mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-04-21 06:59:21 +00:00
Add GitHub data: filename sanitization (#640)
This commit is contained in:
37
github-data/issues/452 - Falcon H1 Support.md
Normal file
37
github-data/issues/452 - Falcon H1 Support.md
Normal file
@@ -0,0 +1,37 @@
|
||||
### 📝 [#452](https://github.com/ikawrakow/ik_llama.cpp/issues/452) - Falcon H1 Support
|
||||
|
||||
| **Author** | `Downtown-Case` |
|
||||
| :--- | :--- |
|
||||
| **State** | ❌ **Closed** |
|
||||
| **Created** | 2025-05-23 |
|
||||
| **Updated** | 2025-06-27 |
|
||||
|
||||
---
|
||||
|
||||
#### Description
|
||||
|
||||
A hybrid transformers/mamba2 series with good performance: https://huggingface.co/collections/tiiuae/falcon-h1-6819f2795bc406da60fab8df
|
||||
|
||||
Officially supported via their fork of llama.cpp here: https://github.com/tiiuae/llama.cpp-Falcon-H1
|
||||
|
||||
Support for ik_llama.cpp's tighter quantization schemes would be nice :). Maybe something in this fork can shrink the Mamba2 context cache as well?
|
||||
|
||||
---
|
||||
|
||||
#### 💬 Conversation
|
||||
|
||||
👤 **ikawrakow** commented the **2025-05-24** at **07:04:24**:<br>
|
||||
|
||||
Have you though about adding a feature request to the llama.cpp-Falcon-H1 authors?
|
||||
|
||||
---
|
||||
|
||||
👤 **Downtown-Case** commented the **2025-06-02** at **18:19:21**:<br>
|
||||
|
||||
Seems their implementation needs more time in the oven anyway.
|
||||
|
||||
---
|
||||
|
||||
👤 **Downtown-Case** commented the **2025-06-27** at **14:31:42**:<br>
|
||||
|
||||
Closing this
|
||||
Reference in New Issue
Block a user