Issues
- 2
How to use it with LangChain?
#30 opened by tonymacx86PRO - 0
gguf / mlx format?
#34 opened by alexander-potemkin - 0
- 2
Timeout on 8 x RTX A6000
#31 opened by andrewerf - 0
- 2
Provide pruned version for weaker hardware
#27 opened by CommanderTvis - 2
Citation bibtex?
#28 opened by Guitaricet - 6
CUDA out of memory
#22 opened by Aspector1 - 1
- 1
- 0
PCI x1 or PCI x16 for GPU
#24 opened by hostingmydata - 1
NCCL error
#23 opened by ZiqianXie - 2
- 9
ZeRO 3 NVMe Offload?
#7 opened by Vbansal21 - 0
- 2
- 2
- 9
Online examples
#3 opened by Slauta - 1
AWS
#15 opened by githubuser100007 - 0
Run on networked nodes
#14 opened by ExtraE113 - 2
Dataset information
#5 opened by finetunej - 2
[NL] token
#8 opened by TatianaShavrina - 2
- 3
Possible to run on 8 x 24GB 3090?
#9 opened by hobodrifterdavid - 2
- 0
Model dataset irregularity
#10 opened by joshlk - 1
- 0
Evaluation benchmarks (lm-eval-harness)
#2 opened by justheuristic