Update peft requirement from <0.14,>=0.10.0 to >=0.10.0,<0.15

[dependabot]

Updates the requirements on peft to permit the latest version.

Release notes

Sourced from peft's releases.

Version 0.14.0: EVA, Context-aware Prompt Tuning, Bone, and more

Highlights

New Methods

Context-aware Prompt Tuning

@​tsachiblau added a new soft prompt method called Context-aware Prompt Tuning (CPT) which is a combination of In-Context Learning and Prompt Tuning in the sense that, for each training sample, it builds a learnable context from training examples in addition to the single training sample. Allows for sample- and parameter-efficient few-shot classification and addresses recency-bias.

Explained Variance Adaptation

@​sirluk contributed a new LoRA initialization method called Explained Variance Adaptation (EVA). Instead of randomly initializing LoRA weights, this method uses SVD of the base layer weights to initialize the LoRA weights and is also able to re-allocate the ranks of the adapter based on the explained variance ratio (derived from SVD). Thus, this initialization method can yield better initial values and better rank distribution.

Bone

@​JL-er added an implementation for Block Affine (Bone) Adaptation which utilizes presumed sparsity in the base layer weights to divide them into multiple sub-spaces that share a single low-rank matrix for updates. Compared to LoRA, Bone has the potential to significantly reduce memory usage and achieve faster computation.

Enhancements

PEFT now supports LoRAs for int8 torchao quantized models (check this and this notebook) . In addition, VeRA can now be used with 4 and 8 bit bitsandbytes quantization thanks to @​ZiadHelal.

Hot-swapping of LoRA adapters is now possible using the hotswap_adapter function. Now you are able to load one LoRA and replace its weights in-place with the LoRA weights of another adapter which, in general, should be faster than deleting one adapter and loading the other adapter in its place. The feature is built so that no re-compilation of the model is necessary if torch.compile was called on the model (right now, this requires ranks and alphas to be the same for the adapters).

LoRA and IA³ now support Conv3d layers thanks to @​jsilter, and @​JINO-ROHIT added a notebook showcasing PEFT model evaluation using lm-eval-harness toolkit.

With the target_modules argument, you can specify which layers to target with the adapter (e.g. LoRA). Now you can also specify which modules not to target by using the exclude_modules parameter (thanks @​JINO-ROHIT).

Changes

• There have been made several fixes to the OFT implementation, among other things, to fix merging, which makes adapter weights trained with PEFT versions prior to this release incompatible (see #1996 for details).
• Adapter configs are now forward-compatible by accepting unknown keys.
• Prefix tuning was fitted to the DynamicCache caching infrastructure of transformers (see #2096). If you are using this PEFT version and a recent version of transformers with an old prefix tuning checkpoint, you should double check that it still works correctly and retrain it if it doesn't.
• Added lora_bias parameter to LoRA layers to enable bias on LoRA B matrix. This is useful when extracting LoRA weights from fully fine-tuned parameters with bias vectors so that these can be taken into account.
• #2180 provided a couple of bug fixes to LoKr (thanks @​yaswanth19). If you're using LoKr, your old checkpoints should still work but it's recommended to retrain your adapter.
• from_pretrained now warns the user if PEFT keys are missing.
• Attribute access to modules in modules_to_save is now properly and transparently handled.
• PEFT supports the changes to bitsandbytes 8bit quantization from the recent v0.45.0 release. To benefit from these improvements, we thus recommend to upgrade bitsandbytes if you're using QLoRA. Expect slight numerical differences in model outputs if you're using QLoRA with 8bit bitsandbytes quantization.

What's Changed

• Bump version to 0.13.1.dev0 by @​BenjaminBossan in huggingface/peft#2094
• Support Conv3d layer in LoRA and IA3 by @​jsilter in huggingface/peft#2082
• Fix Inconsistent Missing Keys Warning for Adapter Weights in PEFT by @​yaswanth19 in huggingface/peft#2084
• FIX: Change check if past_key_values is empty by @​BenjaminBossan in huggingface/peft#2106
• Update install.md by @​Salehbigdeli in huggingface/peft#2110
• Update OFT to fix merge bugs by @​Zeju1997 in huggingface/peft#1996
• ENH: Improved attribute access for modules_to_save by @​BenjaminBossan in huggingface/peft#2117
• FIX low_cpu_mem_usage consolidates devices by @​BenjaminBossan in huggingface/peft#2113
• TST Mark flaky X-LoRA test as xfail by @​BenjaminBossan in huggingface/peft#2114
• ENH: Warn when from_pretrained misses PEFT keys by @​BenjaminBossan in huggingface/peft#2118
• FEAT: Adding exclude modules param(#2044) by @​JINO-ROHIT in huggingface/peft#2102
• fix merging bug / update boft conv2d scaling variable by @​Zeju1997 in huggingface/peft#2127

... (truncated)

Commits

• de88c70 Prepare for PEFT release of v0.14.0 (#2258)
• 860f783 ENH: Updates for upcoming BNB Int8 release (#2245)
• 15712db FIX Prevent CUDA context initialization due to AWQ (#2230)
• f86522e FIX Correctly determine word embeddings on Deberta (#2257)
• c057589 FIX Correctly pass low_cpu_mem_usage argument (#2253)
• 3f9ce55 DOC Update CPT docs, add example (#2229)
• 131efba FIX TST Small regression in BNB LoRA output (#2238)
• 943daf1 ENH Argument to enable bias for LoRA B (#2237)
• 60978d7 ENH Improvements to Bone method (#2233)
• 34e15be Bump version of MacOS from 12 to 13 (#2235)
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot merge will merge this PR after your CI passes on it
• @dependabot squash and merge will squash and merge this PR after your CI passes on it
• @dependabot cancel merge will cancel a previously requested merge and block automerging
• @dependabot reopen will reopen this PR if it is closed
• @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

[dependabot]

OK, I won't notify you again about this release, but will get in touch when a new version is available. If you'd rather skip all updates until the next major or minor version, let me know by commenting @dependabot ignore this major version or @dependabot ignore this minor version. You can also ignore all major, minor, or patch releases for a dependency by adding an ignore condition with the desired update_types to your config file.

If you change your mind, just re-open this PR and I'll resolve any conflicts on it.