mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-24 00:12:08 +00:00
7402a355dc
This PR addresses an issue where calling `model = model.cuda()` would
throw a ValueError when `quantize` is set to "bitsandbytes".
```
> File "/opt/conda/lib/python3.9/site-packages/text_generation_server/server.py", line 147, in serve_inner
model = get_model(
File "/opt/conda/lib/python3.9/site-packages/text_generation_server/models/__init__.py", line 295, in get_model
return CausalLM(
File "/opt/conda/lib/python3.9/site-packages/text_generation_server/models/causal_lm.py", line 515, in __init__
model = model.cuda()
File "/opt/conda/lib/python3.9/site-packages/transformers/modeling_utils.py", line 1998, in cuda
raise ValueError(
ValueError: Calling `cuda()` is not supported for `4-bit` or `8-bit` quantized models. Please use the model as it is, since the model has already been set to the correct devices and casted to the correct `dtype`.
```
Co-authored-by: mmnga <mmnga1mmnga@gmail.com>
|
||
|---|---|---|
| .. | ||
| models | ||
| pb | ||
| utils | ||
| __init__.py | ||
| cache.py | ||
| cli.py | ||
| interceptor.py | ||
| server.py | ||
| tracing.py | ||