From 8994331d7e644b8b6c91643f088c71a45c9bd2ea Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Wed, 6 May 2026 22:11:55 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: DeepSQL/DeepSQL-1.0 Source: Original Platform --- .gitattributes | 38 ++++++ LICENSE.md | 204 ++++++++++++++++++++++++++++ README.md | 288 ++++++++++++++++++++++++++++++++++++++++ config.json | 30 +++++ deepsql-1.0.gguf | 3 + generation_config.json | 9 ++ model.safetensors | 3 + special_tokens_map.json | 23 ++++ tokenizer.json | 3 + tokenizer_config.json | 195 +++++++++++++++++++++++++++ 10 files changed, 796 insertions(+) create mode 100644 .gitattributes create mode 100644 LICENSE.md create mode 100644 README.md create mode 100644 config.json create mode 100644 deepsql-1.0.gguf create mode 100644 generation_config.json create mode 100644 model.safetensors create mode 100644 special_tokens_map.json create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bd3a116 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,38 @@ +*.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 +DeepSQL-1.0/deepsql-model.gguf filter=lfs diff=lfs merge=lfs -text +deepsql-1.0.gguf filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/LICENSE.md b/LICENSE.md new file mode 100644 index 0000000..a85a309 --- /dev/null +++ b/LICENSE.md @@ -0,0 +1,204 @@ +Apache License +Version 2.0, January 2004 +http://www.apache.org/licenses/ + +TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + +1. Definitions. + +"License" shall mean the terms and conditions for use, reproduction, +and distribution as defined by Sections 1 through 9 of this document. + +"Licensor" shall mean the copyright owner or entity granting the License. + +"Legal Entity" shall mean the union of the acting entity and all +other entities that control, are controlled by, or are under common +control with that entity. For the purposes of this definition, +"control" means (i) the power, direct or indirect, to cause the +direction or management of such entity, whether by contract or +otherwise, or (ii) ownership of fifty percent (50%) or more of the +outstanding shares, or (iii) beneficial ownership of such entity. + +"You" (or "Your") shall mean an individual or Legal Entity +exercising permissions granted by this License. + +"Source" form shall mean the preferred form for making modifications, +including but not limited to software source code, documentation +source, and configuration files. + +"Object" form shall mean any form resulting from mechanical +transformation or translation of a Source form, including but +not limited to compiled object code, generated documentation, +and conversions to other media types. + +"Work" shall mean the work of authorship, whether in Source or +Object form, made available under the License, as indicated by a +copyright notice that is included in or attached to the work +(which shall not be construed as modifying the License). + +"Derivative Works" shall mean any work, whether in Source or Object +form, that is based upon (or derived from) the Work and for which the +editorial revisions, annotations, elaborations, or other modifications +represent, as a whole, an original work of authorship. For the purposes +of this License, Derivative Works shall not include works that remain +separable from, or merely link (or bind by name) to the interfaces of, +the Work and derivative works thereof. + +"Contribution" shall mean any work of authorship, including +the original version of the Work and any modifications or additions +to that Work or Derivative Works thereof, that is intentionally +submitted to Licensor for inclusion in the Work by the copyright owner +or by an individual or Legal Entity authorized to submit on behalf of +the copyright owner. For the purposes of this definition, "submitted" +means any form of electronic, verbal, or written communication sent +to the Licensor or its representatives, including but not limited to +communication on electronic mailing lists, source code control +systems, and issue tracking systems that are managed by, or on behalf +of, the Licensor for the purpose of discussing and improving the Work, +but excluding communication that is conspicuously marked or otherwise +designated in writing by the copyright owner as "Not a Contribution." + +"Contributor" shall mean Licensor and any individual or Legal Entity +on behalf of whom a Contribution has been received by Licensor and +subsequently incorporated within the Work. + +2. Grant of Copyright License. Subject to the terms and conditions of +this License, each Contributor hereby grants to You a perpetual, +worldwide, non-exclusive, no-charge, royalty-free, irrevocable +copyright license to use, reproduce, modify, merge, publish, +distribute, sublicense, and/or sell copies of the Work, and to +permit persons to whom the Work is furnished to do so, subject to +the following conditions: + +The above copyright notice and this permission notice shall be +included in all copies or substantial portions of the Work. + +3. Grant of Patent License. Subject to the terms and conditions of +this License, each Contributor hereby grants to You a perpetual, +worldwide, non-exclusive, no-charge, royalty-free, irrevocable +(except as stated in this section) patent license to make, have made, +use, offer to sell, sell, import, and otherwise transfer the Work, +where such license applies only to those patent