print("Trying CPU offloading...") + model = AutoModelForCausalLM.from_pretrained( + model_id, + torch_dtype=torch.float16, + device_map="balanced", # Balance between GPU and CPU + low_cpu_mem_usage=True, + trust_remote_code=True + ) + print("✓ Model loaded with CPU offloading") + + except Exception as e: + print(f"CPU offloading failed: {e}") + + # Option 3: Full CPU loading as fallback + print("Loading on CPU...") + model = AutoModelForCausalLM.from_pretrained( + model_id, + torch_dtype=torch.float16, + device_map="cpu", + low_cpu_mem_usage=True, + trust_remote_code=True + ) + print("✓ Model loaded on CPU") + +# Load tokenizer +tokenizer = AutoTokenizer.from_pretrained(model_id) +if tokenizer.pad_token is None: + tokenizer.pad_token = tokenizer.eos_token + +# Create pipeline +generator = pipeline( + "text-generation", + model=model, + tokenizer=tokenizer +) + +print("✓ Pipeline created successfully!") + + +# Your existing prompt code +finance_prompt_template = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request. + +### Instruction: +{} + +### Input: +{} + +### Response: +""" + +# Update the system prompt to provide a more detailed description of the chatbot's role +messages = [ + {"role": "system", "content": "You are a highly knowledgeable finance chatbot. Your purpose is to provide accurate, insightful, and actionable financial advice to users, tailored to their specific needs and contexts."}, + {"role": "user", "content": "What strategies can an individual investor use to diversify their portfolio effectively in a volatile market?"}, +] + +# Update the generator call to use the messages +prompt = "\n".join([f"{msg['role'].capitalize()}: {msg['content']}" for msg in messages]) + +print("\n--- Generating Response ---") + +try: + outputs = generator( + prompt, + #max_new_tokens=250, # Reduced for memory efficiency + do_sample=True, + temperature=0.7, + top_p=0.9, + pad_token_id=tokenizer.eos_token_id, + # Memory efficient generation settings + num_beams=1, # No beam search to save memory + early_stopping=True, + use_cache=True + ) + + # Extract response + generated_text = outputs[0]['generated_text'] + response_start = generated_text.rfind("### Response:") + if response_start != -1: + response = generated_text[response_start + len("### Response:"):].strip() + print("\n--- Response ---") + print(response) + else: + print(generated_text) + + # Clean up GPU memory after generation + if torch.cuda.is_available(): + torch.cuda.empty_cache() + +except Exception as e: + print(f"Generation error: {e}") + + +```` +**Citation 📌** +```` +@misc{tarun7r/Finance-Llama-8B, + author = {tarun7r}, + title = {tarun7r/Finance-Llama-8B: A Llama 3.1 8B Model Fine-tuned on Josephgflowers/Finance-Instruct-500k}, + year = {2025}, + publisher = {Hugging Face}, + journal = {Hugging Face Model Hub}, + howpublished = {\url{https://huggingface.co/tarun7r/Finance-Llama-8B}} +} + +```` + +## Disclaimer & Intended Uses + +### Model & License +This model is an experimental research implementation based on Meta's LLaMA 3.1 architecture and is governed by the LLaMA 3.1 community license terms, with additional restrictions as outlined below. It is designed for academic and research purposes to explore the influence of financial data in training language models. Users are advised that this model is experimental and should be used at their own risk, with full responsibility for any implementation or application. **This model is not a financial advisor and should not be used for financial decision-making.** + +### Liability & Responsibility +The creators of this model: +- Accept no responsibility for any use of the model, including any financial losses or damages incurred. +- Provide no warranties or guarantees regarding its performance, accuracy, or reliability. +- Make no claims about the suitability of the model for any specific purpose. + +### Intellectual Property & Attribution +- All findings and opinions expressed are solely those of the authors. +- This model is not endorsed by or affiliated with Meta, the CFA Institute, or any other institutions. +- All trademarks and intellectual property rights belong to their respective owners. \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..01615d4 --- /dev/null +++ b/config.json @@ -0,0 +1,38 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128001, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 128004, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.51.3", + "unsloth_fixed": true, + "unsloth_version": "2025.5.7", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..232d4a7 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,11 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": 128001, + "max_length": 131072, + "pad_token_id": 128004, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.51.3" +} diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..4bb0778 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 16060522496 + }, + "weight_map": { + "model.embed_tokens.