初始化项目，由ModelHub XC社区提供模型

Model: Mungert/Aryabhata-1.0-GGUF Source: Original Platform
2026-10-13 22:14:13 +08:00
commit 288955dc30
35 changed files with 499 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,79 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+ 
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+Aryabhata-1.0-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-iq1_s.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-iq1_m.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-iq2_s.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-q2_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-tq2_0.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-f16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-q2_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-iq2_m.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-iq2_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-iq2_xs.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-tq1_0.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-bf16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0.imatrix filter=lfs diff=lfs merge=lfs -text
+Aryabhata-1.0-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
--- a/Aryabhata-1.0-bf16.gguf
+++ b/Aryabhata-1.0-bf16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2085e8140dc6411c1c6e638a695bf28d73795952c2d66918e697777fe911b830
+size 15237854048
--- a/Aryabhata-1.0-bf16_q8_0.gguf
+++ b/Aryabhata-1.0-bf16_q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d42080a958fdf05e177fc5c14355fcc8d080f78042c5fc71d07e7c52cd0905
+size 11287999328
--- a/Aryabhata-1.0-f16_q8_0.gguf
+++ b/Aryabhata-1.0-f16_q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9abd5d6a82243b11e17beca3addbb1c7b192d76b4dd8312397e3d74e146e465f
+size 11287999328
--- a/Aryabhata-1.0-iq1_m.gguf
+++ b/Aryabhata-1.0-iq1_m.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee51a635667e014150d82f515c66533ffe58af3421c9d0efe230969cd3bde7f2
+size 2581804192
--- a/Aryabhata-1.0-iq1_s.gguf
+++ b/Aryabhata-1.0-iq1_s.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:402178f1aa65b8b47f9b1c6c02bca97fe87e18aae262f786670ec73dc6bfc0bd
+size 2414402720
--- a/Aryabhata-1.0-iq2_m.gguf
+++ b/Aryabhata-1.0-iq2_m.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10110086cd2139b139865a3dad87ff94a34b08b4598200c0f3a453dedcb69798
+size 3059565728
--- a/Aryabhata-1.0-iq2_s.gguf
+++ b/Aryabhata-1.0-iq2_s.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd2482e570f541bad919e4f3dfaed7fa20598feba5bb6ef7a31fb9e4ab0c18bc
+size 2933408928
--- a/Aryabhata-1.0-iq2_xs.gguf
+++ b/Aryabhata-1.0-iq2_xs.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed6e4d5a52bf6416a47206fa230ebba571f4b484379e9cf807136f796acfb525
+size 2849141920
--- a/Aryabhata-1.0-iq2_xxs.gguf
+++ b/Aryabhata-1.0-iq2_xxs.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1e280640e50fc1b8f1d2b6c4af84a0c3c31f9c533680ad842bbd4919852d2bd
+size 2652036256
--- a/Aryabhata-1.0-iq3_m.gguf
+++ b/Aryabhata-1.0-iq3_m.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26871e83dfe785d405d9304f6e6976e496e3845dae4c9c5ac5a58ae82dd82942
+size 3820893344
--- a/Aryabhata-1.0-iq3_s.gguf
+++ b/Aryabhata-1.0-iq3_s.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:058b9e2d2cd1f7acf0ad9316a72df57713ec44ada07a02c5822bffbc16c5b243
+size 3780953248
--- a/Aryabhata-1.0-iq3_xs.gguf
+++ b/Aryabhata-1.0-iq3_xs.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e257a2e884233153b9e694be02da6ea99469afceaf7397ae49e50a67a86e6dc4
+size 3455755424
--- a/Aryabhata-1.0-iq3_xxs.gguf
+++ b/Aryabhata-1.0-iq3_xxs.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36c70a3df77168754cc58b8256aadfe2feec3a4cc3bd6feb6d7a4b582496369d
+size 3385509024
--- a/Aryabhata-1.0-iq4_nl.gguf
+++ b/Aryabhata-1.0-iq4_nl.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8b53a76b2ccb5e115a8b0832a7e0c6e465e3667284895575addf7c1d8775fd2
+size 4437814432
--- a/Aryabhata-1.0-iq4_xs.gguf
+++ b/Aryabhata-1.0-iq4_xs.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6ed12207ed91a8272a69878d010ad87547b070d77bf0fcc24e87eaaee626b1b
