Hugging Face's logo
Francisco's picture
39 24

Francisco

Panchovix
ottobunge's profile picture mooki0's profile picture Dannyboy123's profile picture
·
panchovix

AI & ML interests

ML, Text2Image models, Large Language Models.

Organizations

The Royal Lab's profile picture

Panchovix's activity

New activity in NeverSleep/MiquMaid-v1-70B 4 months ago

Any chance for a 6bpw one?
#3 opened 4 months ago by Panchovix
New activity in Panchovix/goliath-120b-exl2-rpcal 4 months ago

unquantized weights?

1
#8 opened 4 months ago by narutofan125

Example code on running the model?

2
#7 opened 4 months ago by bwzimpel
New activity in Panchovix/goliath-120b-exl2 4 months ago

3bpw spam random words on default settings with oobabooga

4
#2 opened 4 months ago by sergkisel3v
New activity in Panchovix/goliath-120b-exl2-rpcal 4 months ago

Should we expect a version for GGUF?

2
#6 opened 4 months ago by AS1200

Quantitative command?

7
#4 opened 5 months ago by akoyaki

Quantization update?

3
#5 opened 5 months ago by imi2
New activity in Panchovix/goliath-120b-exl2-rpcal 5 months ago

GGUF format?

3
#3 opened 5 months ago by Puchacz19
New activity in royallab/Aetheria-L2-70B 5 months ago

EXL2 Quants

2
#2 opened 5 months ago by OrangeApples
New activity in DiscoResearch/DiscoLM-120b 5 months ago

Summoning EXL2 version ;)

9
#2 opened 5 months ago by wolfram
New activity in Panchovix/goliath-120b-exl2-rpcal 6 months ago

Calibration dataset?

3
#1 opened 7 months ago by brucethemoose
New activity in Panchovix/goliath-120b-exl2-4.25bpw-rpcal 6 months ago

Possible to rpcal a GGUF version?

4
#1 opened 6 months ago by PathosOnSunday
New activity in nsfwthrowitaway69/Venus-120b-v1.0 6 months ago

Nice work! Which dataset did you use for measurement.json?

4
#2 opened 6 months ago by Panchovix
New activity in allenai/tulu-2-dpo-70b 6 months ago

Nice work! The config.json seems to have "max_position_embeddings": 8192, but it doesn't work fine after 4096

1
#1 opened 6 months ago by Panchovix
New activity in migtissera/Tess-XL-v1.0 6 months ago

Any chance for an EXL2 version?

15
#2 opened 6 months ago by wolfram
New activity in Panchovix/goliath-120b-exl2-rpcal 6 months ago

VRAM requirements

2
#2 opened 6 months ago by practical-dreamer
New activity in Panchovix/airoboros-33b-gpt4-1.2-SuperHOT-8k 6 months ago

Adding Evaluation Results
#1 opened 6 months ago by leaderboard-pr-bot
New activity in Panchovix/WizardLM-33B-V1.0-Uncensored-SuperHOT-8k 6 months ago

Adding Evaluation Results
#2 opened 6 months ago by leaderboard-pr-bot
New activity in Panchovix/goliath-120b-exl2 6 months ago

3bpw not working anymore

6
#1 opened 6 months ago by mpasila
New activity in Panchovix/llama-2-70b-Guanaco-QLoRA-fp16-safetensors 7 months ago

Thanks

1
#1 opened 7 months ago by MB7977
New activity in Panchovix/Xwin-LM-70B-V0.1-safetensors 8 months ago

Upload xwin_wizardlm-evol-70k_measurement.json

1
#1 opened 8 months ago by sophosympatheia
New activity in Panchovix/airoboros-l2-70b-gpt4-1.4.1_2.5bpw-h6-exl2 8 months ago

Can you please create a 3-bit file via exllama2?

1
#3 opened 8 months ago by Kotokin

Error parsing message when loading model

6
#2 opened 8 months ago by MasonJ
New activity in Panchovix/airoboros-l2-70b-gpt4-1.4.1-safetensors 8 months ago

Update bin2safetensors/convert.py
#2 opened 8 months ago by Thireus
New activity in Panchovix/airoboros-l2-70b-gpt4-1.4.1_2.5bpw-h6-exl2 8 months ago

Error while loading

2
#1 opened 8 months ago by Nexesenex
New activity in Panchovix/airoboros-l2-70b-gpt4-1.4.1-safetensors 8 months ago

Update bin2safetensors/convert.py

1
#1 opened 8 months ago by Thireus
New activity in Panchovix/airoboros-l2-70b-gpt4-1.4.1_5.0bpw-h6-exl2 8 months ago

Convertion process

3
#1 opened 8 months ago by Thireus
New activity in Panchovix/LLaMA-2-70B-GPTQ-transformers4.32.0.dev0 9 months ago

-chat

1
#1 opened 9 months ago by ehartford
New activity in upstage/Llama-2-70b-instruct 10 months ago

Does this finetune let you use 4096 context?

1
#2 opened 10 months ago by Panchovix
New activity in Panchovix/Guanaco-33B-SuperHOT-8k 11 months ago

This model is not working

5
#1 opened 11 months ago by rombodawg
New activity in Panchovix/WizardLM-33B-V1.0-Uncensored-SuperHOT-8k-4bit-32g 11 months ago

RuntimeError: unable to mmap 19426750144 bytes

3
#3 opened 11 months ago by Leaf45
New activity in kaiokendev/superhot-30b-8k-no-rlhf-test 11 months ago

Thanks for all the hard work! Chance to see superhot-65b?

9
#1 opened 11 months ago by Panchovix
New activity in Panchovix/WizardLM-33B-V1.0-Uncensored-SuperHOT-8k-4bit-32g 11 months ago

Best parameters for 24GB VRAM?

1
#2 opened 11 months ago by Thireus

Prompt format?

1
#1 opened 11 months ago by Thireus
New activity in Panchovix/WizardLM-33B-V1.0-Uncensored-SuperHOT-8k 11 months ago

Prompt format?

1
#1 opened 11 months ago by Thireus
New activity in cognitivecomputations/WizardLM-33B-V1.0-Uncensored 11 months ago

Upload 4 files
#1 opened 11 months ago by Panchovix
New activity in flashvenom/Airoboros-13B-SuperHOT-8K-4bit-GPTQ 11 months ago

Can you be more specific how to use 8k context with ExLLama in Oobabooga?

4
#3 opened 11 months ago by justsumguy
New activity in Peeepy/Airoboros-33b-SuperHOT-8k-GPTQ 11 months ago

Is possible to see a merged Airoboros-33b-SuperHOT-8k without GPTQ?

1
#1 opened 11 months ago by Panchovix