Add YAML metadata to model card
Browse files
README.md
CHANGED
|
@@ -1,3 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# EAGLE3 Draft Model for GLM-4.7-Flash
|
| 2 |
|
| 3 |
GLM-4.7-Flash-Eagle3 is an EAGLE3 draft model trained for speculative decoding with **GLM-4.7-Flash**. It enables faster inference by predicting multiple future tokens in parallel, which are then verified by the target model in a single forward pass.
|
|
@@ -5,7 +23,7 @@ GLM-4.7-Flash-Eagle3 is an EAGLE3 draft model trained for speculative decoding w
|
|
| 5 |
**Version:** 1.0
|
| 6 |
**Release Date:** 2026-02-16
|
| 7 |
**Organization:** ThoughtWorks
|
| 8 |
-
**License:**
|
| 9 |
|
| 10 |
---
|
| 11 |
|
|
@@ -221,7 +239,7 @@ print(response.json())
|
|
| 221 |
|
| 222 |
## License
|
| 223 |
|
| 224 |
-
|
| 225 |
|
| 226 |
---
|
| 227 |
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: transformers
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
|
| 7 |
+
- speculative-decoding
|
| 8 |
+
|
| 9 |
+
- eagle3
|
| 10 |
+
|
| 11 |
+
- glm
|
| 12 |
+
|
| 13 |
+
- draft-model
|
| 14 |
+
|
| 15 |
+
- text-generation
|
| 16 |
+
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
# EAGLE3 Draft Model for GLM-4.7-Flash
|
| 20 |
|
| 21 |
GLM-4.7-Flash-Eagle3 is an EAGLE3 draft model trained for speculative decoding with **GLM-4.7-Flash**. It enables faster inference by predicting multiple future tokens in parallel, which are then verified by the target model in a single forward pass.
|
|
|
|
| 23 |
**Version:** 1.0
|
| 24 |
**Release Date:** 2026-02-16
|
| 25 |
**Organization:** ThoughtWorks
|
| 26 |
+
**License:** apache-2.0
|
| 27 |
|
| 28 |
---
|
| 29 |
|
|
|
|
| 239 |
|
| 240 |
## License
|
| 241 |
|
| 242 |
+
apache-2.0
|
| 243 |
|
| 244 |
---
|
| 245 |
|