Sweaterdog commited on
Commit
742e7f6
·
verified ·
1 Parent(s): 8eab1f5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -11
README.md CHANGED
@@ -1,12 +1,12 @@
1
- ---
2
- license: apache-2.0
3
- language:
4
- - en
5
- base_model:
6
- - allenai/OLMoE-1B-7B-0125
7
- pipeline_tag: text-generation
8
- library_name: transformers
9
- ---
10
 
11
  ![GRaPE_Logo](https://cdn-uploads.huggingface.co/production/uploads/66960602f0ffd8e3a381106a/XjHkzctrE41e1qqJYeDzN.png)
12
 
@@ -15,7 +15,7 @@ _The **G**eneral **R**easoning **A**gent (for) **P**roject **E**xploration_
15
  # The GRaPE Family
16
  | Attribute | Size | Modalities | Domain |
17
  | :--- | :--- | :--- | :--- |
18
- | **GRaPE** | 10B A2.7B | Text + Image + Video in, Text out | Complex Reasoning Tasks |
19
  | **GRaPE Flash** (this model) | 7B A1B | Text in, Text out | High-Speed Applications |
20
  | **GRaPE Mini** | 1.7B | Text in, Text out | Edge Deployment |
21
 
@@ -29,7 +29,7 @@ The GRaPE Family was trained on about **14 billion** tokens of data after pre-tr
29
 
30
  # Architecture
31
 
32
- * GRaPE: Built on the `Qwen3 VL MoE` Architecture, allowing for long-context understanding and reasoning over visual tasks, as well as any text-based task. Allowing for deep understanding.
33
 
34
  * GRaPE Flash: Built on the `OlMoE` Architecture, allowing for incredibly fast speeds where it matters. Allows for retaining factual information, but lacks in logical tasks.
35
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ base_model:
6
+ - allenai/OLMoE-1B-7B-0125
7
+ pipeline_tag: text-generation
8
+ library_name: transformers
9
+ ---
10
 
11
  ![GRaPE_Logo](https://cdn-uploads.huggingface.co/production/uploads/66960602f0ffd8e3a381106a/XjHkzctrE41e1qqJYeDzN.png)
12
 
 
15
  # The GRaPE Family
16
  | Attribute | Size | Modalities | Domain |
17
  | :--- | :--- | :--- | :--- |
18
+ | **GRaPE Pro** | 10B A2.7B | Text + Image + Video in, Text out | Complex Reasoning Tasks |
19
  | **GRaPE Flash** (this model) | 7B A1B | Text in, Text out | High-Speed Applications |
20
  | **GRaPE Mini** | 1.7B | Text in, Text out | Edge Deployment |
21
 
 
29
 
30
  # Architecture
31
 
32
+ * GRaPE Pro: Built on the `Qwen3 VL MoE` Architecture, allowing for long-context understanding and reasoning over visual tasks, as well as any text-based task. Allowing for deep understanding.
33
 
34
  * GRaPE Flash: Built on the `OlMoE` Architecture, allowing for incredibly fast speeds where it matters. Allows for retaining factual information, but lacks in logical tasks.
35