+size 4218473632
--- a/Aryabhata-1.0-q2_k_m.gguf
+++ b/Aryabhata-1.0-q2_k_m.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1dd7f00acbf3efa00e9486f917f43d1e490488a77b52a421dcfd6f8b2efccc2
+size 3284182176
--- a/Aryabhata-1.0-q2_k_s.gguf
+++ b/Aryabhata-1.0-q2_k_s.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0db260e263e0ab535397ac3b0d7562c913b74cf13e027a87debca3c5d478f3a
+size 3137768608
--- a/Aryabhata-1.0-q3_k_m.gguf
+++ b/Aryabhata-1.0-q3_k_m.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a9c5fc8b9e1e4f1934ed6b562df9040662af721ea599375b155b575d8418092
+size 4021281952
--- a/Aryabhata-1.0-q3_k_s.gguf
+++ b/Aryabhata-1.0-q3_k_s.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21ee036b834f78e3212a5759ef5d1756fa4a9bc68452592f1087d101934a4ca3
+size 3858740384
--- a/Aryabhata-1.0-q4_0.gguf
+++ b/Aryabhata-1.0-q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:768abe1bf6033db27c6a50b7139cf3aa388ae04fc0801341f560b44822b9b16f
+size 4290884768
--- a/Aryabhata-1.0-q4_1.gguf
+++ b/Aryabhata-1.0-q4_1.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5232cb8b18765621de3b42b3700dd1960a0a4b23dcf21d264c99b289bdab60f
+size 4766839968
--- a/Aryabhata-1.0-q4_k_m.gguf
+++ b/Aryabhata-1.0-q4_k_m.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcd601a694e3fe06a199c2f8f1fec10ee98aad9f6041272011a91ccea8edae09
+size 4833215648
--- a/Aryabhata-1.0-q4_k_s.gguf
+++ b/Aryabhata-1.0-q4_k_s.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cffcc17069625e2e7c947ef2b527cf29fc8730419423fe997708df70fe277eca
+size 4634059936
--- a/Aryabhata-1.0-q5_0.gguf
+++ b/Aryabhata-1.0-q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51f62a282104b1bb5f413f99b4c23fdf507d996d59f36cafb89e1e8ad1fc41aa
+size 5242795168
--- a/Aryabhata-1.0-q5_1.gguf
+++ b/Aryabhata-1.0-q5_1.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ee4959421e1c0e36c76097b84fc30ad93e0f1efe058480dd4d12197fce249c8
+size 5718750368
--- a/Aryabhata-1.0-q5_k_m.gguf
+++ b/Aryabhata-1.0-q5_k_m.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15ab9165cdf25d4294e002305dd2a2ce4af9c9a62e7253ed04a11b24e30e513e
+size 5527450784
--- a/Aryabhata-1.0-q5_k_s.gguf
+++ b/Aryabhata-1.0-q5_k_s.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54a990bcee6f8c3b515b2ddfa21a25c0a1d72db2cf3d19a26137fd6fc5700d2b
+size 5453362336
--- a/Aryabhata-1.0-q6_k_m.gguf
+++ b/Aryabhata-1.0-q6_k_m.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85f056d25720c7ca5aac9f06e706bdbb0ba87f7a008a834787f227e226ce13dd
+size 6254199968
--- a/Aryabhata-1.0-q8_0.gguf
+++ b/Aryabhata-1.0-q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c1282d38c78984245b4e2bb4ac5c5c567d8856c74560f2e6d439a59e2838a22
+size 8098526048
--- a/Aryabhata-1.0-tq1_0.gguf
+++ b/Aryabhata-1.0-tq1_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:720783fade2029d84ac06d9597e6fd51177e1a6fb24e43f59dba69ff39bbc8dd
+size 2137345184
--- a/Aryabhata-1.0-tq2_0.gguf
+++ b/Aryabhata-1.0-tq2_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdb4947201c2c4a1718393c20a35cadd9bd88112e5646118be199e07dbd735eb
+size 2443218080
--- a/Aryabhata-1.0.imatrix
+++ b/Aryabhata-1.0.imatrix
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:326f0f726c28734e1e466f451a4211eea3dc6b8033249c4689de7d955f98ef30
+size 4536712
--- a/README.md
+++ b/README.md
@@ -0,0 +1,323 @@
+---
+license: apache-2.0
+tags:
+- small-language-model
+- jee
+- exam-centric
+- indian-education
+- reinforcement-learning
+- supervised-finetuning
+- model-merging
+- rejection-sampling
+- mathematics
+- ai4education
+- physicswallah
+language:
+- en
+model_name: PhysicsWallah/Aryabhata-1.0
+model_creator: Physics Wallah AI Research
+model_type: Causal decoder-based model
+base_model: Qwen/Qwen2.5-Math-7B
+pipeline_tag: text-generation
+---
+
+# <span style="color: #7FFF7F;">Aryabhata-1.0 GGUF Models</span>
+
+
+## <span style="color: #7F7FFF;">Model Generation Details</span>
+
+This model was generated using [llama.cpp](https://github.com/ggerganov/llama.cpp) at commit [`221c0e0c`](https://github.com/ggerganov/llama.cpp/commit/221c0e0c5841a814e95b9bfd549de9d6ae00ac6e).
