qingpei nielsr HF Staff commited on
Commit
cb8436d
·
verified ·
1 Parent(s): e368e29

Add pipeline tag and library name (#2)

Browse files

- Add pipeline tag and library name (f0575ca2bc1ace3b44cc54d0c273609e54e22044)


Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +20 -9
README.md CHANGED
@@ -1,7 +1,9 @@
1
  ---
2
- license: mit
3
  base_model:
4
  - inclusionAI/Ling-lite
 
 
 
5
  ---
6
 
7
  # Ming-Lite-Omni
@@ -115,7 +117,7 @@ Note: All models are evaluated based on 128 uniformly sampled frames.
115
  <div align="center">
116
 
117
  | Model | aishell1 | aishell2_android | aishell2_ios | cv15_zh | fleurs_zh | wenetspeech_meeting | wenetspeech_net | librispeech_test_clean | librispeech_test_other | multilingual_librispeech | cv15_en | fleurs_en | voxpopuli_v1.0_en |
118
- |:--------------:|:--------:|:----------------:|:------------:|:--------:|:---------:|:-------------------:|:---------------:|:----------------------:|:----------------------:|:------------------------:|:--------:|:---------:|:--------------------:|
119
  | Ming-lite-omni | 1.47 | **2.55** | **2.52** | 6.31 | 2.96 | 5.95 | 5.46 | 1.44 | 2.80 | **4.15** | **6.89** | **3.39** | **5.80** |
120
  | Qwen2.-Omni | 1.18 | 2.75 | 2.63 | **5.20** | 3.00 | **5.90** | 7.70 | 1.80 | 3.40 | 7.56 | 7.60 | 4.10 | **5.80** |
121
  | Qwen2-Audio | 1.53 | 2.92 | 2.92 | 6.90 | 7.50 | 7.16 | 8.42 | 1.60 | 3.60 | 5.40 | 8.60 | 6.90 | 6.84 |
@@ -200,8 +202,6 @@ If you're in mainland China, we strongly recommend you to download our model fro
200
  Additional demonstration cases are available on our project [page](https://lucaria-academy.github.io/Ming-Omni/).
201
 
202
 
203
-
204
-
205
  ## Example Usage
206
 
207
  Please download our model following [Model Downloads](#model-downloads), then you can refer to the following codes to run Ming-lite-omni model.
@@ -275,19 +275,31 @@ messages = [
275
  To enable thinking before response, adding the following system prompt before your question:
276
 
277
  ```python
278
- cot_prompt = "SYSTEM: You are a helpful assistant. When the user asks a question, your response must include two parts: first, the reasoning process enclosed in <thinking>...</thinking> tags, then the final answer enclosed in <answer>...</answer> tags. The critical answer or key result should be placed within \\boxed{}.\n"
 
279
  # And your input message should be like this:
280
  messages = [
281
  {
282
  "role": "HUMAN",
283
  "content": [
284
  {"type": "image", "image": os.path.join(assets_path, "reasoning.png")},
285
- {"type": "text", "text": cot_prompt + "In the rectangle $A B C D$ pictured, $M_{1}$ is the midpoint of $D C, M_{2}$ the midpoint of $A M_{1}, M_{3}$ the midpoint of $B M_{2}$ and $M_{4}$ the midpoint of $C M_{3}$. Determine the ratio of the area of the quadrilateral $M_{1} M_{2} M_{3} M_{4}$ to the area of the rectangle $A B C D$.\nChoices:\n(A) $\frac{7}{16}$\n(B) $\frac{3}{16}$\n(C) $\frac{7}{32}$\n(D) $\frac{9}{32}$\n(E) $\frac{1}{5}$"},
 
 
 
 
 
 
286
  ],
287
  },
288
  ]
289
  # Output:
290
- # \<think\>\nOkay, so I have this problem about a rectangle ABCD ... (thinking process omitted) ... So, the correct answer is C.\n\</think\>\n\<answer\>\\boxed{C}\</answer\>\n\n
 
 
 
 
 
291
  ```
292
 
