Hugging Face's logo
John Rachwan's picture
29 3 43

John Rachwan

johnrachwanpruna
thomwolf's profile picture 21world's profile picture jonidimo's profile picture
·
https://www.pruna.ai/

AI & ML interests

None yet

Organizations

Pruna AI's profile picture

johnrachwanpruna's activity

New activity in PrunaAI/dolphin-2.9-llama3-8b-256k-GGUF-smashed about 2 months ago

Issues with PrunaAI Dolphin-2.9 Model: Poor Performance on Logic, Math, and Code Generation Compared to Older Llama Models

4
#2 opened about 2 months ago by jonidimo
New activity in PrunaAI/Llama-3-8B-Instruct-Gradient-1048k-GGUF-smashed about 2 months ago

New weights available

1
#2 opened about 2 months ago by michaelfeil
New activity in PrunaAI/Phi-3-mini-128k-instruct-GGUF-Imatrix-smashed 2 months ago

Mistake in readme instructions

2
#5 opened 2 months ago by adamkdean
New activity in PrunaAI/dolphin-2.9-llama3-8b-256k-GGUF-smashed 2 months ago

What is smashed?

2
#1 opened 2 months ago by supercharge19
New activity in PrunaAI/Phi-3-mini-128k-instruct-GGUF-Imatrix-smashed 2 months ago

gibberish results when context is greater 2048

9
#4 opened 2 months ago by Bakanayatsu

Thanks Guys!

5
#1 opened 2 months ago by Joseph717171

Do they work with ollama? How was the conversion done for 128K, llama.cpp/convert.py complains about ROPE.

8
#2 opened 2 months ago by BigDeeper

- Download huggingface-cli command have a typo

1
#3 opened 2 months ago by Jay9787WaiF
New activity in PrunaAI/Meta-Llama-3-8B-Instruct-GGUF-smashed 2 months ago

Please post the imatrix that was used to quantize

1
#1 opened 2 months ago by Joseph717171
New activity in PrunaAI/Llama-3-13B-Instruct-v0.1-GGUF-smashed 2 months ago

Based on?

5
#1 opened 2 months ago by frenzygr
New activity in PrunaAI/gemma-2b-GGUF-smashed 2 months ago

Upload folder using huggingface_hub

2
#1 opened 2 months ago by johnrachwanpruna
New activity in PrunaAI/gemma-2b-it-GGUF-smashed 2 months ago

Upload folder using huggingface_hub

2
#1 opened 2 months ago by johnrachwanpruna
New activity in PrunaAI/zephyr-orpo-141b-A35b-v0.1-GGUF-smashed 2 months ago

[WIP] Upload folder using huggingface_hub (multi-commit 351cb1c3795b45aa5c7aa10bd5d53ea3f58ee7797f37c66fab0bf543abfd3dd2)
#1 opened 3 months ago by johnrachwanpruna
New activity in PrunaAI/WizardLM-2-7B-GGUF-smashed 3 months ago

Upload folder using huggingface_hub

2
#1 opened 3 months ago by johnrachwanpruna
New activity in PrunaAI/codegemma-7b-it-GGUF-smashed 3 months ago

Upload folder using huggingface_hub

2
#1 opened 3 months ago by johnrachwanpruna
New activity in PrunaAI/lynn-7b-alpha-GGUF-smashed 3 months ago

Upload folder using huggingface_hub

2
#1 opened 3 months ago by johnrachwanpruna
New activity in PrunaAI/Poro-34B-GGUF-smashed 3 months ago

[WIP] Upload folder using huggingface_hub (multi-commit 2d2b70dfe35df5dcb72ff0de6c328a35bfc802ad5e0a9a2c4efc3a8e347f869e)
#1 opened 3 months ago by johnrachwanpruna
New activity in PrunaAI/Mistral-7B-Instruct-v0.2-GGUF-smashed 3 months ago

Upload folder using huggingface_hub

2
#1 opened 3 months ago by johnrachwanpruna
New activity in PrunaAI/Mistral-22B-v0.2-GGUF-smashed 3 months ago

Upload folder using huggingface_hub

2
#1 opened 3 months ago by johnrachwanpruna
New activity in PrunaAI/phi-2-GGUF-smashed 3 months ago

Upload folder using huggingface_hub

2
#3 opened 3 months ago by johnrachwanpruna

Upload folder using huggingface_hub

2
#2 opened 3 months ago by johnrachwanpruna

Upload folder using huggingface_hub

2
#1 opened 3 months ago by johnrachwanpruna
New activity in PrunaAI/Mixtral-8x22B-v0.1-bnb-4bit-smashed 3 months ago

Is it possible to convert these to a single GGUF?

1
#2 opened 3 months ago by smcleod
New activity in PrunaAI/dbrx-instruct-bnb-4bit 3 months ago

generation is not good

9
#2 opened 3 months ago by jmjzz
New activity in PrunaAI/Jamba-v0.1-bnb-4bit 3 months ago

environment setup

1
#2 opened 3 months ago by Alex18
New activity in PrunaAI/dbrx-base-bnb-4bit 3 months ago

Can you please also convert dbrx-instruct to bnb-4bit

1
#2 opened 3 months ago by MLDataScientist

invalid weights doesn't match modeling code

1
#3 opened 3 months ago by winglian
New activity in PrunaAI/dbrx-instruct-bnb-4bit 3 months ago

Getting an error when loading the model

15
#3 opened 3 months ago by MLDataScientist
New activity in databricks/dbrx-instruct 3 months ago

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

31
#10 opened 3 months ago by tdrussell