HuggingFaceH4
/

starchat-alpha

Text Generation

text-generation-inference

Model card Files Files and versions

Metrics Training metrics Community

Resources

View closed (5)

habibi

#29 opened over 1 year ago by deleted

Adding Evaluation Results

#28 opened over 1 year ago by

leaderboard-pr-bot

🚩 Report

#27 opened over 1 year ago by

Incomplete Output even with max_new_tokens

#26 opened over 1 year ago by

Update README.md

#25 opened over 1 year ago by

Evaluations on LM Harness

#24 opened over 1 year ago by

Warning

#23 opened almost 2 years ago by

Error while loading the model using safe tensors

#22 opened almost 2 years ago by

Getting expected maxsize to be an integer or None

#21 opened almost 2 years ago by

Getting ValueError while loading 'HuggingFaceH4/starchat-alpha' model in pipeline

#20 opened almost 2 years ago by

Getting Cuda runtime error when running the get started code snippet.

#19 opened almost 2 years ago by

Update README.md

#18 opened almost 2 years ago by

Request to Train Chat LM Model with our English-Sinhala Translation Dataset

#16 opened almost 2 years ago by

ggml demo

#15 opened almost 2 years ago by

How to deploy this on Vertex AI?

#14 opened almost 2 years ago by

NotImplementedError: Cannot copy out of meta tensor; no data!

#13 opened almost 2 years ago by

max new tokens error despite setting lower size, The size of tensor a (8192) must match the size of tensor b (8193) at non-singleton dimension 2

#12 opened almost 2 years ago by

Text Truncation even with increase in max_new_tokens

#11 opened almost 2 years ago by

what is the Humaneval metric for starchat?

#10 opened almost 2 years ago by

Has anybody tried the inference endpoints of this model

#9 opened almost 2 years ago by

adityasharma2695

CPU bound when loaded on GPU?

#6 opened almost 2 years ago by

Can you share the server code for local deploy?

#4 opened almost 2 years ago by

General tips around inference speed?

#3 opened almost 2 years ago by

Model doesn't end/terminate generation: Need to modify EOS token

#2 opened almost 2 years ago by