tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Fix(doc): Clarify doc on attention configs and missing pad_token (#2455) [skip ci]

Browse Source 
* fix: clarify input type

* fix: handling of error message if data_files not available

* fix: clarify attention handling

* fix: add doc on missing pad token
This commit is contained in:
NanoCode012
2025-04-01 02:47:28 +07:00
committed by GitHub
parent b6fc46ada8
commit 7acf93b59f
3 changed files with 29 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
docs/config.qmd
View File

@@ -587,26 +587,31 @@ max_grad_norm:
# currently only supported on Llama and Mistral
neftune_noise_alpha:
# Whether to bettertransformers
# Optional[bool]. Whether to bettertransformers
flash_optimum:
# Whether to use xformers attention patch https://github.com/facebookresearch/xformers:
# Note: Only one of the following attention patches can be used at a time.
# For example, if you set `xformers_attention` to `true`, do not set `flash_attention` to `true`.
# Optional[bool]. Whether to use xformers attention patch https://github.com/facebookresearch/xformers:
xformers_attention:
# Whether to use flash attention patch https://github.com/Dao-AILab/flash-attention:
# Optional[bool]. Whether to use flash attention patch https://github.com/Dao-AILab/flash-attention:
flash_attention:
flash_attn_cross_entropy: # Whether to use flash-attention cross entropy implementation - advanced use only
flash_attn_rms_norm: # Whether to use flash-attention rms norm implementation - advanced use only
flash_attn_fuse_qkv: # Whether to fuse QKV into a single operation
flash_attn_fuse_mlp: # Whether to fuse part of the MLP into a single operation
# Whether to use scaled-dot-product attention
flash_attn_cross_entropy: # Optional[bool]. Whether to use flash-attention cross entropy implementation - advanced use only
flash_attn_rms_norm: # Optional[bool]. Whether to use flash-attention rms norm implementation - advanced use only
flash_attn_fuse_qkv: # Optional[bool]. Whether to fuse QKV into a single operation
flash_attn_fuse_mlp: # Optional[bool]. Whether to fuse part of the MLP into a single operation
# Optional[bool]. Whether to use scaled-dot-product attention
# https://pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html
sdp_attention:
# Shifted-sparse attention (only llama) - https://arxiv.org/pdf/2309.12307.pdf
# Optional[bool]. Shifted-sparse attention (only llama) - https://arxiv.org/pdf/2309.12307.pdf
s2_attention:
# Optional[bool]. Whether to use low_cpu_mem_usage
low_cpu_mem_usage:
# Resume from a specific checkpoint dir
# Optional[str]. Resume from a specific checkpoint dir
resume_from_checkpoint:
# If resume_from_checkpoint isn't set and you simply want it to start where it left off.
# Optional[bool]. If resume_from_checkpoint isn't set and you simply want it to start where it left off.
# Be careful with this being turned on between different models.
auto_resume_from_checkpoints: false