Hugging Face's logo
J Bochi's picture
33 3 19

J Bochi

jbochi
windcold's profile picture Suparious's profile picture Must42's profile picture
·

AI & ML interests

None yet

Organizations

MLX Community's profile picture

jbochi's activity

New activity in jbochi/candle-coedit-quantized 7 months ago

Llama.cpp error while loading

1
#2 opened 7 months ago by HR1777
New activity in jbochi/madlad400-8b-lm 8 months ago

Running 8b-lm

1
#3 opened 8 months ago by Ehsanjahanbakhsh
New activity in jbochi/madlad400-3b-mt 8 months ago

Translation of longer texts

3
#13 opened 8 months ago by hanshupe
New activity in google/madlad400-10b-mt 8 months ago

How do you specify source and target language?

3
#2 opened 10 months ago by narai
New activity in jbochi/madlad400-3b-mt 8 months ago

quantized version as app

4
#11 opened 9 months ago by sarahai
New activity in grammarly/coedit-xl 8 months ago

Infinite loop of processing

2
#3 opened 8 months ago by Ejentos
New activity in grammarly/coedit-large 8 months ago

Grammar explanation

6
#9 opened 9 months ago by Ejentos
New activity in TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF 8 months ago

Upload tinyllama-1.1b-chat-v1.0.Q4_1.gguf
#3 opened 8 months ago by jbochi
New activity in jbochi/madlad400-3b-mt 8 months ago

add protobuf to pip installation instruction

1
#12 opened 8 months ago by gqd
New activity in jbochi/madlad400-3b-mt 9 months ago

Translations are getting cut short

4
#10 opened 9 months ago by CXDuncan

Skip a subset of tokens during translation

1
#9 opened 9 months ago by anothersherlock
New activity in SkunkworksAI/phi-2 9 months ago

Add safetensors

1
#9 opened 9 months ago by jbochi
New activity in jbochi/coedit-base 9 months ago

cc-by-nc vs dataset license

2
#1 opened 10 months ago by pszemraj
New activity in jbochi/madlad400-3b-mt 10 months ago

Quantized model of the larger versions?

8
#7 opened 10 months ago by Runo888
New activity in jbochi/madlad400-8b-lm 10 months ago

Vocab size of tokenizer is not equal to vocab size of the model

2
#2 opened 10 months ago by dinhanhx
New activity in jbochi/madlad400-3b-mt 10 months ago

gguf invalid and no support in llama.cpp

2
#8 opened 10 months ago by cmp-nct
New activity in grammarly/coedit-large 10 months ago

Add onnx files

1
#8 opened 10 months ago by jbochi
New activity in jbochi/madlad400-8b-lm 10 months ago

Fix padding token
#1 opened 10 months ago by jbochi
New activity in jbochi/madlad400-3b-mt 10 months ago

Better Tokenizer

1
#5 opened 10 months ago by Ehsanjahanbakhsh
New activity in jbochi/madlad400-10b-mt 10 months ago

Fix padding token
#1 opened 10 months ago by jbochi
New activity in jbochi/madlad400-7b-mt-bt 10 months ago

Fix padding token
#1 opened 10 months ago by jbochi
New activity in jbochi/madlad400-7b-mt 10 months ago

Fix padding token
#1 opened 10 months ago by jbochi
New activity in jbochi/madlad400-3b-mt 10 months ago

Better Tokenization (Uses the correct token for padding)

1
#6 opened 10 months ago by Ehsanjahanbakhsh

Can't run your model. Got this error: no example target named `quantized-t5`. How can i fix it?

11
#4 opened 11 months ago by NikolayKozloff
New activity in jbochi/madlad400-3b-mt 11 months ago

converting LM

6
#2 opened 11 months ago by jisx

Tie word embeddings
#3 opened 11 months ago by jbochi

mt5 config

1
#1 opened 11 months ago by jbochi
New activity in grammarly/coedit-xxl 12 months ago

Upload model.safetensors with huggingface_hub

1
#3 opened 12 months ago by jbochi

Upload model.safetensors with huggingface_hub

1
#2 opened 12 months ago by jbochi
New activity in grammarly/coedit-large 12 months ago

Add example inputs to the text generation widget

1
#7 opened 12 months ago by jbochi
New activity in jbochi/candle-coedit-quantized 12 months ago

Add instructions to quantize model
#1 opened 12 months ago by jbochi
New activity in google/flan-t5-small about 1 year ago

Adding `safetensors` variant of this model

2
#14 opened about 1 year ago by SFconvertbot
New activity in grammarly/coedit-large about 1 year ago

Adding `safetensors` variant of this model

1
#4 opened about 1 year ago by SFconvertbot