Update README.md
Browse files
README.md
CHANGED
@@ -2,11 +2,16 @@
|
|
2 |
license: apache-2.0
|
3 |
---
|
4 |
|
5 |
-
**NOTE:** Tested with KoboldCpp.
|
|
|
6 |
|
7 |
-
**2023-04-20:** Converted using ggerganov/ggml's "stablelm" conversion script and quantization code as of [commit 05f3079](https://github.com/ggerganov/ggml/tree/05f307971862b83df12fada0c42ee027ba5a82b5/examples/stablelm).
|
8 |
|
9 |
-
**2023-04-30:** Converted using ggerganov/ggml's "stablelm" conversion script and quantization code as of [commit 5dd92f4](https://github.com/ggerganov/ggml/tree/5dd92f421ee44f18b8fde0afbf5ca8fc7bf93841/examples/stablelm).
|
|
|
|
|
|
|
|
|
10 |
|
11 |
These conversions are based off of the updated Pythia Deduped checkpoints, not the original v0 trainings.
|
12 |
|
|
|
2 |
license: apache-2.0
|
3 |
---
|
4 |
|
5 |
+
# **NOTE:** Tested with KoboldCpp.
|
6 |
+
## (I can't promise that it will work with other frontends, if at all. Use at your own risk!)
|
7 |
|
8 |
+
**2023-04-20:** Includes q4_3 versions of all Pythia Deduped models. Converted using ggerganov/ggml's "stablelm" conversion script and quantization code as of [commit 05f3079](https://github.com/ggerganov/ggml/tree/05f307971862b83df12fada0c42ee027ba5a82b5/examples/stablelm).
|
9 |
|
10 |
+
**2023-04-30:** Includes q5_0, q5_1, and q8_0 versions of Pythia Deduped models up to 2.8B. Converted using ggerganov/ggml's "stablelm" conversion script and quantization code as of [commit 5dd92f4](https://github.com/ggerganov/ggml/tree/5dd92f421ee44f18b8fde0afbf5ca8fc7bf93841/examples/stablelm).
|
11 |
+
|
12 |
+
**2023-05-06:** Includes q4_0 and q4_2 versions of Pythia Deduped models up to 2.8B. Converted using ggerganov/ggml's "stablelm" conversion script and quantization code as of [commit ff6e03c](https://github.com/ggerganov/ggml/tree/ff6e03cbcd9bf6e9fa41d49f2495c042efae4dc6/examples/stablelm).
|
13 |
+
|
14 |
+
They're separated by date and commit so it's easier to track any breaking changes. The last two go up to 2.8B because it's time-consuming (and unreliable even overnight) for me to upload q4_0, q5_0, q5_1, and q8_0 for the 6.9B and 12B conversions. If you have the hardware for a 7B+ model, I would recommend the currently-training [OpenLLaMA 7B](https://huggingface.co/vihangd/open_llama_7b_300bt_ggml).
|
15 |
|
16 |
These conversions are based off of the updated Pythia Deduped checkpoints, not the original v0 trainings.
|
17 |
|