Comments (8)
Fixed it, will do a PR right now.
from transformers.
Awesome, thanks !
from transformers.
Hi @mxjmtxrm
Can you share which model are you trying to quantize?
from transformers.
It is my own model based on hf llama2 7B. I just modify the bias of qkv proj is True. So the pretrained ckpt contains .bias
, and then the above error arised.
from transformers.
I use the distil-whisper model. I'm getting the same error. BitsAndBytesConfig optimization method works. HQQ method gives error.
from transformers.
Can you check?
from transformers.
Can you share a code snippet to reproduce this please?
from transformers.
Thanks everyone ! Indeed I was able to repro with:
from transformers import AutoModelForSpeechSeq2Seq, HqqConfig
model_id = "distil-whisper/distil-large-v2"
quant_config = HqqConfig(nbits=1, group_size=64, quant_zero=False, quant_scale=False, axis=0)
model = AutoModelForSpeechSeq2Seq.from_pretrained(model_id, quantization_config=quant_config, device_map="cuda")
print(model)
from transformers.
Related Issues (20)
- Add Mamba2 HOT 5
- Speed up image processors - cast to array before BatchFeature
- PreTrainedModel.from_pretrained(path, from_flax=True) fails for sharded Flax checkpoints
- [pipeline] VQA pipeline does not accept list as input HOT 1
- Loading XGLM with Tensorflow and apply resize_token_embeddings() raises an error. HOT 2
- Batch size schedulers HOT 8
- FlashAttention2 issue with Mistral/Mixtral related to max length and RotaryEmbedding HOT 1
- Issue with model.generate returning outdated hidden states for earlier tokens HOT 2
- PEFT + ZeRO Phase 2 + Transformers doesn't output pytorch_model.bin HOT 2
- xpu: Support new PyTorch XPU backend (>=2.4) HOT 3
- Loaded Donut models lost their predictive power HOT 2
- Add a new model for RNA sequence modeling HOT 2
- 🐛 `attn_implementation="sdpa"` slower than `BetterTransformer.transform`? HOT 1
- We Need Compile Support For Mamba! HOT 1
- Add support for non-CUDA architectures at the same time Bitsandbytes is doing it HOT 4
- Intel/dpt-swinv2-tiny-256: TypeError: unsupported operand type(s) for //: 'NoneType' and 'NoneType' HOT 10
- Adaptive Decoding Support HOT 1
- Inconsistent behaviors of generate() between versions before and after 4.41.* on mistralai/Mistral-7B-Instruct-v0.2 HOT 3
- Why is data_seed not in use HOT 7
- Flaky test - tests/models/mobilenet_v1/test_modeling_mobilenet_v1.py::MobileNetV1ModelTest::test_batching_equivalence HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from transformers.