deepanshupillm commited on
Commit
189fbed
·
verified ·
1 Parent(s): 66ba835

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -33
README.md CHANGED
@@ -39,26 +39,7 @@ tags:
39
  <p><b>A 9B open-weight vision-language model for reasoning, coding, and multimodal understanding.</b></p>
40
 
41
  <p>
42
- <a href="https://huggingface.co/169Pi/Alpie_seed"><img src="https://img.shields.io/badge/🤗_Model-Alpie_Seed_9B-FFD21E?style=for-the-badge&labelColor=1a1a2e" alt="Model"></a>
43
  <a href="https://huggingface.co/169Pi/Alpie_Seed_GGUF"><img src="https://img.shields.io/badge/📦_GGUF-2/3/4--bit-7C3AED?style=for-the-badge&labelColor=1a1a2e" alt="GGUF"></a>
44
- <a href="https://ollama.com/169pi/alpie-core"><img src="https://img.shields.io/badge/🦙_Ollama-169pi/alpie--core-00C2A8?style=for-the-badge&labelColor=1a1a2e" alt="Ollama"></a>
45
- </p>
46
-
47
- <p>
48
- <img src="https://img.shields.io/badge/License-Apache_2.0-22C55E?style=flat-square" alt="license">
49
- <img src="https://img.shields.io/badge/Params-9B-6366F1?style=flat-square" alt="params">
50
- <img src="https://img.shields.io/badge/Context-262K-F59E0B?style=flat-square" alt="context">
51
- <img src="https://img.shields.io/badge/Modality-Text_·_Image_·_Video-EC4899?style=flat-square" alt="modality">
52
- <img src="https://img.shields.io/badge/Base-Qwen3.5--9B-0EA5E9?style=flat-square" alt="base">
53
- </p>
54
-
55
- <p>
56
- <a href="https://github.com/169Pi"><img src="https://img.shields.io/badge/GitHub-169Pi-181717?style=flat-square&logo=github" alt="GitHub"></a>
57
- <a href="https://www.linkedin.com/company/169pi"><img src="https://img.shields.io/badge/LinkedIn-169pi-0A66C2?style=flat-square&logo=linkedin&logoColor=white" alt="LinkedIn"></a>
58
- <a href="https://www.instagram.com/169pi.ai/"><img src="https://img.shields.io/badge/Instagram-169pi.ai-E4405F?style=flat-square&logo=instagram&logoColor=white" alt="Instagram"></a>
59
- <a href="https://www.youtube.com/@169pi"><img src="https://img.shields.io/badge/YouTube-@169pi-FF0000?style=flat-square&logo=youtube&logoColor=white" alt="YouTube"></a>
60
- <a href="https://x.com/169Pi_ai"><img src="https://img.shields.io/badge/X-@169Pi__ai-000000?style=flat-square&logo=x&logoColor=white" alt="X"></a>
61
- <a href="https://ollama.com/169pi/alpie-core"><img src="https://img.shields.io/badge/Ollama-169pi-FFFFFF?style=flat-square&logo=ollama&logoColor=black" alt="Ollama"></a>
62
  </p>
63
 
64
  </div>
@@ -143,7 +124,6 @@ Training used eight NVIDIA H100 GPUs, with 3,034 GRPO steps across five phases.
143
  | **Coding & Software Engineering** | | | | | | | |
144
  | LiveCodeBench v6 | 65.6 | 72.0 | 61.6 | 61.0 | 70.0 | -- | ![72.99](https://img.shields.io/badge/72.99-F59E0B?style=flat-square) 🏆 |
145
  | SWE-Bench Verified | 60.0 | 52.0 | -- | 60.7 | 34.0 | 51.56 | ![61.20](https://img.shields.io/badge/61.20-F59E0B?style=flat-square) 🏆 |
146
- | **🏆 Rows won** | 0 | 0 | 0 | 0 | 1 | 0 | ![6](https://img.shields.io/badge/6-F59E0B?style=flat-square) 🏆 |
147
 
148
  ### 👁️ Vision Language
149
 
@@ -158,10 +138,9 @@ Training used eight NVIDIA H100 GPUs, with 3,034 GRPO steps across five phases.
158
  | HallusionBench | 58.4 | 64.5 | 66.0 | 69.3 | -- | ![79.88](https://img.shields.io/badge/79.88-F59E0B?style=flat-square) 🏆 |
159
  | **Text Recognition and Document Understanding** | | | | | | |
160
  | OCRBench | 75.3 | 82.5 | 83.9 | 89.2 | -- | ![90.30](https://img.shields.io/badge/90.30-F59E0B?style=flat-square) 🏆 |
161
- | **🏆 Rows won** | 0 | 0 | 0 | 2 | 1 | ![3](https://img.shields.io/badge/3-F59E0B?style=flat-square) 🏆 |
162
 