293
  ```python
@@ -547,5 +559,4 @@ If you find our work helpful, feel free to give us a cite.
547
  archivePrefix = {arXiv},
548
  url = {https://arxiv.org/abs/2506.09344}
549
  }
550
- ```
551
-
 
1
  ---
 
2
  base_model:
3
  - inclusionAI/Ling-lite
4
+ license: mit
5
+ pipeline_tag: any-to-any
6
+ library_name: transformers
7
  ---
8
 
9
  # Ming-Lite-Omni
 
117
  <div align="center">
118
 
119
  | Model | aishell1 | aishell2_android | aishell2_ios | cv15_zh | fleurs_zh | wenetspeech_meeting | wenetspeech_net | librispeech_test_clean | librispeech_test_other | multilingual_librispeech | cv15_en | fleurs_en | voxpopuli_v1.0_en |
120
+ |:--------------:|:--------:|:----------------:|:------------:|:--------:|:---------:|:-------------------:|:---------------:|:----------------------:|:----------------------:|:------------------------:|:--------:|:---------:|:--------------------:|\
121
  | Ming-lite-omni | 1.47 | **2.55** | **2.52** | 6.31 | 2.96 | 5.95 | 5.46 | 1.44 | 2.80 | **4.15** | **6.89** | **3.39** | **5.80** |
122
  | Qwen2.-Omni | 1.18 | 2.75 | 2.63 | **5.20** | 3.00 | **5.90** | 7.70 | 1.80 | 3.40 | 7.56 | 7.60 | 4.10 | **5.80** |
123
  | Qwen2-Audio | 1.53 | 2.92 | 2.92 | 6.90 | 7.50 | 7.16 | 8.42 | 1.60 | 3.60 | 5.40 | 8.60 | 6.90 | 6.84 |
 
202
  Additional demonstration cases are available on our project [page](https://lucaria-academy.github.io/Ming-Omni/).
203
 
204
 
 
 
205
  ## Example Usage
206
 
207
  Please download our model following [Model Downloads](#model-downloads), then you can refer to the following codes to run Ming-lite-omni model.
 
275
  To enable thinking before response, adding the following system prompt before your question:
276
 
277
  ```python
278
+ cot_prompt = "SYSTEM: You are a helpful assistant. When the user asks a question, your response must include two parts: first, the reasoning process enclosed in <thinking>...</thinking> tags, then the final answer enclosed in <answer>...</answer> tags. The critical answer or key result should be placed within \\boxed{}.
279
+ "
280
  # And your input message should be like this:
281
  messages = [
282
  {
283
  "role": "HUMAN",
284
  "content": [
285
  {"type": "image", "image": os.path.join(assets_path, "reasoning.png")},
286
+ {"type": "text", "text": cot_prompt + "In the rectangle $A B C D$ pictured, $M_{1}$ is the midpoint of $D C, M_{2}$ the midpoint of $A M_{1}, M_{3}$ the midpoint of $B M_{2}$ and $M_{4}$ the midpoint of $C M_{3}$. Determine the ratio of the area of the quadrilateral $M_{1} M_{2} M_{3} M_{4}$ to the area of the rectangle $A B C D$.
287
+ Choices:
288
+ (A) $\\frac{7}{16}$
289
+ (B) $\\frac{3}{16}$
290
+ (C) $\\frac{7}{32}$
291
+ (D) $\\frac{9}{32}$
292
+ (E) $\\frac{1}{5}$"},
293
  ],
294
  },
295
  ]
296
  # Output:
297
+ # \<think\>
298
+ Okay, so I have this problem about a rectangle ABCD ... (thinking process omitted) ... So, the correct answer is C.
299
+ \</think\>
300
+ \<answer\>\\boxed{C}\</answer\>
301
+
302
+
303
  ```
304
 
305
  ```python
 
559
  archivePrefix = {arXiv},
560
  url = {https://arxiv.org/abs/2506.09344}
561
  }
562
+ ```