Text Generation
Transformers
Safetensors
English
qwen2
text-generation-inference
unsloth
conversational
Instructions to use hozifa1/Faqih-R1-14B-Islamic-AI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hozifa1/Faqih-R1-14B-Islamic-AI with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="hozifa1/Faqih-R1-14B-Islamic-AI") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("hozifa1/Faqih-R1-14B-Islamic-AI") model = AutoModelForCausalLM.from_pretrained("hozifa1/Faqih-R1-14B-Islamic-AI", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use hozifa1/Faqih-R1-14B-Islamic-AI with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "hozifa1/Faqih-R1-14B-Islamic-AI" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hozifa1/Faqih-R1-14B-Islamic-AI", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/hozifa1/Faqih-R1-14B-Islamic-AI
- SGLang
How to use hozifa1/Faqih-R1-14B-Islamic-AI with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "hozifa1/Faqih-R1-14B-Islamic-AI" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hozifa1/Faqih-R1-14B-Islamic-AI", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "hozifa1/Faqih-R1-14B-Islamic-AI" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hozifa1/Faqih-R1-14B-Islamic-AI", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Studio
How to use hozifa1/Faqih-R1-14B-Islamic-AI with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for hozifa1/Faqih-R1-14B-Islamic-AI to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for hozifa1/Faqih-R1-14B-Islamic-AI to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for hozifa1/Faqih-R1-14B-Islamic-AI to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="hozifa1/Faqih-R1-14B-Islamic-AI", max_seq_length=2048, ) - Docker Model Runner
How to use hozifa1/Faqih-R1-14B-Islamic-AI with Docker Model Runner:
docker model run hf.co/hozifa1/Faqih-R1-14B-Islamic-AI
Training in progress, step 400
Browse files- README.md +39 -116
- adapter_config.json +52 -0
- adapter_model.safetensors +3 -0
- tokenizer.json +2 -2
- tokenizer_config.json +186 -6
- training_args.bin +3 -0
README.md
CHANGED
|
@@ -1,136 +1,59 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
license: apache-2.0
|
| 6 |
-
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
|
| 7 |
tags:
|
| 8 |
-
-
|
| 9 |
-
- arabic
|
| 10 |
-
- fiqh
|
| 11 |
-
- hadith
|
| 12 |
-
- quran
|
| 13 |
-
- reasoning
|
| 14 |
-
- deepseek-r1
|
| 15 |
- unsloth
|
| 16 |
-
-
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
---
|
| 20 |
-
|
| 21 |
-
# 🕌 Faqih-R1-14B (فقيه): Islamic AI & Jurisprudential Reasoning Model
|
| 22 |
-
|
| 23 |
-
<div align="center">
|
| 24 |
-
|
| 25 |
-
[](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B)
|
| 26 |
-
[](LICENSE)
|
| 27 |
-
[](https://github.com/unslothai/unsloth)
|
| 28 |
-
[](#)
|
| 29 |
-
|
| 30 |
-
</div>
|
| 31 |
-
|
| 32 |
-
---
|
| 33 |
-
|
| 34 |
-
## ⚠️ تنويه شرعي وبحثي هام (Important Research & Religious Disclaimer)
|
| 35 |
-
|
| 36 |
-
> [!IMPORTANT]
|
| 37 |
-
> **هذا النموذج هو إصدار تجريبي وبحثي قيد التطوير والتدريب النشط (Experimental Research Preview / Under Active Training).**
|
| 38 |
-
>
|
| 39 |
-
> 1. **ليس نموذجاً معصوماً ولا مكتملاً بنسبة 100%:** لا يزال النموذج يخضع لعمليات التحسين والمواءمة ومراجعة المصادر لمنع الهلوسة وضبط الدقة الاستنباطية.
|
| 40 |
-
> 2. **ليس بديلاً عن العلماء ودور الإفتاء المعتمدة:** هذا النموذج هو أداة بحثية وتقنية مساعدة للباحثين وطلبة العلم، **ولا يجوز استخدامه كمفتٍ مطلق أو إصدار فتاوى قطعية ملزمة** في النوازل والقضايا الحساسة دون الرجوع للمجامع الفقهية وهيئات كبار العلماء الرسمية (مثل هيئة كبار العلماء، دار الإفتاء المصرية، مجمع الفقه الإسلامي الدولي).
