Custom 4-bit Finetuning 5-7 times faster inference than QLora
pinned
1
#13 opened about 1 year ago
by
rmihaylov
How to make it work for less experienced AI whisperers
pinned
17
#4 opened about 1 year ago
by
Sloba
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6432f4e34521083b9d286a48/v9bX1bMorcB7XWlmG2aUi.jpeg)
Support for LoRA?
pinned
17
#3 opened about 1 year ago
by
cekal
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63ebfd71ca08a72ba9ce6fe0/WEXOVko_Lgvq_Y8_Zlb4o.png)
Two repeated errors in model output
1
#102 opened 2 months ago
by
virilo
ValueError: The current `device_map` had weights offloaded to the disk.
#101 opened 3 months ago
by
MohamedZouabi
Why does falcon-7b have 71 attention heads?
1
#100 opened 3 months ago
by
alpindale
![](https://cdn-avatars.huggingface.co/v1/production/uploads/635567189c72a7e742f1419c/tbfBz0furS-y4ISgoe6j0.jpeg)
Creating vectordatabse using the falcon-7b model embeddings.
#99 opened 4 months ago
by
alchemistPS01
FalconForCausalLM does not support Flash Attention 2.0 yet
#98 opened 5 months ago
by
Menouar
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/SSICrZQNeRxTOvatt90ym.jpeg)
Error while trying to load model
#96 opened 6 months ago
by
dwojcik
Adding `safetensors` variant of this model
#95 opened 7 months ago
by
SFconvertbot
![](https://cdn-avatars.huggingface.co/v1/production/uploads/635fd4cc14657fb8cff2a081/GDkyDwAcuqDBpaOvQgJuq.png)
Adding Evaluation Results
#94 opened 7 months ago
by
leaderboard-pr-bot
![](https://cdn-avatars.huggingface.co/v1/production/uploads/655506df9dc61e22c5f9c732/IZGvup0FdVlioPPIPnzZv.jpeg)
Model does not know when to stop generating text?
#93 opened 7 months ago
by
jashsayani
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64784fb2c43296134a43135d/ZQYeP21wlw_onpn5UPbHu.jpeg)
Could we machine translatation task using this model?
2
#91 opened 8 months ago
by
Pitambarmuduli
Falcon-7B decoding error
#90 opened 8 months ago
by
rahulseetharaman
[AUTOMATED] Model Memory Requirements
#89 opened 8 months ago
by
model-sizer-bot
Upload configuration_RW.py
#88 opened 8 months ago
by
imranshah
Upload configuration_RW.py
#87 opened 8 months ago
by
imranshah
Getting: HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/tiiuae/falcon-7b/resolve/main/configuration_RW.py
1
#86 opened 9 months ago
by
f5-lolabhattu
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6441482c603214724ebd0f5f/0SXKf9U2ykTDL-SV09QK1.jpeg)
What does this file do? modeling_falcon.py
#85 opened 9 months ago
by
Tony068
Anyone discovered "Mini" yet in prompting?
#83 opened 9 months ago
by
YoYo1234Qwerty
How to avoid running into memory/ storage problems associated with HF Spaces while using tiiuae/falcon-7b 0r 40b etc.,
4
#82 opened 9 months ago
by
vsrinivas
Update generation_config.json
1
#81 opened 9 months ago
by
nkasmanoff
![](https://cdn-avatars.huggingface.co/v1/production/uploads/60d3850107da9c17c7270912/WzhEbEvjunrDJ2IpdOxtZ.png)
ValueError: Unrecognized configuration class <class 'transformers_modules.falcon-7b.configuration_RW.RWConfig'> for this kind of AutoModel....
2
#80 opened 9 months ago
by
Inoob
RuntimeError: CUDA error: CUBLAS_STATUS_NOT_SUPPORTED
#79 opened 9 months ago
by
ConorVanek
ImportError: Using `load_in_8bit=True` requires Accelerate
3
#78 opened 10 months ago
by
aimananees
Adding `safetensors` variant of this model
#77 opened 10 months ago
by
bikalnetomi
Use input attention mask instead of casual mask in attention
#76 opened 10 months ago
by
CyberZHG
Question answering task with falcon model fails with "TypeError: forward() got an unexpected keyword argument 'token_type_ids'"
1
#75 opened 10 months ago
by
karolzak13
Inaccurate number of parameters
1
#74 opened 11 months ago
by
mohamedlotfy50
Title: Best Practice for Handling Variable-Length Sequences in Training an LLM Model on a Chatbot Dataset
#73 opened 11 months ago
by
humza-sami
![](https://cdn-avatars.huggingface.co/v1/production/uploads/633d6d4f48ab6a0add2ce1a3/qTO75kR0hk1Yn1SaP7ZPb.jpeg)
Can't use the model load locally
1
#72 opened 11 months ago
by
Alouettewind
Falcon 7b instruct using cpu for inference even on NVIDIA A40 cards with 50GB VRAM
#70 opened 11 months ago
by
Akshadv
Why is alibi: false in the config.json?
#69 opened 11 months ago
by
ekurtic
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1668801593252-628e0ce4e53bbd334577fcb0.jpeg)
getting error
1
#67 opened 11 months ago
by
Akash1267a
Revert in-library commit
#65 opened 11 months ago
by
Rocketknight1
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1660312628256-60ba519750effef3a58beac3.png)
Senior ML Scientist
#63 opened 11 months ago
by
FinTrU-TA
OSError: tiiuae/falcon-7b does not appear to have a file named configuration_RW.py
5
#62 opened 11 months ago
by
chintan4560
about eos and bos token id
1
#61 opened 11 months ago
by
louisY
configuration_RW.py missing in latest commit
9
#60 opened 11 months ago
by
ravikiran3690
Inference time issue
#59 opened 11 months ago
by
amnasher
Update generation_config.json
#55 opened 12 months ago
by
psinger
![](https://cdn-avatars.huggingface.co/v1/production/uploads/636d18755aaed143cd6698ef/AalDh13Gp8jv1BfM5IASh.png)
Fine-tuning issues
1
#53 opened 12 months ago
by
nebulae7
How to push or shere adapter to the hub?
7
#52 opened 12 months ago
by
Imran1
![](https://cdn-avatars.huggingface.co/v1/production/uploads/62846faa99bff5076f0a93b4/QO7sgRWOXS6nlQ-GcEg94.jpeg)
Getting an error: RuntimeError: shape '[x, 71, 64]' is invalid for input of size 3904
#51 opened 12 months ago
by
Carolinehu
Getting an error TypeError: unsupported operand type(s) for *: 'Tensor' and 'NoneType'
7
#49 opened 12 months ago
by
NajiAboo
Fix typo in `README.md`
#48 opened 12 months ago
by
alvarobartt
![](https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg)
Model Inference with trust_remote_code=False
#47 opened 12 months ago
by
eranhe
Trying to understand internals of falcon
1
#46 opened 12 months ago
by
MorphzZ
No Output is generated, Running on Cloud
#45 opened 12 months ago
by
Yassin-sameh