Downloads · 30 days
144
3% of all-time downloads
Yi-VL-34B-GGUF
cmp-nct/Yi-VL-34B-GGUF
Yi-VL-34B-GGUF is a machine learning model from cmp-nct. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This is a quantization of Yi-VL-34B and of the visual transformer.
All-time downloads
5.5K
Public
Repo size
76.4 GB
Likes
10
Public
Repo makeup
Click a slice to open those files.
.gguf76.4 GB · 100%
At a glance
- Access
- Public
- Created
- Jan 24, 2024
- Updated
- Jan 29, 2024
- SHA
- a5715ec6
Model card
From the Hugging Face model README
This is a quantization of Yi-VL-34B and of the visual transformer.
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
Yi-Vl-34B is prone to hallucinations, to me it appears like a rushed release. Something did not go right in training. However, while 6B was the 2nd worst llava-model I've tested, the 34B did show some strengths.
- Created
- Jan 24, 2024
- Updated
- Jan 29, 2024