|
| 41 |
-
|
| 42 |
-
---
|
| 43 |
-
|
| 44 |
-
## 📌 عن النموذج (Model Overview)
|
| 45 |
-
|
| 46 |
-
نموذج **Faqih-R1-14B (فقيه)** هو نموذج لغوي كبير متخصص في **الاستدلال الفقهي والعلوم الإسلامية**، مبني ومدرب عبر تقنيات التفكير العميق المنظم (Chain-of-Thought Reasoning).
|
| 47 |
-
|
| 48 |
-
* **النموذج التأسيسي (Base Model):** [`deepseek-ai/DeepSeek-R1-Distill-Qwen-14B`](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B).
|
| 49 |
-
* **المعمارية (Architecture):** معمارية Qwen 2.5 المقطرة من DeepSeek-R1 بحجم 14.8 مليار معلمة (14.8B Parameters).
|
| 50 |
-
* **تقنية التدريب (Fine-Tuning Method):** Unsloth QLoRA (4-bit quantization) مع سياق استدلال موسع.
|
| 51 |
-
* **البيانات التدريبية (Training Corpus):** أكثر من 60,820 مسألة فقهية واستدلالية محققة تغطي:
|
| 52 |
-
* الفقه المقارن على المذاهب الأربعة المعتمدة (الحنفي، المالكي، الشافعي، الحنبلي).
|
| 53 |
-
* تفاسير القرآن الكريم وأسباب النزول.
|
| 54 |
-
* تخريج الأحاديث النبوية ودرجات صحتها.
|
| 55 |
-
* مسائل حساب الفرائض والمواريث.
|
| 56 |
-
|
| 57 |
---
|
| 58 |
|
| 59 |
-
#
|
| 60 |
-
|
| 61 |
-
يستخدم النموذج وسوم التفكير `<think> ... </think>` لتفكيك المسألة الشرعية قبل تقديم الحكم النهائي:
|
| 62 |
-
|
| 63 |
-
```text
|
| 64 |
-
المستخدم: ما حكم الجمع بين الصلاتين للمسافر في المذهب الشافعي؟
|
| 65 |
-
|
| 66 |
-
النموذج:
|
| 67 |
-
<think>
|
| 68 |
-
1. تحليل المسألة: مسألة الجمع بين الظهر والعصر، أو المغرب والعشاء للمسافر.
|
| 69 |
-
2. المذهب المطلوب: مذهب الإمام الشافعي رحمه الله.
|
| 70 |
-
3. مراجعة شروط القصر والجمع في المذهب:
|
| 71 |
-
- مسافة السفر: سفر طويل مباح (أربعة بُرد / حوالي 83 كم).
|
| 72 |
-
- أنواع الجمع: يجوز جمع تقديم أو جمع تأخير.
|
| 73 |
-
- الشروط: الترتيب، نية الجمع في أولى الصلاتين، والموالاة.
|
| 74 |
-
4. صياغة الجواب مع الأدلة من السنة النبوية وأمهات كتب الشافعية (المجموع للنووي، منهاج الطالبين).
|
| 75 |
-
</think>
|
| 76 |
-
|
| 77 |
-
يجوز للمسافر سفراً طويلاً مباحاً (مسافة 83 كم فأكثر) الجمع بين الظهر والعصر، والمغرب والعشاء، جمع تقديم أو تأخير وفق معتمد المذهب الشافعي، بالشروط الآتية:
|
| 78 |
-
1. الترتيب بين الصلاتين.
|
| 79 |
-
2. نية الجمع في الصلاة الأولى.
|
| 80 |
-
3. الموالاة بينهما.
|
| 81 |
-
...
