stochasticai/xTuring
Build, customize and control you own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHXuSJEk6
PythonApache-2.0
Issues
- 1
- 1
Issue with installing xTuring on Windows
#279 opened by SwaroopMeher - 2
I have generated a dataset
#261 opened by abrahimzaman360 - 1
Bug in generate_dataset_from_dir()
#266 opened by TimofeiKargin - 1
Add `mistral-7B` as a base model of xTuring
#273 opened by fpaupier - 1
- 5
- 6
[Feature Request] Support more popular compression algorithms and highly optimized kernels on the CPU
#264 opened by yiliu30 - 1
- 2
Fine-tune llama2-7b base(not using lora) with 8-A100 GPU(AWS ml.p4de.24xlarge) is not available.
#267 opened by WL0118 - 1
The example pages link in the documentation is not working shows "Not Found"
#256 opened by AayushSameerShah - 5
Problem installing xTuring
#252 opened by heyili - 2
xFinance tuning example and methodology details
#251 opened by mjsteele12 - 24
- 1
- 1
- 2
Loss is "nan" while training gpt2
#238 opened by sankethgadadinni - 1
CUDA Not found?
#249 opened by basemaly - 1
lora finetunelarger galactica checkpoints
#245 opened by JonathanSchmidt1 - 2
How to launch?
#247 opened by basemaly - 3
KeyError: 'llama_lora_int4'
#233 opened by adastra9257 - 3
RuntimeError: Lightning can't create new processes if CUDA is already initialized.
#231 opened by christina-nasika-edo - 3
CPU Only Support
#222 opened by chriskuchar - 1
- 3
- 2
Load saved model in GenericLoraModel
#228 opened by shrimonmuke0202 - 3
Unable to filetune falcon-7b with int8
#223 opened by msinha251 - 1
How to set generate_dataset_from_dir parameters properly for more diverse samples?
#183 opened by raziurtotha - 5
GenericLoraModel load error
#218 opened by xupruvu - 5
Add support for more sizes of LLaMA
#169 opened by cnbeining - 3
Add MPT-7B
#204 opened by MohamedAliRashad - 2
xturing-0.1.4 BaseModel.create error
#213 opened by xupruvu - 3
New models of dataset to use
#199 opened by mums77 - 1
Cpu Offloading
#203 opened by JochenGuckSnk - 4
Add Open Assistant support
#168 opened by jimafisk - 1
Training LlaMa with alpaca data multigpu error
#194 opened by cmxela - 1
- 4
MisconfigurationException: Trainer [...] is not compatible with an interactive environment
#186 opened by mmontag - 2
Request for CPU only support
#193 opened by chriskuchar - 1
logging output appears on stdout
#197 opened by markusdr - 1
generate() returns the same output 8 times
#196 opened by markusdr - 1
Exporting to ggml
#185 opened by peter-ch - 1
How to release memory in Colab
#188 opened by mmontag - 2
How can i have multiGPU facility in xturing ?
#187 opened by sazzad15-1779 - 5
- 1
are flan-t5 models supported?
#184 opened by vahuja4 - 4
cannot create model
#175 opened by apollo-de - 1
Quickstart script abruptly terminating
#173 opened by exwhyz - 1
Issue: New model request
#170 opened by brijeshKarna - 2
Fine-tuning error: Lightning can't create new processes if CUDA is already initialized.
#171 opened by markusdr