Hugging Face's logo
wing lian's picture
65 5 392

wing lian PRO

winglian
Hamabak's profile picture chaocrypto's profile picture reogine'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 about 1 month ago

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

add axolotl tag
#3 opened about 1 month ago by winglian
New activity in cognitivecomputations/dolphin-2.9-llama3-8b about 1 month ago

add axolotl tag
#12 opened about 1 month ago by winglian
New activity in openbmb/Eurus-RM-7b about 1 month ago

Enable flash_attention_2 support since the underlying Mistral model supports it
#3 opened about 1 month ago by winglian
New activity in meta-llama/Meta-Llama-3-8B about 2 months ago

Rename original/tokenizer.model to tokenizer.model

3
#6 opened about 2 months ago by winglian
commented a paper 2 months ago
New activity in PrunaAI/dbrx-base-bnb-4bit 2 months ago

invalid weights doesn't match modeling code

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

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

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

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

reduce logging verbosity

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

dbrx-base

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

finetuning issues

2
#9 opened 2 months ago by winglian

Fix bias logic to enable QLoRA finetuning

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

Trouble with streaming

6
#5 opened 10 months ago by andersonbcdefg
New activity in open-llm-leaderboard/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 open-llm-leaderboard/open_llm_leaderboard 6 months ago

possible model failure?

1
#403 opened 6 months ago by winglian
New activity in open-llm-leaderboard/open_llm_leaderboard 7 months ago

please remove openaccess-ai-collective/grendel

3
#387 opened 7 months ago by winglian

Unable to submit public models for evaluation

1
#379 opened 7 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 9 months ago

add axolotl badge to readme

1
#1 opened 9 months ago by winglian
New activity in PygmalionAI/pygmalion-2-7b 9 months ago

add axolotl badge to readme
#2 opened 9 months ago by winglian
New activity in PygmalionAI/mythalion-13b 9 months ago

Add axolotl badge to readme
#1 opened 9 months ago by winglian
New activity in microsoft/phi-1_5 9 months ago

add _no_split_modules property
#17 opened 9 months ago by winglian
New activity in garage-bAInd/Platypus2-13B 10 months ago

Dataset

3
#1 opened 10 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 11 months ago

Upload 3 files
#1 opened 11 months ago by winglian
New activity in winglian/t5-large-flan-cot 11 months ago

Adding `safetensors` variant of this model
#1 opened 11 months ago by SFconvertbot
New activity in openaccess-ai-collective/openllama-7b-4k 12 months ago

What does the 4k stand for?

2
#1 opened 12 months ago by flashvenom
New activity in openaccess-ai-collective/hippogriff-30b-chat 12 months ago

Will you consider releasing a public dataset?

3
#1 opened about 1 year ago by Jackdiy

Set use_cache to True, otherwise inference performance is poor
#2 opened about 1 year ago by TheBloke
New activity in CarperAI/pythia-6.9b-deduped-4k about 1 year ago

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

upstream-replit-updates

4
#43 opened about 1 year ago by winglian
commented a paper about 1 year ago
New activity in TheBloke/WizardLM-30B-Uncensored-GPTQ about 1 year ago

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

7
#2 opened about 1 year ago by nichedreams
New activity in openaccess-ai-collective/manticore-13b about 1 year ago

can you provie the data process demo before train llms?

2
#7 opened about 1 year ago by scall
New activity in openaccess-ai-collective/jeopardy-bot about 1 year ago

Token length 3908?

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

Is this based on LLaMA?

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

What model is this?

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

epoch 3 final? or 4 coming?

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

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

fine-tuning script notebook

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

Some suggestions for optimization

10
#3 opened about 1 year ago by polymer

specific instruct prompt to use

3
#2 opened about 1 year ago by digitous

What inputs does the model expect?

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

Prompt format contradiction

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

Difference with Wizzard Mega

1
#1 opened about 1 year 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