|
| 82 |
-
```
|
| 83 |
-
|
| 84 |
-
---
|
| 85 |
|
| 86 |
-
|
|
|
|
| 87 |
|
| 88 |
-
##
|
| 89 |
|
| 90 |
```python
|
| 91 |
-
from transformers import
|
| 92 |
-
import torch
|
| 93 |
|
| 94 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 95 |
|
| 96 |
-
|
| 97 |
-
model = AutoModelForCausalLM.from_pretrained(
|
| 98 |
-
model_id,
|
| 99 |
-
torch_dtype=torch.bfloat16,
|
| 100 |
-
device_map="auto"
|
| 101 |
-
)
|
| 102 |
|
| 103 |
-
|
| 104 |
-
messages = [
|
| 105 |
-
{"role": "user", "content": prompt}
|
| 106 |
-
]
|
| 107 |
|
| 108 |
-
inputs = tokenizer.apply_chat_template(
|
| 109 |
-
messages,
|
| 110 |
-
tokenize=True,
|
| 111 |
-
add_generation_prompt=True,
|
| 112 |
-
return_tensors="pt"
|
| 113 |
-
).to("cuda")
|
| 114 |
|
| 115 |
-
|
| 116 |
-
inputs,
|
| 117 |
-
max_new_tokens=1024,
|
| 118 |
-
temperature=0.6,
|
| 119 |
-
top_p=0.95
|
| 120 |
-
)
|
| 121 |
|
| 122 |
-
|
| 123 |
-
print(response)
|
| 124 |
-
```
|
| 125 |
|
| 126 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 127 |
|
| 128 |
-
##
|
| 129 |
|
| 130 |
-
* **الامتناع عن القطع في المختلف فيه:** تم تدريب النموذج على عرض أقوال المذاهب بأدلتها دون تعصب لمذهب واحد.
|
| 131 |
-
* **عدم الاجتهاد المطلق:** يقتصر النموذج على نقل وتلخيص واستنباط ما قرره علماء الأمة المحققون من أمهات المصادر، ولا يُنشئ أحكاماً مستحدثة خارج الإجماع المستقر.
|
| 132 |
|
| 133 |
-
---
|
| 134 |
|
| 135 |
-
|
| 136 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: unsloth/deepseek-r1-distill-qwen-14b-unsloth-bnb-4bit
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: Faqih-R1-14B-Islamic-AI
|
|
|
|
|
|
|
| 5 |
tags:
|
| 6 |
+
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
- unsloth
|
| 8 |
+
- sft
|
| 9 |
+
- trl
|
| 10 |
+
licence: license
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
+
# Model Card for Faqih-R1-14B-Islamic-AI
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
|
| 15 |
+
This model is a fine-tuned version of [unsloth/deepseek-r1-distill-qwen-14b-unsloth-bnb-4bit](https://huggingface.co/unsloth/deepseek-r1-distill-qwen-14b-unsloth-bnb-4bit).
|
| 16 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 17 |
|
| 18 |
+
## Quick start
|
| 19 |
|
| 20 |
```python
|
| 21 |
+
from transformers import pipeline
|
|
|
|
| 22 |
|
| 23 |
+
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 24 |
+
generator = pipeline("text-generation", model="hozifa1/Faqih-R1-14B-Islamic-AI", device="cuda")
|
| 25 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 26 |
+
print(output["generated_text"])
|
| 27 |
+
```
|
| 28 |
|
| 29 |
+
## Training procedure
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
|
| 31 |
+
|
|
|
|
|
|
|
|
|
|
| 32 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
|
| 34 |
+
This model was trained with SFT.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
|
| 36 |
+
### Framework versions
|
|
|
|
|
|
|
| 37 |
|
| 38 |
+
- TRL: 0.24.0
|
| 39 |
+
- Transformers: 5.5.0
|
| 40 |
+
- Pytorch: 2.10.0+cu128
|
| 41 |
+
- Datasets: 4.3.0
|
| 42 |
+
- Tokenizers: 0.22.2
|
| 43 |
|
| 44 |
+
## Citations
|
| 45 |
|
|
|
|
|
|
|
| 46 |
|
|
|
|
| 47 |
|
| 48 |
+
Cite TRL as:
|
| 49 |
+
|
| 50 |
+
```bibtex
|
| 51 |
+
@misc{vonwerra2022trl,
|
| 52 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
| 53 |
+
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
|
| 54 |
+
year = 2020,
|
| 55 |
+
journal = {GitHub repository},
|
| 56 |
+
publisher = {GitHub},
|
| 57 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 58 |
+
}
|
| 59 |
+
```
|
adapter_config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": {
|
| 6 |
+
"base_model_class": "Qwen2ForCausalLM",
|
| 7 |
+
"parent_library": "transformers.models.qwen2.modeling_qwen2",
|
| 8 |
+
"unsloth_fixed": true
|
| 9 |
+
},
|
| 10 |
+
"base_model_name_or_path": "unsloth/deepseek-r1-distill-qwen-14b-unsloth-bnb-4bit",
|
| 11 |