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.safetensors", + "lm_head.weight": "pytorch_model-00004-of-00004.safetensors", + "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00004.safetensors", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.safetensors", + "model.norm.weight": "pytorch_model-00004-of-00004.safetensors" + } +} \ No newline at end of file diff --git a/pytorch_model-00001-of-00004.safetensors b/pytorch_model-00001-of-00004.safetensors new file mode 100644 index 0000000..d92f14a --- /dev/null +++ b/pytorch_model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd958bceca742b63988e37e4a5d3d1a021ea45836ba893ae1ca1108942d31422 +size 4976698592 diff --git a/pytorch_model-00002-of-00004.safetensors b/pytorch_model-00002-of-00004.safetensors new file mode 100644 index 0000000..0462350 --- /dev/null +++ b/pytorch_model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45f4aeb19a1b9bc93161a0c887e5793c7528d29d5744fd6e7a3bdbdf8a6b1692 +size 4999802616 diff --git a/pytorch_model-00003-of-00004.safetensors b/pytorch_model-00003-of-00004.safetensors new file mode 100644 index 0000000..9612212 --- /dev/null +++ b/pytorch_model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89cb5929bf924cd3936409a97a0e1071eace8b4976a7355cfe821068eea8d966 +size 4915916080 diff --git a/pytorch_model-00004-of-00004.safetensors b/pytorch_model-00004-of-00004.safetensors new file mode 100644 index 0000000..5ee590c --- /dev/null +++ b/pytorch_model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b665ba94a043aaa20672dd38661974ae23af59db44e4c306fd0e0fce8d44557c +size 1168138808 diff --git a/safe.py b/safe.py new file mode 100644 index 0000000..d7a821d --- /dev/null +++ b/safe.py @@ -0,0 +1,44 @@ +import json +from safetensors import safe_open + +def generate_safetensors_index(model_path="."): + """Generate model.safetensors.index.json from existing safetensors files""" + + # Load the existing bin index as reference + with open(f"pytorch_model.bin.index.json", "r") as f: + bin_index = json.load(f) + + # Initialize the safetensors index structure + safetensors_index = { + "metadata": bin_index.get("metadata", {}), + "weight_map": {} + } + + # Map each safetensors file and get its tensor names + safetensors_files = [ + "pytorch_model-00001-of-00004.safetensors", + "pytorch_model-00002-of-00004.safetensors", + "pytorch_model-00003-of-00004.safetensors", + "pytorch_model-00004-of-00004.safetensors" + ] + + for safetensor_file in safetensors_files: + try: + with safe_open(f"{safetensor_file}", framework="pt") as f: + for tensor_name in f.keys(): + safetensors_index["weight_map"][tensor_name] = safetensor_file + print(f"✓ Processed {safetensor_file}") + except Exception as e: + print(f"✗ Error processing {safetensor_file}: {e}") + + # Save the index file + with open(f"model.safetensors.index.json", "w") as f: + json.dump(safetensors_index, f, indent=2) + + print(f"✓ Generated model.safetensors.index.json with {len(safetensors_index['weight_map'])} tensors") + return safetensors_index + +# Run the function +if __name__ == "__main__": + # Change this path to your model directory if needed + generate_safetensors_index("./Finance-Llama-8B") \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..68b10c7 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..1c1d8d5 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..193429e --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2066 @@ +{ + "add_bos_token": true, + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|end_of_text|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|finetune_right_pad_id|>", + "padding_side": "left", + "tokenizer_class": "PreTrainedTokenizer", + "unk_token": null +}