Hugging Face's logo
Maxime Labonne's picture
214 92 626

Maxime Labonne PRO

mlabonne
CultriX's profile picture leonardlin's profile picture ahmedmalek185's profile picture
·
https://mlabonne.github.io/blog
maximelabonne
mlabonne

AI & ML interests

Post-training, model editing, quantization

Articles

Organizations

Blog-explorers's profile picture Qwen's profile picture ZeroGPU Explorers's profile picture Social Post Explorers's profile picture Merge Crew's profile picture Liquid AI's profile picture

mlabonne's activity

New activity in mlabonne/FrankenLlama-3-12B-Instruct 4 days ago

Сan you increase LLAMA3 8b simply by duplicating some layers?

3
#2 opened 5 days ago by Regrin
New activity in mlabonne/chessllm 8 days ago

chess

1
#2 opened 9 days ago by LeroyDyer
New activity in ucalyptus/prem-615M-chat 8 days ago

How to up-merge?

1
#1 opened 8 days ago by ucalyptus
New activity in mlabonne/Meta-Llama-3-120B-Instruct 10 days ago

fix snippet

1
#8 opened 10 days ago by philschmid

fine-tuning is needed after self-merging?

1
#7 opened 10 days ago by oodgnas

Why did you convert to float16 and not bfloat16?

1
#6 opened 10 days ago by PhilipMay
New activity in mlabonne/Meta-Llama-3-120B-Instruct 11 days ago

How to score the creative writing

1
#5 opened 11 days ago by zhouzr
New activity in mlabonne/FrankenLlama-3-12B-Instruct 11 days ago

How good is this model?

1
#1 opened 11 days ago by Regrin
New activity in mlabonne/Meta-Llama-3-120B-Instruct 12 days ago

Attention, stupid question

2
#4 opened 12 days ago by Debich
New activity in mlabonne/Meta-Llama-3-225B-Instruct 12 days ago

mergekit config pls :)

4
#1 opened 13 days ago by ehartford
New activity in mlabonne/Meta-Llama-3-120B-Instruct 13 days ago

Would love to try a quantized version!

27
#2 opened 16 days ago by dillfrescott

Mention?

1
#3 opened 13 days ago by ehartford
New activity in mlabonne/NeuralMonarch-7B 15 days ago

Could you please share the merging config with us?

1
#3 opened 15 days ago by PhilipMay
New activity in mlabonne/AlphaMonarch-7B 15 days ago

Could you please share the merging config with us?

1
#7 opened 15 days ago by PhilipMay
New activity in HuggingFaceH4/open_llm_leaderboard 15 days ago

Resubmit mlabonne/OrpoLlama-3-8B

7
#725 opened 17 days ago by mlabonne
New activity in mlabonne/Meta-Llama-3-120B-Instruct 16 days ago

C_H_U_N_K_Y-L_L_A_M_A

1
#1 opened 16 days ago by rombodawg
New activity in Muhammad2003/OrpoLlama3-8B 17 days ago

Base model

3
#1 opened 17 days ago by mlabonne
New activity in lilacai/lilac 21 days ago

Runtime error
#2 opened 21 days ago by mlabonne
New activity in mlabonne/arena-preferences 21 days ago

Librarian Bot: Add language metadata for dataset
#2 opened 21 days ago by librarian-bot
New activity in mlabonne/ChimeraLlama-3-8B-v2 24 days ago

Any plans on uploading the model itself?

2
#2 opened 24 days ago by bartowski
New activity in mlabonne/ChimeraLlama-3-8B 24 days ago

Create generation_config.json

1
#1 opened 24 days ago by bartowski
New activity in mlabonne/ChimeraLlama-3-8B-v2 24 days ago

for your consideration

4
#1 opened 24 days ago by LaferriereJC
New activity in mlabonne/arena-preferences 25 days ago

[bot] Conversion to Parquet
#1 opened 25 days ago by parquet-converter
New activity in flytech/python-codes-25k 26 days ago

Question about dataset generation

4
#3 opened 26 days ago by mlabonne
New activity in mlabonne/OrpoLlama-3-8B 26 days ago

Repetition from tuning via https://huggingface.co/blog/mlabonne/orpo-llama-3

4
#2 opened 27 days ago by Satya93
New activity in mlabonne/Llama-3-SLERP-8B 26 days ago

What's the purpose of this?

4
#1 opened 29 days ago by xms991
New activity in mlabonne/OrpoLlama-3-8B 26 days ago

Update README.md

2
#3 opened 26 days ago by hadraoui
New activity in mlabonne/OrpoLlama-3-8B 28 days ago

Looking forward to full release!