+
+
+
+
+
+---
+
+## <span style="color: #7FFF7F;">Quantization Beyond the IMatrix</span>
+
+I've been experimenting with a new quantization approach that selectively elevates the precision of key layers beyond what the default IMatrix configuration provides.
+
+In my testing, standard IMatrix quantization underperforms at lower bit depths, especially with Mixture of Experts (MoE) models. To address this, I'm using the `--tensor-type` option in `llama.cpp` to manually "bump" important layers to higher precision. You can see the implementation here:  
+👉 [Layer bumping with llama.cpp](https://github.com/Mungert69/GGUFModelBuilder/blob/main/model-converter/tensor_list_builder.py)
+
+While this does increase model file size, it significantly improves precision for a given quantization level.
+
+### **I'd love your feedback—have you tried this? How does it perform for you?**
+
+
+
+
+---
+
+<a href="https://readyforquantum.com/huggingface_gguf_selection_guide.html" style="color: #7FFF7F;">
+  Click here to get info on choosing the right GGUF model format
+</a>
+
+---
+
+
+
+<!--Begin Original Model Card-->
+
+
+# Aryabhatta 1.0 : An exam-focused language model for JEE Math
+
+![](benchmark.png)
+
+## Overview
+
+**Aryabhata 1.0** is a 7B parameter small language model for mathematics developed by **Physics Wallah AI Research**, optimized for high-stakes Indian competitive exams like **JEE Mains**. Despite its compact size, Aryabhata 1.0 achieves **state-of-the-art performance** on exam-centric reasoning tasks with impressive **token efficiency** and low inference cost.
+
+
+> 🚧 *Aryabhata 1.0 is an **experimental release**. We are actively seeking feedback — please contribute in the Discussion tab of this repo.*
+---
+
+## 🧠 Key Features
+
+- **Architecture**: 7B parameter causal decoder-based model.
+- **Exam-Centric Optimization**: Specifically tuned for JEE-level Mathematics reasoning.
+- **High Accuracy**:
+  - **86%** on **JEE Mains January 2025** session.
+  - **90.2%** on **JEE Mains April 2025** session.
+- **Token Efficiency**: Operates effectively around a **~2K token window**, compared to ~8K required by other reasoning models.
+- **Compute Efficient**: Trained on a **1x2 NVIDIA H100 GPU** using optimized pipeline.
+
+---
+
+## 🛠️ Training Details
+
+- **Training Data**: ~130K problem-solution pairs curated from proprietary Physics Wallah exam datasets.
+- **Training Pipeline**:
+  - **Model Merging**
+  - **Rejection Sampling**
+  - **Supervised Fine-Tuning (SFT)**
+  - **Reinforcement Learning with Verifiable Rewards (RLVR)**
+
+### 🔀 Model Merging
+We began with model merging (Weighted average) to build a strong initialization (Aryabhata 0.5) by combining diverse model capabilities:
+* Qwen 2.5 Math: A robust math-centric LLM with solid symbolic math foundations.
+* Ace Math: An enhanced version of Qwen 2.5 Math, fine-tuned by NVIDIA for improved accuracy in mathematics benchmarks.
+* DeepSeek R1 Distill Qwen: A long-form reasoning model, fine-tuned on reasoning traces distilled from DeepSeek R1.
+
+### 📚 Data Curation + Rejection Sampling
+We extracted ~250K raw questions from Physics Wallah's internal database and applied aggressive filtering and cleaning:
+* Removed: diagram-based, non-English, and option-heavy questions.