163
  * SWE-Bench Verified: resolved rate using Mini-SWE-agent, with retries disabled.
164
- * Comparison-model scores were not re-run by 169Pi, and harnesses, prompts, and benchmark versions differ, so cross-model comparisons are indicative rather than strictly like-for-like. "Rows won" counts only rows where at least two models have a score. Scores vary with dataset versions, prompts, evaluation harnesses, and inference settings.
165
  * Empty cells (--) indicate scores not yet available or not applicable.
166
  * MMLU for GPT-OSS-20B is from OpenAI's model card (high reasoning); MMLU for Sarvam-30B and Math-500 for Sarvam-30B and GPT-OSS-20B are from Sarvam's release comparison. Qwen3.5-9B AIME 2026 is from a third-party evaluation.
167
 
@@ -191,6 +170,10 @@ Alpie Seed is intended for research, development, and general-purpose applicatio
191
  - Quantization may affect quality, speed, and memory differently across hardware.
192
  - Not a substitute for professional judgment; do not use as the sole basis for medical, legal, financial, or other high-impact decisions.
193
 
 
 
 
 
194
  ## Citation
195
 
196
  ```bibtex
@@ -200,14 +183,4 @@ Alpie Seed is intended for research, development, and general-purpose applicatio
200
  year = {2026},
201
  howpublished = {\url{https://huggingface.co/169Pi/Alpie_seed}}
202
  }
203
- ```
204
-
205
- ## License
206
-
207
- Apache License 2.0. Users are responsible for ensuring their use and deployment comply with applicable laws and regulations.
208
-
209
- <div align="center">
210
-
211
- **Developed by 169Pi AI** 🌱 · [GitHub](https://github.com/169Pi) · [LinkedIn](https://www.linkedin.com/company/169pi) · [Instagram](https://www.instagram.com/169pi.ai/) · [YouTube](https://www.youtube.com/@169pi) · [X](https://x.com/169Pi_ai) · [Ollama](https://ollama.com/169pi/alpie-core)
212
-
213
- </div>
 
39
  <p><b>A 9B open-weight vision-language model for reasoning, coding, and multimodal understanding.</b></p>
40
 
41
  <p>
 
42
  <a href="https://huggingface.co/169Pi/Alpie_Seed_GGUF"><img src="https://img.shields.io/badge/📦_GGUF-2/3/4--bit-7C3AED?style=for-the-badge&labelColor=1a1a2e" alt="GGUF"></a>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
  </p>
44
 
45
  </div>
 
124
  | **Coding & Software Engineering** | | | | | | | |
125
  | LiveCodeBench v6 | 65.6 | 72.0 | 61.6 | 61.0 | 70.0 | -- | ![72.99](https://img.shields.io/badge/72.99-F59E0B?style=flat-square) 🏆 |
126
  | SWE-Bench Verified | 60.0 | 52.0 | -- | 60.7 | 34.0 | 51.56 | ![61.20](https://img.shields.io/badge/61.20-F59E0B?style=flat-square) 🏆 |
 
127
 
128
  ### 👁️ Vision Language
129
 
 
138
  | HallusionBench | 58.4 | 64.5 | 66.0 | 69.3 | -- | ![79.88](https://img.shields.io/badge/79.88-F59E0B?style=flat-square) 🏆 |
139
  | **Text Recognition and Document Understanding** | | | | | | |
140
  | OCRBench | 75.3 | 82.5 | 83.9 | 89.2 | -- | ![90.30](https://img.shields.io/badge/90.30-F59E0B?style=flat-square) 🏆 |
 
141
 
142
  * SWE-Bench Verified: resolved rate using Mini-SWE-agent, with retries disabled.
143
+ * Comparison-model scores were not re-run by 169Pi, and harnesses, prompts, and benchmark versions differ, so cross-model comparisons are indicative rather than strictly like-for-like. Scores vary with dataset versions, prompts, evaluation harnesses, and inference settings.
144
  * Empty cells (--) indicate scores not yet available or not applicable.
145
  * MMLU for GPT-OSS-20B is from OpenAI's model card (high reasoning); MMLU for Sarvam-30B and Math-500 for Sarvam-30B and GPT-OSS-20B are from Sarvam's release comparison. Qwen3.5-9B AIME 2026 is from a third-party evaluation.
146
 
 
170
  - Quantization may affect quality, speed, and memory differently across hardware.
171
  - Not a substitute for professional judgment; do not use as the sole basis for medical, legal, financial, or other high-impact decisions.
172
 
173
+ ## License
174
+
175
+ Apache License 2.0. Users are responsible for ensuring their use and deployment comply with applicable laws and regulations.
176
+
177
  ## Citation
178
 
179
  ```bibtex
 
183
  year = {2026},
184
  howpublished = {\url{https://huggingface.co/169Pi/Alpie_seed}}
185
  }
186
+ ```