Pinned issues
Issues
- 3
- 0
Big difference between the before-cooldown-ckpt and the final checkpoint in the results of downstream tasks?
#104 opened by siqi13579 - 0
Chatting and prompt
#103 opened by kazunaritakeichi - 0
Windows fatal exception: access violation
#102 opened by mct-lrh - 1
Why my output is so short?
#60 opened by Dmayset - 1
- 2
Target modules ['query_key_value', 'dense', 'dense_h_to_4h', 'dense_4h_to_h'] not found in the base model. Please check the target modules and try again.
#98 opened by andysingal - 4
Is this project abandoned?
#83 opened by agademic - 3
OSError: stabilityai/stablelm-base-alpha-3b-v2 does not appear to have a file named pytorch_model.bin, tf_model.h5, model.ckpt or flax_model.msgpack.
#99 opened by RylanSchaeffer - 8
License unclear
#77 opened by dylancvdean - 0
Stability AI
#84 opened by metadot01 - 1
The output is the same as the input.
#81 opened by yz-qiang - 4
process killed
#76 opened by gmankab - 1
- 1
How to expand the sequence length of llama?
#79 opened by binganao - 17
How to Fine-tune the Model?
#37 opened by berkecanrizai - 0
Consider using OpenAI Evals
#80 opened by walking-octopus - 6
Training Script stablity 3B and 7B
#72 opened by aamir-gmail - 6
- 3
Can't load model on AWS Sagemaker
#57 opened by DavidHaintz - 2
fairyfloss
#75 opened by Davido554 - 2
Cannot run demo
#74 opened by WencongY - 2
Unclear tokenizer class
#73 opened by carmocca - 2
- 3
- 0
Is padding token supported?
#59 opened by nirvedhmeshram - 3
- 1
loss not decreasing with deepspeed
#71 opened by haorannlp - 1
RLHF training code for StableVicuna open sourced?
#69 opened by REIGN12 - 3
RLHF training code
#65 opened by jaideep11061982 - 2
Support for MPS device (Apple M1/M2)
#61 opened by louis030195 - 2
- 1
How to train the StableLM-Tuned-Alpha-3b or StableLM-Tuned-Alpha-7b? I want to know the details of the fine-tuning. Thanks.
#55 opened by Appleyc - 1
Source code for the model
#56 opened by vivek-kokotree - 0
The example code does not respect stop tokens
#62 opened by gee842 - 1
- 0
Running Quantized Model
#53 opened by RaghavMajorBoost - 1
What Other Models are Available?
#46 opened by RaghavMajorBoost - 1
RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory
#47 opened by yudonglee - 2
15B, 30B, 65B
#51 opened by HUA9803 - 3
Will the StableLM support Chinese?
#50 opened by MaggieGao02 - 1
failed to detect simple syntax code errors
#52 opened by rosolinol - 4
Getting outofMemory error: CUDA
#39 opened by groundswel - 2
Write me an essay about yoga
#35 opened by Nightsun996 - 6
- 0
- 20
This is not a issue 👍
#42 opened by nuhmanpk - 0
Вся
#45 opened by vlad27-blip - 1
How to convert to 4bit gptq
#44 opened by c-seeger - 1
How to finetune StableLM with LoRA?
#40 opened by Itto1992