Inference failed with "axis 2 has dimension xxxx but expected yyyy" error
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 4.7k
- Forks
- 536
- Avg merge
- 12h 12m
- Merged PRs (30d)
- 4
Description
I tried to use ctranslate2 as the inference framework to do model inference, but failed with error as below:
"axis 2 has dimension 8192 but expected 7680"
What I've done:
-
First I must convert the model to CT2 model, but due to big model size, I used Quantify parameter to reduce model file's size:
converter.convert(output_dir, quantization="int8",force=True) -
Then, Load the quantified model and do inference, unfortunately I hitted below error:
"axis 2 has dimension 8192 but expected 7680" error
How to fix it ?
Inference code snippet is as below:
`
try:
# 加载量化后的模型作为 Generator
generator = ctranslate2.Generator("gemma-2-9b-it-ct2", device="cpu")
# 准备输入
input_text = "Translate this to French: Hello, world!"
tokens = tokenizer.convert_ids_to_tokens(tokenizer.encode(input_text))
# 使用 generate_batch 方法进行推理
results = generator.generate_batch([tokens], max_length=50, sampling_topk=1)
# 解码并打印结果
for result in results:
output_tokens = result.sequences[0]
output_text = tokenizer.decode(tokenizer.convert_tokens_to_ids(output_tokens))
print(f"Input: {input_text}")
print(f"Output: {output_text}")
except Exception as e:
print(f"Error during model loading or inference: {e}")`
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the conversion and inference steps shown for gemma-2-9b-it-ct2, including int8 quantization and Generator.generate_batch. Investigate the reported axis-dimension mismatch between conversion and inference; done means identifying a supported configuration or a confirmed fix for successful inference.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp, python
- Domain
- backend, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100