+
"bias": "none",
|
| 12 |
+
"corda_config": null,
|
| 13 |
+
"ensure_weight_tying": false,
|
| 14 |
+
"eva_config": null,
|
| 15 |
+
"exclude_modules": null,
|
| 16 |
+
"fan_in_fan_out": false,
|
| 17 |
+
"inference_mode": true,
|
| 18 |
+
"init_lora_weights": true,
|
| 19 |
+
"layer_replication": null,
|
| 20 |
+
"layers_pattern": null,
|
| 21 |
+
"layers_to_transform": null,
|
| 22 |
+
"loftq_config": {},
|
| 23 |
+
"lora_alpha": 32,
|
| 24 |
+
"lora_bias": false,
|
| 25 |
+
"lora_dropout": 0.05,
|
| 26 |
+
"lora_ga_config": null,
|
| 27 |
+
"megatron_config": null,
|
| 28 |
+
"megatron_core": "megatron.core",
|
| 29 |
+
"modules_to_save": null,
|
| 30 |
+
"peft_type": "LORA",
|
| 31 |
+
"peft_version": "0.19.1",
|
| 32 |
+
"qalora_group_size": 16,
|
| 33 |
+
"r": 16,
|
| 34 |
+
"rank_pattern": {},
|
| 35 |
+
"revision": null,
|
| 36 |
+
"target_modules": [
|
| 37 |
+
"k_proj",
|
| 38 |
+
"v_proj",
|
| 39 |
+
"q_proj",
|
| 40 |
+
"down_proj",
|
| 41 |
+
"gate_proj",
|
| 42 |
+
"o_proj",
|
| 43 |
+
"up_proj"
|
| 44 |
+
],
|
| 45 |
+
"target_parameters": null,
|
| 46 |
+
"task_type": "CAUSAL_LM",
|
| 47 |
+
"trainable_token_indices": null,
|
| 48 |
+
"use_bdlora": null,
|
| 49 |
+
"use_dora": false,
|
| 50 |
+
"use_qalora": false,
|
| 51 |
+
"use_rslora": false
|
| 52 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6e5dbc1af183fb8a90912b87881f12fdb47774d7cc2d1816bb1e56dc825019e
|
| 3 |
+
size 275341720
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
|
| 3 |
+
size 11422778
|
tokenizer_config.json
CHANGED
|
@@ -4,12 +4,192 @@
|
|
| 4 |
"bos_token": "<|begin▁of▁sentence|>",
|
| 5 |
"clean_up_tokenization_spaces": false,
|
| 6 |
"eos_token": "<|end▁of▁sentence|>",
|
|
|
|
| 7 |
"is_local": false,
|
| 8 |
-
"legacy":
|
| 9 |
-
"
|
| 10 |
-
"
|
| 11 |
-
"
|
| 12 |
"sp_model_kwargs": {},
|
| 13 |
-
"tokenizer_class": "
|
| 14 |
-
"unk_token": null
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
}
|
|
|
|
| 4 |
"bos_token": "<|begin▁of▁sentence|>",
|
| 5 |
"clean_up_tokenization_spaces": false,
|
| 6 |
"eos_token": "<|end▁of▁sentence|>",
|
| 7 |
+
"from_slow": true,
|
| 8 |
"is_local": false,
|
| 9 |
+
"legacy": false,
|
| 10 |
+
"model_max_length": 131072,
|
| 11 |
+
"pad_token": "<|vision_pad|>",
|
| 12 |
+
"padding_side": "right",
|
| 13 |
"sp_model_kwargs": {},
|
| 14 |
+
"tokenizer_class": "TokenizersBackend",
|
| 15 |
+
"unk_token": null,
|
| 16 |
+
"use_default_system_prompt": false,
|
| 17 |
+
"added_tokens_decoder": {
|
| 18 |
+
"151643": {
|
| 19 |
+
"content": "<|end▁of▁sentence|>",
|
| 20 |
+
"single_word": false,
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"rstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"special": true
|
| 25 |
+
},
|
| 26 |
+
"151644": {
|
| 27 |
+
"content": "<|User|>",
|
| 28 |
+
"single_word": false,
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"special": false
|
| 33 |
+
},
|
| 34 |
+
"151645": {
|
| 35 |
+
"content": "<|Assistant|>",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": false
|
| 41 |
+
},
|
| 42 |
+
"151646": {
|
| 43 |
+
"content": "<|begin▁of▁sentence|>",
|
| 44 |
+
"single_word": false,
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"rstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"special": true
|
| 49 |
+
},
|
| 50 |
+
"151647": {
|
| 51 |
+
"content": "<|EOT|>",
|
| 52 |
+
"single_word": false,
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"rstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"special": false
|
| 57 |
+
},
|
| 58 |
+
"151648": {
|
| 59 |
+
"content": "<think>",
|
| 60 |
+
"single_word": false,
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"rstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"special": false
|
| 65 |
+
},
|
| 66 |
+
"151649": {
|
| 67 |
+
"content": "</think>",
|
| 68 |
+
"single_word": false,
