llama.cpp verification source 2026-05-22
Some checks are pending
Copilot Setup Steps / copilot-setup-steps (push) Waiting to run
Check Pre-Tokenizer Hashes / pre-tokenizer-hashes (push) Waiting to run
Python check requirements.txt / check-requirements (push) Waiting to run
Python Type-Check / python type-check (push) Waiting to run
Update Operations Documentation / update-ops-docs (push) Waiting to run
Some checks are pending
Copilot Setup Steps / copilot-setup-steps (push) Waiting to run
Check Pre-Tokenizer Hashes / pre-tokenizer-hashes (push) Waiting to run
Python check requirements.txt / check-requirements (push) Waiting to run
Python Type-Check / python type-check (push) Waiting to run
Update Operations Documentation / update-ops-docs (push) Waiting to run
This commit is contained in:
25
tools/mtmd/debug/mtmd-debug.md
Normal file
25
tools/mtmd/debug/mtmd-debug.md
Normal file
@@ -0,0 +1,25 @@
|
||||
# mtmd-debug
|
||||
|
||||
## Debugging encode pass
|
||||
|
||||
Example of debugging an input gray image (raw, not preprocessed):
|
||||
|
||||
```py
|
||||
from transformers import AutoModel
|
||||
|
||||
model = AutoModel.from_pretrained(...)
|
||||
|
||||
def test_vision():
|
||||
img_size = 896 # number of patches per side
|
||||
pixel_values = torch.zeros(1, 3, img_size, img_size) + 0.5 # gray image
|
||||
with torch.no_grad():
|
||||
outputs = model.model.get_image_features(pixel_values=pixel_values)
|
||||
print("last_hidden_state shape:", outputs.last_hidden_state.shape)
|
||||
print("last_hidden_state:", outputs.last_hidden_state)
|
||||
|
||||
test_vision()
|
||||
```
|
||||
|
||||
## Debugging preprocess pass
|
||||
|
||||
(TODO)
|
||||
Reference in New Issue
Block a user