Comments (5)
same on google colab
from gptq-for-llama.
diff --git a/llama.py b/llama.py
index 09b527e..cc652dd 100644
--- a/llama.py
+++ b/llama.py
@@ -238,7 +238,7 @@ def load_quant(model, checkpoint, wbits):
make_quant(model, layers, wbits)
print('Loading model ...')
- if checkpoint.endswith('.safetensors'):
+ if checkpoint.as_posix().endswith('.safetensors'):
from safetensors.torch import load_file as safe_load
model.load_state_dict(safe_load(checkpoint))
else:
that patch worked for me in linux at least
from gptq-for-llama.
Same on windows native. A similar solution worked for me (skipping that check entirely).
from gptq-for-llama.
Fixed a bug.
Please test if you still have such problem.
I didn't encounter such problem with wsl2.
from gptq-for-llama.
I can confirm the same problem with current code:
text-generation-webui-text-generation-webui-1 | Loading llama-13b...
text-generation-webui-text-generation-webui-1 | Loading model ...
text-generation-webui-text-generation-webui-1 | Traceback (most recent call last):
text-generation-webui-text-generation-webui-1 | File "/app/server.py", line 194, in <module>
text-generation-webui-text-generation-webui-1 | shared.model, shared.tokenizer = load_model(shared.model_name)
text-generation-webui-text-generation-webui-1 | File "/app/modules/models.py", line 119, in load_model
text-generation-webui-text-generation-webui-1 | model = load_quant(path_to_model, Path(f"models/{pt_model}"), 4)
text-generation-webui-text-generation-webui-1 | File "/app/repositories/GPTQ-for-LLaMa/llama.py", line 241, in load_quant
text-generation-webui-text-generation-webui-1 | if checkpoint.endswith('.safetensors'):
text-generation-webui-text-generation-webui-1 | AttributeError: 'PosixPath' object has no attribute 'endswith'
Docker under Windows, python 3.10
Edit: on a side note, this might be connected to the python version
Edit2: After a rebuild now, I can't reproduce the error. Not sure what happened, it could be possible docker used an old build cache, but I don't see how. That layer have only started working due to changes done today which should invalidate all old layer caches.
from gptq-for-llama.
Related Issues (20)
- llama_inference 4bits error
- inference with the saved model error: AttributeError: module 'torch.backends.cuda' has no attribute 'sdp_kernel' HOT 2
- Could not obtain official perplexity using bloom_eval()
- can it support openllama model?
- Issue with GPTQ HOT 1
- High PPL when groupsize != -1 for OPT model after replace linear layer with quantlinear. HOT 1
- Help: Quantized llama-7b model with custom prompt format produces only gibberish HOT 1
- Why does the model quantization prompt KILLED at the end? HOT 2
- Would GPTQ be able to support LLaMa2? HOT 1
- Can i quantize HF version of llama model
- Transformers broke again (AttributeError: 'GPTQ' object has no attribute 'inp1') HOT 1
- LoRa and diff with bitsandbytes
- neox.py needs to add "import math"
- error: block with no terminator, has llvm.cond_br %5624, ^bb2, ^bb3
- Support Mistral.
- Syntax changed in triton.testing.do_bench() causing error when running llama_inference.py
- datasets.utils.info_utils.ExpectedMoreSplits: {'validation'} HOT 1
- Error when load GPTQ model
- GPTQ vs bitsandbytes
- add support for minicpm
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 gptq-for-llama.