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"rstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"special": false
|
| 73 |
+
},
|
| 74 |
+
"151650": {
|
| 75 |
+
"content": "<|quad_start|>",
|
| 76 |
+
"single_word": false,
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"rstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"special": true
|
| 81 |
+
},
|
| 82 |
+
"151651": {
|
| 83 |
+
"content": "<|quad_end|>",
|
| 84 |
+
"single_word": false,
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"rstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"special": true
|
| 89 |
+
},
|
| 90 |
+
"151652": {
|
| 91 |
+
"content": "<|vision_start|>",
|
| 92 |
+
"single_word": false,
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"rstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"special": true
|
| 97 |
+
},
|
| 98 |
+
"151653": {
|
| 99 |
+
"content": "<|vision_end|>",
|
| 100 |
+
"single_word": false,
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"rstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"special": true
|
| 105 |
+
},
|
| 106 |
+
"151654": {
|
| 107 |
+
"content": "<|vision_pad|>",
|
| 108 |
+
"single_word": false,
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"rstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"special": true
|
| 113 |
+
},
|
| 114 |
+
"151655": {
|
| 115 |
+
"content": "<|image_pad|>",
|
| 116 |
+
"single_word": false,
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"rstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"special": true
|
| 121 |
+
},
|
| 122 |
+
"151656": {
|
| 123 |
+
"content": "<|video_pad|>",
|
| 124 |
+
"single_word": false,
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"rstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"special": true
|
| 129 |
+
},
|
| 130 |
+
"151657": {
|
| 131 |
+
"content": "<tool_call>",
|
| 132 |
+
"single_word": false,
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"rstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"special": false
|
| 137 |
+
},
|
| 138 |
+
"151658": {
|
| 139 |
+
"content": "</tool_call>",
|
| 140 |
+
"single_word": false,
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"rstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"special": false
|
| 145 |
+
},
|
| 146 |
+
"151659": {
|
| 147 |
+
"content": "<|fim_prefix|>",
|
| 148 |
+
"single_word": false,
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"rstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"special": false
|
| 153 |
+
},
|
| 154 |
+
"151660": {
|
| 155 |
+
"content": "<|fim_middle|>",
|
| 156 |
+
"single_word": false,
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"rstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"special": false
|
| 161 |
+
},
|
| 162 |
+
"151661": {
|
| 163 |
+
"content": "<|fim_suffix|>",
|
| 164 |
+
"single_word": false,
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"rstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"special": false
|
| 169 |
+
},
|
| 170 |
+
"151662": {
|
| 171 |
+
"content": "<|fim_pad|>",
|
| 172 |
+
"single_word": false,
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"rstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"special": false
|
| 177 |
+
},
|
| 178 |
+
"151663": {
|
| 179 |
+
"content": "<|repo_name|>",
|
| 180 |
+
"single_word": false,
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"rstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"special": false
|
| 185 |
+
},
|
| 186 |
+
"151664": {
|
| 187 |
+
"content": "<|file_sep|>",
|
| 188 |
+
"single_word": false,
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"rstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"special": false
|
| 193 |
+
}
|
| 194 |
+
}
|
| 195 |
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2dcb9fd1efebc7c487e99696e7655a5dce1fb979ef93fc72ec06ba1e079f6ebf
|
| 3 |
+
size 5777
|