Hugging Face's logo

Spaces:
Dovakiins
/
qwerrwe
Build error

App Files Community
qwerrwe / src

Commit History

standardize attn hijack patches (#381)
06edf17
unverified

tmm1 winglian commited on

fix orca prompts (#422)
1b7e860
unverified

winglian commited on

Fix(config): Update handling of deepspeed config (#404)
c01015f
unverified

Nanobit commited on

fix eval steps and strategy (#403)
da10af0
unverified

winglian commited on

better handling of empty input ids when tokenizing (#395)
85cf4f8
unverified

winglian commited on

add utils.data.prepare_dataset
2e22404

tmm1 commited on

use context manager to run things on rank0 before others (#397)
fc2d6be
unverified

winglian commited on

don't use mask expansion for inference (#392)
1687be6
unverified

winglian commited on

Feat(config): add max steps (#387)
3c2ad00
unverified

ittailup commited on

Added "epoch" evaluation_strategy (#388)
5d48a10
unverified

flotos commited on

Feat(config): Add hub_strategy (#386)
73a0b6e
unverified

Nanobit commited on

Error msg for sharegpt if conv has less than 2 msg (#379)
63fdb5a
unverified

flotos commited on

don't pass rope_scaling kwarg if it's None (#383)
919246f
unverified

winglian commited on

Fix crash when running without CUDA
15f6e57

chargoddard commited on

try to detect accelerate and only use device_map=None in that case (#373)
094fc2c
unverified

tmm1 commited on

fix check for flash attn branching (#377)
343ac84
unverified

winglian commited on

remove unnecessary local variable
0c96727

tmm1 commited on

simplify `load_tokenizer`
efb3b2c

tmm1 commited on

improve GPU logging to break out pytorch cache and system mem
7b55fe6

tmm1 commited on

quiet noise from llama tokenizer by setting pad token earlier
e029ab3

tmm1 commited on

extract module for working with cfg
8cec513

tmm1 commited on

fix DefaultDict.__or__
a13e45d

tmm1 commited on

Attention mask and position id fixes for packing (#285)
2bb0b78
unverified

winglian commited on

Add wandb_entity to wandb options, update example configs, update README (#361)
7019509
unverified

Morgan McGuire Morgan McGuire winglian commited on

Fix(model loading): Warn when model revision is passed to gptq (#364)
96bd6ae
unverified

Nanobit commited on

Fix(message): Improve error message for bad format (#365)
e37d935
unverified

Nanobit commited on

Feat: Add rope scaling (#343)
b521206
unverified

Nanobit commited on

Merge pull request #356 from tmm1/load_model-args
11ddccb
unverified

tmm1 commited on

simplify load_model signature
7181022

tmm1 commited on

log GPU memory usage
e303d64

tmm1 commited on

ensure enable_input_require_grads is called on model before getting the peft model (#345)
176b888
unverified

winglian commited on

experimental llama 2 chat support (#296)
3392270
unverified

Jan Philipp Harries Jan Philipp Harries commited on

Update XFormers Attention Monkeypatch to handle Llama-2 70B (GQA) (#339)
10405b9
unverified

ssmi153 commited on

Added Orca Mini prompt strategy (#263)
c93655c
unverified

Jan Philipp Harries Jan Philipp Harries commited on

optimize the iteration when tokenizeing large datasets (#332)
fe28543
unverified

winglian commited on

fix typo
2eda9e0

tmm1 commited on

scope flash-attn+qlora fix correctly, scope to llama, add comment
78b9efb

tmm1 commited on

move flash-attn monkey patch alongside the others
312a9fa

tmm1 commited on

ensure flash-attn fixes happen in both adapter/lora modes, and use torch_dtype
248bf90

tmm1 commited on

qlora w flash attention fixes (#333)
77085ea
unverified

winglian commited on

add peft install back since it doesn't get installed by setup.py (#331)
db2a358
unverified

winglian commited on

update prompts for open orca to match the paper (#317)
3d4984b
unverified

winglian commited on

Merge pull request #307 from OpenAccess-AI-Collective/xgen-user-sharegpt-tokens
40a53ff
unverified

winglian commited on

Merge pull request #313 from OpenAccess-AI-Collective/tokenizer-llama2-embeddings
3ffb018
unverified

winglian commited on

don't resize embeddings to multiples of 32x by default
1066751

winglian commited on

better handling since xgen tokenizer breaks with convert_tokens_to_ids
2a428e8

winglian commited on

flash attention 2
9b790d3

winglian commited on

fix sdp attention to use the flash/mem-efficient context manaager
a032c9f

winglian commited on

feat: use multi-core
45ac7c4

Nanobit commited on