claims licensable +by such Contributor that are necessarily infringed by their +Contribution(s) alone or by combination of their Contribution(s) +with the Work to which such Contribution(s) was submitted. If You +institute patent litigation against any entity (including a +cross-claim or counterclaim in a lawsuit) alleging that the Work +or a Contribution incorporated within the Work constitutes direct +or contributory patent infringement, then any patent licenses +granted to You under this License for that Work shall terminate +as of the date such litigation is filed. + +4. Redistribution. You may reproduce and distribute copies of the +Work or Derivative Works thereof in any medium, with or without +modifications, and in Source or Object form, provided that You +meet the following conditions: + +(a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + +(b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + +(c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, trademark, patent, + attribution and other notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + +(d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + +You may add Your own copyright notice to Your modifications and +may provide additional or different license terms and conditions +for use, reproduction, or distribution of Your modifications, or +for any such Derivative Works as a whole, provided Your use, +reproduction, and distribution of the Work otherwise complies with +the conditions stated in this License. + +5. Submission of Contributions. Unless You explicitly state otherwise, +any Contribution intentionally submitted for inclusion in the Work +by You to the Licensor shall be under the terms and conditions of +this License, without any additional terms or conditions. +Notwithstanding the above, nothing herein shall supersede or modify +the terms of any separate license agreement you may have executed +with Licensor regarding such Contributions. + +6. Trademarks. This License does not grant permission to use the trade +names, trademarks, service marks, or product names of the Licensor, +except as required for reasonable and customary use in describing the +origin of the Work and reproducing the content of the NOTICE file. + +7. Disclaimer of Warranty. Unless required by applicable law or +agreed to in writing, Licensor provides the Work (and each +Contributor provides its Contributions) on an "AS IS" BASIS, +WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or +implied, including, without limitation, any warranties or conditions +of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A +PARTICULAR PURPOSE. You are solely responsible for determining the +appropriateness of using or redistributing the Work and assume any +risks associated with Your exercise of permissions under this License. + +8. Limitation of Liability. In no event and under no legal theory, +whether in tort (including negligence), contract, or otherwise, +unless required by applicable law (such as deliberate and grossly +negligent acts) or agreed to in writing, shall any Contributor be +liable to You for damages, including any direct, indirect, special, +incidental, or consequential damages of any character arising as a +result of this License or out of the use or inability to use the +Work (including but not limited to damages for loss of goodwill, +work stoppage, computer failure or malfunction, or any and all +other commercial damages or losses), even if such Contributor +has been advised of the possibility of such damages. + +9. Accepting Warranty or Additional Liability. When redistributing +the Work or Derivative Works thereof, You may choose to offer, +and charge a fee for, acceptance of support, warranty, indemnity, +or other liability obligations and/or rights consistent with this +License. However, in accepting such obligations, You may act only +on Your own behalf and on Your sole responsibility, not on behalf +of any other Contributor, and only if You agree to indemnify, +defend, and hold each Contributor harmless for any liability +incurred by, or claims asserted against, such Contributor by reason +of your accepting any such warranty or additional liability. + +END OF TERMS AND CONDITIONS + +APPENDIX: How to apply the Apache License to your work. + +To apply the Apache License to your work, attach the following +boilerplate notice, with the fields enclosed by brackets "[]" +replaced with your own identifying information. (Don't include +the brackets!) The text should be enclosed in the appropriate +comment syntax for the file format. We also recommend that a +file or class name and description of purpose be included on the +same page as the copyright notice for easier identification within +third-party archives. + +Copyright [2026] [Ameet Naik] + +Licensed under the Apache License, Version 2.0 (the "License"); +you may not use this file except in compliance with the License. +You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + +Unless required by applicable law or agreed to in writing, software +distributed under the License is distributed on an "AS IS" BASIS, +WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +See the License for the specific language governing permissions and +limitations under the License. \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..74fb5c9 --- /dev/null +++ b/README.md @@ -0,0 +1,288 @@ +--- +license: apache-2.0 +base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B +tags: +- text-to-sql +- sql-generation +- natural-language-to-sql +- deepseek +- qwen +- reasoning +- database +language: +- en +pipeline_tag: text-generation +datasets: +- ameet/deepsql_training +--- + +# DeepSQL + +DeepSQL is a fine-tuned language model specialized in converting natural language questions into SQL queries. It is based on [DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) and has been trained to understand database schemas and generate accurate SQL queries from natural language questions. + +## Model Details + +### Model Description + +- **Model Type**: Causal Language Model (Qwen2-based) +- **Architecture**: Qwen2ForCausalLM +- **Base Model**: DeepSeek-R1-Distill-Qwen-1.5B +- **Parameters**: 1.5B +- **Fine-tuning Method**: LoRA (Low-Rank Adaptation) with FSDP (Fully Sharded Data Parallel) +- **Context Length**: 131,072 tokens + +### Model Architecture + +- **Hidden Size**: 1,536 +- **Intermediate Size**: 8,960 +- **Number of Layers**: 28 +- **Attention Heads**: 12 +- **Key-Value Heads**: 2 +- **Vocabulary Size**: 151,936 +- **Activation Function**: SiLU +- **Normalization**: RMSNorm + +## Intended Use + +### Direct Use + +DeepSQL is designed to: +- Convert natural language questions about databases into SQL queries +- Understand complex database schemas and relationships +- Generate SQL queries with reasoning about the query structure +- Handle multi-table joins, aggregations, and complex filtering conditions + +### Out-of-Scope Use + +This model should not be used for: +- General-purpose text generation +- Tasks unrelated to SQL generation +- Generating SQL queries without proper schema validation +- Production database operations without proper testing and validation + +## Training Details + +### Training Data + +The model was fine-tuned on the SynSQL2.5M dataset, a large-scale text-to-SQL dataset comprising over 2.5 million diverse and high-quality samples spanning more than 16,000 databases from various domains. The training data was processed and formatted as the `ameet/deepsql_training` dataset, which contains: +- Natural language questions about databases +- Corresponding database schemas (DDL) +- Chain-of-thought reasoning for SQL generation +- Target SQL queries +- External knowledge annotations + +The SynSQL2.5M dataset provides comprehensive coverage of SQL query patterns, including complex joins, aggregations, subqueries, and various SQL dialects, making it an ideal training resource for text-to-SQL models. + +### Training Procedure + +- **Training Framework**: PyTorch with FSDP +- **Optimizer**: AdamW +- **Learning Rate**: 1e-5 +- **LoRA Configuration**: + - Rank (r): 16 + - LoRA Alpha: 32 + - Target Modules: q_proj, k_proj, v_proj, o_proj + - LoRA Dropout: 0 +- **Precision**: bfloat16 +- **Training Infrastructure**: Multi-GPU training with FSDP sharding + +### Training Input Format + +The model uses a specific chat template format: + +``` +The user asks a question about a database, and the Assistant helps convert it to SQL. The assistant first thinks about how to write the SQL query by analyzing the question, database schema and external knowledge, then provides the final SQL query. +The reasoning process and SQL query are enclosed within and tags respectively. The answer query must contain the SQL query within ```sql``` tags. + +Database Schema: {schema} + +External Knowledge: {external_knowledge} + +User: {question} + +Assistant: {cot} + +{sql} + +``` + +## How to Use + +### Using Transformers + +```python +from transformers import AutoTokenizer, AutoModelForCausalLM +import torch + +model_name = "DeepSQL/DeepSQL-1.0" +tokenizer = AutoTokenizer.from_pretrained(model_name) +model = AutoModelForCausalLM.from_pretrained( + model_name, + torch_dtype=torch.bfloat16, + device_map="auto" +) + +# Prepare your input +schema = """ +CREATE TABLE "vehicles" ( + "vehicle_id" INTEGER, + "make" TEXT, + "model" TEXT, + "year" INTEGER, + "price" REAL, + PRIMARY KEY ("vehicle_id") +); +""" + +question = "What is the average price of vehicles by make?" +external_knowledge = "" + +prompt = f"""The user asks a question about a database, and the Assistant helps convert it to SQL. The assistant first thinks about how to write the SQL query by analyzing the question, database schema and external knowledge, then provides the final SQL query. +The reasoning process and SQL query are enclosed within and tags respectively. The answer query must contain the SQL query within ```sql``` tags. + +Database Schema: {schema} + +External Knowledge: {external_knowledge} + +User: {question} + +Assistant:""" + +# Tokenize and generate +inputs = tokenizer(prompt, return_tensors="pt").to(model.device) +outputs = model.generate( + **inputs, + max_new_tokens=1024, + do_sample=True, + temperature=0.8, + pad_token_id=tokenizer.eos_token_id +) + +response = tokenizer.decode(outputs[0], skip_special_tokens=False) +print(response) +``` + +### Using LMStudio with GGUF + +A GGUF model file (`deepsql-1.0.gguf`) is provided for easy inference with LMStudio: + +1. **Download the GGUF file**: + - Download `deepsql-1.0.gguf` from the model repository + +2. **Open LMStudio**: + - Launch LMStudio on your system + +3. **Load the model**: + - Click on the "Browse" button in the Models section + - Navigate to the directory containing `deepsql-1.0.gguf` + - Select the file and