+* Kept: questions matching the distribution of JEE Main 2019–2024.
+Final curated dataset: ~130K high-quality questions.
+
+For each question:
+* Generated 4 CoTs using Aryabhata 0.5.
+* Retained only those leading to correct final answers.
+
+Resulting Dataset:
+* ~100K questions
+* ~350K high-quality CoTs
+
+We used this dataset for SFT.
+
+### 🎯 Reinforcement Learning with Verifiable Rewards (RLVR)
+We used a custom in-house variant of Group Relative Policy Optimization (GRPO), adapted for math-specific reward functions.
+* Removed KL-divergence penalty
+* Removed clipping
+
+We used RLVR on the remaining ~30K questions.
+
+This multi-phase training strategy allows Aryabhata 1.0 to capture **pedagogy-aligned reasoning patterns**, making it highly effective for solving real student queries in mathematics.
+
+---
+
+## 📊 Performance Highlights
+
+### Evaluation Setup
+All evaluations were performed with temperature = 0.0, and we report pass@1 accuracy.
+
+#### Evaluation Datasets
+We evaluated the model on two sets of official JEE Mains 2025 mathematics papers:
+* January Session: 10 question papers containing 250 questions.
+* April Session: 9 question papers containing 225 questions.
+
+Each paper includes a mix of:
+* Multiple Choice Questions (MCQs) with one correct option
+* Numeric Answer Type (NAT) questions requiring precise numerical responses
+
+#### Evaluation Metric
+We used a composite evaluation metric to reflect real-world grading rigor and reduce false positives:
+
+1. Float Match
+  * Compares predicted and target answers within a tolerance (±1e-9)
+  * Handles rounding artifacts and small numerical errors robustly
+2. String Match
+  * Used for symbolic answers (e.g., fractions, radicals)
+  * Uses strict exact match — predictions must match ground truth character-for-character
+3. LLM-as-Judge (GPT-4o-mini)
+  * Used for Mathematical equivalence for ambiguous formats
+
+### 🔹 Accuracy Comparison Across Models
+![](accuracy.png)
+> *Aryabhata has the best accuracy on JEE Main Maths, on par with frontier models*
+
+### 🔹 Accuracy vs Token Usage
+![](accuracy-vs-token.png)
+> *Aryabhata is on par with frontier models in terms of accuracy vs token usage*
+
+---
+
+## 🔧 Intended Use
+
+**Primary Use Cases**:
+- Competitive exam preparation (JEE Main level mathematics problems)
+- Question answering and doubt-solving systems
+- Educational tutoring and concept explanation
+
+
+## 💡 How to Use
+
+### 🧪 Using with 🤗 Transformers
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
+
+model_id = "PhysicsWallahAI/Aryabhata-1.0"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+
+# Define stop strings
+stop_strings = ["<|im_end|>", "<|end|>", "<im_start|>", "⁠```python\n", "⁠<|im_start|>", "]}}]}}]"]
+
+def strip_bad_tokens(s, stop_strings):
+    for suffix in stop_strings:
+        if s.endswith(suffix):
+            return s[:-len(suffix)]
+    return s
+
+
+# Create generation config (can also set temperature, top_p, etc.)
