Hugging Face's logo
wing lian's picture
65 5 389

wing lian PRO

winglian
siddhu1716's profile picture Evi1ran's profile picture lee0ray's profile picture
·
winglian
winglian

AI & ML interests

None yet

Organizations

Open-Source AI Meetup's profile picture Open Access AI Collective's profile picture Alignment Lab Ai's profile picture OpenChat's profile picture OpenOrca's profile picture SNB Technologies's profile picture Qwen's profile picture Open Phi's profile picture 2 Year Future Ventures's profile picture textbooks's profile picture ZeroGPU Explorers's profile picture Wynd Network's profile picture Social Post Explorers's profile picture Cognitive Computations's profile picture Amplified 's profile picture Axolotl AI's profile picture

winglian's activity

New activity in NousResearch/Hermes-2-Pro-Llama-3-8B 17 days ago

add axolotl tag
#1 opened 17 days ago by winglian
New activity in mattshumer/Llama-3-8B-16K 25 days ago

add axolotl tag
#3 opened 25 days ago by winglian
New activity in cognitivecomputations/dolphin-2.9-llama3-8b 27 days ago

add axolotl tag
#12 opened 27 days ago by winglian
New activity in openbmb/Eurus-RM-7b 28 days ago

Enable flash_attention_2 support since the underlying Mistral model supports it
#3 opened 28 days ago by winglian
New activity in meta-llama/Meta-Llama-3-8B 30 days ago

Rename original/tokenizer.model to tokenizer.model

2
#6 opened 30 days ago by winglian
commented a paper about 1 month ago
New activity in PrunaAI/dbrx-base-bnb-4bit about 2 months ago

invalid weights doesn't match modeling code

1
#3 opened about 2 months ago by winglian
New activity in SinclairSchneider/dbrx-base-quantization-fixed about 2 months ago

reduce verbosity of logging
#1 opened about 2 months ago by winglian
New activity in databricks/dbrx-instruct about 2 months ago

The fused expert parameters means load_in_4bit doesn't work properly, nor does LoRA

31
#10 opened about 2 months ago by tdrussell
New activity in LnL-AI/dbrx-base-converted-v2 about 2 months ago

reduce logging verbosity

1
#3 opened about 2 months ago by winglian
New activity in SinclairSchneider/dbrx-instruct-quantization-fixed about 2 months ago

dbrx-base

1
#2 opened about 2 months ago by winglian
New activity in ai21labs/Jamba-v0.1 about 2 months ago

finetuning issues

2
#9 opened about 2 months ago by winglian

Fix bias logic to enable QLoRA finetuning

3
#5 opened about 2 months ago by winglian
New activity in cerebras/SlimPajama-627B 5 months ago

Trouble with streaming

6
#5 opened 9 months ago by andersonbcdefg
New activity in HuggingFaceH4/open_llm_leaderboard 6 months ago

latest commit breaks ability to submit mistral finetunes

4
#410 opened 6 months ago by winglian
New activity in Open-Orca/Mistral-7B-OpenOrca 6 months ago

Can you share the training configuration of Axolotl?

3
#24 opened 6 months ago by timlim123
New activity in HuggingFaceH4/open_llm_leaderboard 6 months ago

possible model failure?

1
#403 opened 6 months ago by winglian

please remove openaccess-ai-collective/grendel

3
#387 opened 6 months ago by winglian

Unable to submit public models for evaluation

1
#379 opened 6 months ago by winglian
New activity in Open-Orca/SlimOrca-Dedup 7 months ago

minhash deduping

1
#2 opened 7 months ago by winglian
New activity in crumb/c4-benchfilter-nano 7 months ago

Script to run against more of c4?
#2 opened 7 months ago by winglian
New activity in stabilityai/stablelm-3b-4e1t 8 months ago

fix get_input_embdeddings

1
#3 opened 8 months ago by winglian
New activity in microsoft/phi-1_5 8 months ago

Attention mask not working during training

7
#34 opened 8 months ago by codegood
New activity in PygmalionAI/pygmalion-2-13b 8 months ago

add axolotl badge to readme

1
#1 opened 8 months ago by winglian
New activity in PygmalionAI/pygmalion-2-7b 8 months ago

add axolotl badge to readme
#2 opened 8 months ago by winglian
New activity in PygmalionAI/mythalion-13b 8 months ago

Add axolotl badge to readme
#1 opened 8 months ago by winglian
New activity in microsoft/phi-1_5 8 months ago

add _no_split_modules property
#17 opened 8 months ago by winglian
New activity in garage-bAInd/Platypus2-13B 9 months ago

Dataset

3
#1 opened 9 months ago by winglian
New activity in Open-Orca/OpenOrcaxOpenChat-Preview2-13B 10 months ago

Unreliable Benchmarks. Definitely worse than LLaMA2-13b

3
#5 opened 10 months ago by anon7463435254
New activity in eugenepentland/oo-packing-checkpoint-15000 10 months ago

Upload 3 files
#1 opened 10 months ago by winglian
New activity in winglian/t5-large-flan-cot 10 months ago

Adding `safetensors` variant of this model
#1 opened 10 months ago by SFconvertbot
New activity in openaccess-ai-collective/openllama-7b-4k 11 months ago

What does the 4k stand for?