click "Load" + +4. **Configure settings** (recommended): + - **Temperature**: 0.6-0.8 (for more focused SQL generation) + - **Top P**: 0.95 + - **Max Tokens**: 1024 (sufficient for most SQL queries) + +5. **Use the Chat interface**: + - Format your prompt according to the training template: + ``` + Database Schema: [your schema here] + + External Knowledge: [optional external knowledge] + + User: [your question] + + Assistant: + ``` + +6. **Extract the SQL query**: + - The model will generate reasoning in `` tags + - The SQL query will be in the `` section within ```sql``` tags + - Copy the SQL query from the response + +### Example Usage in LMStudio + +**Input:** +``` +Database Schema: +CREATE TABLE "products" ( + "product_id" INTEGER PRIMARY KEY, + "name" TEXT, + "price" REAL, + "category" TEXT +); + +User: What are the top 5 most expensive products in the Electronics category? +``` + +**Expected Output:** +``` + +I need to find the top 5 most expensive products in the Electronics category. This requires: +1. Filtering by category = 'Electronics' +2. Ordering by price in descending order +3. Limiting to 5 results + + +\```sql +SELECT product_id, name, price, category +FROM products +WHERE category = 'Electronics' +ORDER BY price DESC +LIMIT 5; +\``` + +``` + +## Limitations and Bias + +- The model may generate SQL queries that are syntactically correct but logically incorrect +- Performance may vary depending on the complexity of the database schema +- The model is trained primarily on English language questions +- Generated SQL queries should always be validated and tested before execution on production databases +- The model may struggle with very complex multi-table joins or advanced SQL features not present in the training data + +## Evaluation + +The model's performance should be evaluated on: +- SQL accuracy (syntactic correctness) +- SQL execution success rate +- Semantic correctness of generated queries +- Handling of edge cases and complex schemas + +## Citation + +If you use DeepSQL in your research or applications, please cite: + +```bibtex +@misc{deepsql2026, + title={DeepSQL: A Fine-tuned Language Model for Text-to-SQL Generation}, + author={Your Name}, + year={2026}, + publisher={Hugging Face}, + howpublished={\url{https://huggingface.co/your-username/deepsql}} +} +``` + +### Dataset Citation + +This model was trained using the SynSQL2.5M dataset. If you use this model, please also cite the SynSQL2.5M dataset: + +```bibtex +@article{li2025omnisql, + title={OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale}, + author={Li, Haoyang and Wu, Song and Zhang, Xinyuan and Huang, Xinyi and Zhang, Jiaqi and Jiang, Fei and Wang, Siyuan and Zhang, Tianyi and Chen, Jing and Shi, Rui}, + journal={Proceedings of the VLDB Endowment}, + volume={18}, + number={12}, + pages={4695--4706}, + year={2025} +} +``` + +## Model Card Contact + +For questions, issues, or contributions, please open an issue on the model repository. + +## License + +This model is licensed under the Apache 2.0 license. See the LICENSE file for more details. \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..ce4297a --- /dev/null +++ b/config.json @@ -0,0 +1,30 @@ +{ + "_name_or_path": "./models/DeepSeek-R1-Distill-Qwen-1.5B", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 1536, + "initializer_range": 0.02, + "intermediate_size": 8960, + "max_position_embeddings": 131072, + "max_window_layers": 21, + "model_type": "qwen2", + "num_attention_heads": 12, + "num_hidden_layers": 28, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.48.2", + "use_cache": false, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/deepsql-1.0.gguf b/deepsql-1.0.gguf new file mode 100644 index 0000000..aec8e37 --- /dev/null +++ b/deepsql-1.0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78c85dd4a8375f99b9a191af6b121fc036201bb4526f62deb8d16892024394e3 +size 3560416000 diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..faa5974 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "bos_token_id": 151646, + "do_sample": true, + "eos_token_id": 151643, + "temperature": 0.6, + "top_p": 0.95, + "transformers_version": "4.48.2" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..7064e30 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16bea0a35dba47a078ac1750e001512a02837da37c70c3c806244efbe9efefc8 +size 3554214752 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..1d385d6 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..1a2db24 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..3240a49 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,195 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "151643": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<｜User｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151645": { + "content": "<｜Assistant｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151646": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|EOT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151648": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151649": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "<｜begin▁of▁sentence｜>", + "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<｜end▁of▁sentence｜>", + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 16384, + "pad_token": "<｜end▁of▁sentence｜>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": null, + "use_default_system_prompt": false +}