Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
This is a quantization of Yi-VL-34B and of the visual transformer.
|
| 2 |
+
|
| 3 |
+
You currently need to apply this PR to make it work: https://github.com/ggerganov/llama.cpp/pull/5093 - this adds the additional normalization steps into the projection
|
| 4 |
+
|
| 5 |
+
Yi-Vl-34B is prone to hallucinations, to me it appears like a rushed release. Something did not go right in training.
|
| 6 |
+
However, while 6B was the 2nd worst llava-model I've tested, the 34B did show some strengths.
|