wellecks / llmstep Goto Github PK
View Code? Open in Web Editor NEWllmstep: [L]LM proofstep suggestions in Lean 4.
License: MIT License
llmstep: [L]LM proofstep suggestions in Lean 4.
License: MIT License
Hey,
really like the project!
I am really interested in the performance of this this LLM vs the official Reprover.
Did you consider running a lean-dojo benchmark? If so, where can we find the results?
Any chance for Colab support for those of us without a GPU?
As a beginner I'm eager to try this out, I feel like it could be really useful, but can't run it locally.
After 9299059, I get this error whenever I try to use the llmstep
tactic:
process 'python3' exited with code 1
I tried adding this error logging:
diff --git a/python/server.py b/python/server.py
index 0efa17b..0322341 100644
--- a/python/server.py
+++ b/python/server.py
@@ -94,6 +94,7 @@ class LLMStepRequestHandler(BaseHTTPRequestHandler):
response = result
self.wfile.write(json.dumps(response).encode('utf-8'))
except Exception as e:
+ print("Error", e)
error_response = {'error': str(e)}
self.wfile.write(json.dumps(error_response).encode('utf-8'))
And the error shown is:
Error "LayerNormKernelImpl" not implemented for 'Half'
The error goes away if I revert 9299059.
For additional context:
I'm running python python/server.py
with no arguments. Additionally, I've disabled cuda because my card does not have enough memory:
diff --git a/python/server.py b/python/server.py
index 0efa17b..0c2c8b5 100644
--- a/python/server.py
+++ b/python/server.py
@@ -18,7 +18,7 @@ def load_hf(hf_model):
model = transformers.AutoModelForCausalLM.from_pretrained(hf_model)
tokenizer = transformers.AutoTokenizer.from_pretrained(hf_model)
- if torch.cuda.is_available():
+ if False:
model.cuda()
model.eval()
print("Done.")
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.