4
#1 opened 29 days ago by bartowski
New activity in mlabonne/orpo-dpo-mix-40k 29 days ago

Suggestion

1
#3 opened 29 days ago by neovalle
New activity in mlabonne/orpo-dpo-mix-40k 30 days ago

Great job!

3
#2 opened 30 days ago by alvarobartt

[bot] Conversion to Parquet
#1 opened about 1 month ago by parquet-converter
New activity in mlabonne/chatml_dpo_pairs about 1 month ago

Add DPO tag

1
#2 opened about 1 month ago by davanstrien
New activity in mlabonne/Yet_Another_LLM_Leaderboard about 1 month ago

The like metric values are not correct...

1
#11 opened about 1 month ago by zhiminy
New activity in automerger/YamshadowExperiment28-7B about 1 month ago

Update README.md
#3 opened about 1 month ago by mlabonne

Update README.md
#2 opened about 1 month ago by mlabonne

Update README.md
#1 opened about 1 month ago by mlabonne
New activity in mlabonne/NeuralHermes-2.5-Mistral-7B about 1 month ago

W&B Link Returns 404

2
#10 opened about 1 month ago by ZennyKenny
New activity in mlabonne/NeuralBeagle14-7B about 1 month ago

Adding Evaluation Results
#10 opened about 1 month ago by dragonSwing
New activity in mlabonne/Zebrafish-7B about 1 month ago

ty!

1
#1 opened about 1 month ago by gate369
New activity in mlabonne/UltraMerge-7B about 1 month ago

Dataset

2
#2 opened about 1 month ago by mrfakename

License

2
#3 opened about 1 month ago by mrfakename
New activity in mlabonne/Jambalpaca-v0.1 about 2 months ago

Jamba Notebook

2
#1 opened about 2 months ago by Severian
New activity in mlabonne/AlphaMonarch-7B-2bit-HQQ about 2 months ago

Amazing model

4
#1 opened about 2 months ago by CatUkraine
New activity in mlabonne/UltraMerge-7B about 2 months ago

🚩 Report

3
#1 opened about 2 months ago by electroglyph
New activity in mlabonne/ultrafeedback-binarized-preferences-cleaned about 2 months ago

Librarian Bot: Add language metadata for dataset
#1 opened about 2 months ago by librarian-bot
New activity in macadeliccc/Mistral-7B-v0.2-OpenHermes about 2 months ago

Evaluation

1
#1 opened about 2 months ago by mlabonne
New activity in mlabonne/Beyonder-4x7B-v3 about 2 months ago

AQLM version please

2
#2 opened about 2 months ago by AiModelsMarket

About Moe vocab extended model with non vocab extended model

1
#3 opened about 2 months ago by ancv
New activity in mlabonne/Beyonder-4x7B-v3-GGUF about 2 months ago

Excellent work on this, sir!

3
#2 opened about 2 months ago by dillfrescott
New activity in mlabonne/Beyonder-4x7B-v3 about 2 months ago

Add Exl2 quant link

2
#1 opened about 2 months ago by bartowski
New activity in mlabonne/Beyonder-4x7B-v3-GGUF about 2 months ago

Update README.md

2
#1 opened about 2 months ago by kgourgou
New activity in mlabonne/FrankenMonarch-7B about 2 months ago

Why merge the same model 5 times?

2
#1 opened about 2 months ago by UniversalLove333

add GGUF link
#2 opened about 2 months ago by seyf1elislam
New activity in mlabonne/AutoMerger 2 months ago

I had a similar idea recently

2
#5 opened 2 months ago by CultriX
New activity in mlabonne/Yet_Another_LLM_Leaderboard 2 months ago

Reasoning behind including TruthfulQA?

1
#10 opened 2 months ago by Phil337
New activity in mlabonne/AutoMerger 2 months ago

allow multiple people to access automerger at once

2
#6 opened 2 months ago by mrfakename
New activity in mlabonne/llm-auto-eval 2 months ago

Multiple GPU's

2
#3 opened 2 months ago by CultriX
New activity in mlabonne/gemma-7b-it-GGUF 2 months ago

Failed to load

5
#3 opened 3 months ago by Priderock
New activity in mlabonne/gemma-2b-it-GGUF 2 months ago

Model Type in ctransformers to use gguf gemma

1
#1 opened 2 months ago by aryachakraborty
New activity in mlabonne/AutoMerger 2 months ago

'utf-8' codec can't decode byte 0x96 in position 789: invalid start byte

3
#4 opened 2 months ago by mrfakename