Upload README.md
Browse files
README.md
CHANGED
|
@@ -24,7 +24,7 @@ We release **AM-Thinking‑v1**, a 32B dense language model focused on enhancing
|
|
| 24 |
Built on Qwen 2.5‑32B‑Base, AM-Thinking‑v1 shows strong performance on reasoning benchmarks, comparable to much larger MoE models like **DeepSeek‑R1**, **Qwen3‑235B‑A22B**, **Seed1.5-Thinking**, and larger dense model like **Nemotron-Ultra-253B-v1**.
|
| 25 |
|
| 26 |
<div style="text-align: center;">
|
| 27 |
-
<img src="assets/benchmark.png" alt="benchmark" style="width: 90%;">
|
| 28 |
</div>
|
| 29 |
|
| 30 |
|
|
@@ -39,8 +39,8 @@ Large Mixture‑of‑Experts (MoE) models such as **DeepSeek‑R1** or **Qwen3
|
|
| 39 |
* **Deploys on one A100‑80 GB** with deterministic latency—no MoE routing overhead.
|
| 40 |
|
| 41 |
<div style="text-align: center;">
|
| 42 |
-
<img src="assets/param-aime2024.jpeg" alt="AIME 2024" style="width: 90%; margin-bottom: 20px;">
|
| 43 |
-
<img src="assets/param-lcb.jpeg" alt="LiveCodeBench" style="width: 90%;">
|
| 44 |
<div style="margin-top: 10px;">
|
| 45 |
<em>AM-Thinking-v1 achieves strong reasoning performance with significantly fewer parameters.</em>
|
| 46 |
</div>
|
|
@@ -56,7 +56,7 @@ PROMPT :
|
|
| 56 |
write a python script for a bouncing red ball within a triangle, make sure to handle collision detection properly. make the triangle slowly rotate. implement it in python. make sure ball stays within the triangle
|
| 57 |
</pre>
|
| 58 |
<div style="text-align: center;">
|
| 59 |
-
<img src="assets/ball.gif" alt="Bouncing Red Ball" width="50%">
|
| 60 |
</div>
|
| 61 |
|
| 62 |
|
|
@@ -64,13 +64,13 @@ write a python script for a bouncing red ball within a triangle, make sure to ha
|
|
| 64 |
|
| 65 |
|
| 66 |
<div style="text-align: center;">
|
| 67 |
-
<img src="assets/diamond.png" alt="diamond" width="90%">
|
| 68 |
</div>
|
| 69 |
|
| 70 |
|
| 71 |
### 3) Writing
|
| 72 |
<div style="text-align: center;">
|
| 73 |
-
<img src="assets/writing.png" alt="sushi" width="90%">
|
| 74 |
</div>
|
| 75 |
|
| 76 |
|
|
|
|
| 24 |
Built on Qwen 2.5‑32B‑Base, AM-Thinking‑v1 shows strong performance on reasoning benchmarks, comparable to much larger MoE models like **DeepSeek‑R1**, **Qwen3‑235B‑A22B**, **Seed1.5-Thinking**, and larger dense model like **Nemotron-Ultra-253B-v1**.
|
| 25 |
|
| 26 |
<div style="text-align: center;">
|
| 27 |
+
<img src="https://huggingface.co/a-m-team/AM-Thinking-v1/blob/main/assets/benchmark.png" alt="benchmark" style="width: 90%;">
|
| 28 |
</div>
|
| 29 |
|
| 30 |
|
|
|
|
| 39 |
* **Deploys on one A100‑80 GB** with deterministic latency—no MoE routing overhead.
|
| 40 |
|
| 41 |
<div style="text-align: center;">
|
| 42 |
+
<img src="https://huggingface.co/a-m-team/AM-Thinking-v1/blob/main/assets/param-aime2024.jpeg" alt="AIME 2024" style="width: 90%; margin-bottom: 20px;">
|
| 43 |
+
<img src="https://huggingface.co/a-m-team/AM-Thinking-v1/blob/main/assets/param-lcb.jpeg" alt="LiveCodeBench" style="width: 90%;">
|
| 44 |
<div style="margin-top: 10px;">
|
| 45 |
<em>AM-Thinking-v1 achieves strong reasoning performance with significantly fewer parameters.</em>
|
| 46 |
</div>
|
|
|
|
| 56 |
write a python script for a bouncing red ball within a triangle, make sure to handle collision detection properly. make the triangle slowly rotate. implement it in python. make sure ball stays within the triangle
|
| 57 |
</pre>
|
| 58 |
<div style="text-align: center;">
|
| 59 |
+
<img src="https://huggingface.co/a-m-team/AM-Thinking-v1/blob/main/assets/ball.gif" alt="Bouncing Red Ball" width="50%">
|
| 60 |
</div>
|
| 61 |
|
| 62 |
|
|
|
|
| 64 |
|
| 65 |
|
| 66 |
<div style="text-align: center;">
|
| 67 |
+
<img src="https://huggingface.co/a-m-team/AM-Thinking-v1/blob/main/assets/diamond.png" alt="diamond" width="90%">
|
| 68 |
</div>
|
| 69 |
|
| 70 |
|
| 71 |
### 3) Writing
|
| 72 |
<div style="text-align: center;">
|
| 73 |
+
<img src="https://huggingface.co/a-m-team/AM-Thinking-v1/blob/main/assets/writing.png" alt="sushi" width="90%">
|
| 74 |
</div>
|
| 75 |
|
| 76 |
|