+generation_config = GenerationConfig(
+    max_new_tokens=4096,
+    stop_strings = stop_strings
+)
+
+query = 'Find all the values of \\sqrt[3]{1}'
+messages = [{'role': 'system', 'content': 'Think step-by-step; put only the final answer inside \\boxed{}.'},
+            {'role': 'user', 'content': query}]
+
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+inputs = tokenizer([text], return_tensors="pt")
+outputs = model.generate(**inputs, generation_config=generation_config, tokenizer=tokenizer)
+
+print(strip_bad_tokens(tokenizer.decode(outputs[0], skip_special_tokens=True), stop_strings))
+````
+
+---
+
+### ⚡ Using with vLLM
+
+To run the model efficiently using vLLM:
+
+```python
+from vllm import LLM, SamplingParams
+
+# Initialize model (downloads from Hugging Face if not local)
+llm = LLM(model="PhysicsWallahAI/Aryabhata-1.0")
+
+# Define prompt and sampling configuration
+query = 'Find all the values of \\sqrt[3]{1}'
+messages = [{'role': 'system', 'content': 'Think step-by-step; put only the final answer inside \\boxed{}.'},
+            {'role': 'user', 'content': query}]
+sampling_params = SamplingParams(temperature=0.0, max_tokens=4*1024, stop=["<|im_end|>", "<|end|>", "<im_start|>", "⁠```python\n", "⁠<|im_start|>", "]}}]}}]"])
+
+# Run inference
+results = llm.chat(messages, sampling_params)
+
+# Print result
+print(results[0].outputs[0].text.strip())
+```
+
+---
+
+## 🚀 Roadmap
+
+**Aryabhata 2.0** (Upcoming):
+- Extending domain coverage to **Physics** and **Chemistry**
+- Supporting **JEE Advanced**, **NEET**, and **Foundation syllabus**
+- Further optimization for affordability and accuracy in real-time deployments
+
+---
+
+## 🤝 Citation
+
+If you use this model, please cite:
+
+```bibtex
+@misc{Aryabhata2025,
+  title = {Aryabhata 1.0: A compact, exam-focused language model tailored for mathematics in Indian competitive exams, especially JEE Main.},
+  author = {Physics Wallah AI Research},
+  year = {2025},
+  note = {\url{https://huggingface.co/PhysicsWallahAI/Aryabhata-1.0}},
+}
+
+<!--End Original Model Card-->
+
+---
+
+# <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span>
+
+Help me test my **AI-Powered Quantum Network Monitor Assistant** with **quantum-ready security checks**:  
+
+👉 [Quantum Network Monitor](https://readyforquantum.com/?assistant=open&utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme)  
+
+
+The full Open Source Code for the Quantum Network Monitor Service available at my github repos ( repos with NetworkMonitor in the name) : [Source Code Quantum Network Monitor](https://github.com/Mungert69). You will also find the code I use to quantize the models if you want to do it yourself [GGUFModelBuilder](https://github.com/Mungert69/GGUFModelBuilder)
+
+💬 **How to test**:  
+ Choose an **AI assistant type**:  
+   - `TurboLLM` (GPT-4.1-mini)  
+   - `HugLLM` (Hugginface Open-source models)  
+   - `TestLLM` (Experimental CPU-only)  
+
+### **What I’m Testing**  
+I’m pushing the limits of **small open-source models for AI network monitoring**, specifically:  
+- **Function calling** against live network services  
+- **How small can a model go** while still handling:  
+  - Automated **Nmap security scans**  
+  - **Quantum-readiness checks**  
+  - **Network Monitoring tasks**  
+
+🟡 **TestLLM** – Current experimental model (llama.cpp on 2 CPU threads on huggingface docker space):  
+- ✅ **Zero-configuration setup**  
+- ⏳ 30s load time (slow inference but **no API costs**) . No token limited as the cost is low.
+- 🔧 **Help wanted!** If you’re into **edge-device AI**, let’s collaborate!  
+
+### **Other Assistants**  
+🟢 **TurboLLM** – Uses **gpt-4.1-mini** :
+- **It performs very well but unfortunatly OpenAI charges per token. For this reason tokens usage is limited. 
+- **Create custom cmd processors to run .net code on Quantum Network Monitor Agents**
+- **Real-time network diagnostics and monitoring**
+- **Security Audits**
+- **Penetration testing** (Nmap/Metasploit)  
+
+🔵 **HugLLM** – Latest Open-source models:  
+- 🌐 Runs on Hugging Face Inference API. Performs pretty well using the lastest models hosted on Novita.
+
+### 💡 **Example commands you could test**:  
+1. `"Give me info on my websites SSL certificate"`  
+2. `"Check if my server is using quantum safe encyption for communication"`  
+3. `"Run a comprehensive security audit on my server"`
+4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a [Quantum Network Monitor Agent](https://readyforquantum.com/Download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) to run the .net code on. This is a very flexible and powerful feature. Use with caution!
+
+### Final Word
+
+I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is [open source](https://github.com/Mungert69). Feel free to use whatever you find helpful.
+
+If you appreciate the work, please consider [buying me a coffee](https://www.buymeacoffee.com/mahadeva) ☕. Your support helps cover service costs and allows me to raise token limits for everyone.
+
+I'm also open to job opportunities or sponsorship.
+
+Thank you! 😊
--- a/configuration.json
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
				`@@ -0,0 +1 @@`
				`{"framework": "pytorch", "task": "text-generation", "allow_remote": true}`