2
#1 opened 11 months ago by flashvenom
New activity in openaccess-ai-collective/hippogriff-30b-chat 11 months ago

Will you consider releasing a public dataset?

3
#1 opened 12 months ago by Jackdiy

Set use_cache to True, otherwise inference performance is poor
#2 opened 12 months ago by TheBloke
New activity in CarperAI/pythia-6.9b-deduped-4k 12 months ago

inference with anything over 2k tokens causes the following error.
#1 opened 12 months ago by winglian
New activity in mosaicml/mpt-7b 12 months ago

upstream-replit-updates

4
#43 opened 12 months ago by winglian
commented a paper 12 months ago
New activity in TheBloke/WizardLM-30B-Uncensored-GPTQ 12 months ago

Will this work with the Local LLMs One-Click UI runpod?

7
#2 opened 12 months ago by nichedreams
New activity in openaccess-ai-collective/manticore-13b 12 months ago

can you provie the data process demo before train llms?

2
#7 opened 12 months ago by scall
New activity in openaccess-ai-collective/jeopardy-bot 12 months ago

Token length 3908?

1
#1 opened 12 months ago by Yhyu13
New activity in openaccess-ai-collective/StableLManticore-7B 12 months ago

Is this based on LLaMA?

1
#1 opened 12 months ago by Yhyu13
New activity in openaccess-ai-collective/lora-experiments-quant-to-full-weights 12 months ago

What model is this?

1
#1 opened 12 months ago by Yhyu13
New activity in openaccess-ai-collective/manticore-13b 12 months ago

epoch 3 final? or 4 coming?

1
#6 opened 12 months ago by faisalhr1997
New activity in BlinkDL/rwkv-4-pileplus 12 months ago

14B
#1 opened 12 months ago by winglian
New activity in openaccess-ai-collective/mpt-7b-wizardlm 12 months ago

fine-tuning script notebook

4
#1 opened about 1 year ago by g30rv17ys
New activity in openaccess-ai-collective/manticore-13b 12 months ago

Some suggestions for optimization

10
#3 opened 12 months ago by polymer

specific instruct prompt to use

3
#2 opened 12 months ago by digitous

What inputs does the model expect?

1
#4 opened 12 months ago by AlmightYariv
New activity in openaccess-ai-collective/wizard-mega-13b 12 months ago

Prompt format contradiction

2
#5 opened about 1 year ago by 2EyeGuy
New activity in openaccess-ai-collective/manticore-13b 12 months ago

Difference with Wizzard Mega

1
#1 opened 12 months ago by frandmb
New activity in openaccess-ai-collective/wizard-mega-13b about 1 year ago

Fine-tune specific details

6
#2 opened about 1 year ago by polymer
New activity in P1ayer-1/chatgpt-conversations-chatlogs.net about 1 year ago

v1 vs v2

1
#1 opened about 1 year ago by winglian
New activity in openaccess-ai-collective/ggml-ui about 1 year ago

Apply for community grant: Personal project

1
#1 opened about 1 year ago by winglian
New activity in theblackcat102/reward-deberta-v3-large-aspect about 1 year ago

training code
#1 opened about 1 year ago by winglian
New activity in openaccess-ai-collective/wizard-mega-13b about 1 year ago

Change cache = true in config.json to significantly boost inference performance

1
#1 opened about 1 year ago by TheBloke
New activity in mosaicml/mpt-7b about 1 year ago

Can this be fine-tuned with triton backed flash attention and alibi using the huggingface transformers trainer?

1
#13 opened about 1 year ago by winglian
New activity in TehVenom/MPT-7b-Chat-Instruct-LongCTX-Merge about 1 year ago

weighted average?

1
#4 opened about 1 year ago by winglian
New activity in chtan/gpt4-alpaca-lora_mlp-65b about 1 year ago

MLP vs Self Attention

1
#1 opened about 1 year ago by winglian
New activity in OpenAssistant/oasst-sft-6-llama-30b-xor about 1 year ago

training code

1
#31 opened about 1 year ago by winglian
New activity in OpenAssistant/oasst-sft-7-llama-30b-xor about 1 year ago

what is the difference between oasst-sft-7-llama-30b-xor oasst-sft-6-llama-30b-xor?

2
#1 opened about 1 year ago by Surface