Hugging Face's logo
Banghua Zhu's picture
44 7 14

Banghua Zhu

banghua
victor's profile picture evanfrick's profile picture tuantm's profile picture
·
https://people.eecs.berkeley.edu/~banghua/
BanghuaZ
BHZ-BER

AI & ML interests

Foundation models, statistics, information theory

Organizations

Nexusflow's profile picture ZeroGPU Explorers's profile picture Berkeley-Nest's profile picture TemporaryTransfer-NF-AS's profile picture Social Post Explorers's profile picture WolfSuxen's profile picture

banghua's activity

New activity in open-llm-leaderboard/open_llm_leaderboard 5 days ago

Models that used Nectar dataset

9
#749 opened 14 days ago by Stark2008
New activity in berkeley-nest/Starling-RM-7B-alpha 8 days ago

Any ETA on your paper?

2
#7 opened 9 days ago by ttkciar
New activity in Nexusflow/Starling-LM-7B-beta about 2 months ago

What prompts are used in RLAIF?

1
#13 opened about 2 months ago by chujiezheng

Lack of a System Prompt

4
#11 opened 2 months ago by Metricon

Finetuning is very complicated, could you help?

10
#12 opened about 2 months ago by Undi95
New activity in Nexusflow/Starling-LM-7B-beta 2 months ago

Amazing model.

3
#1 opened 2 months ago by rjmehta

verbosity

3
#2 opened 2 months ago by lixbo
New activity in Nexusflow/Nexus_Function_Calling_Leaderboard 2 months ago

Any arxiv or codebase along with the leaderboard?

3
#2 opened 3 months ago by zhiminy
New activity in berkeley-nest/Starling-LM-7B-alpha 3 months ago

Responsible for me

1
#28 opened 4 months ago by Anonimus12345678902

Why change the licence ?

1
#30 opened 3 months ago by trashpanda75

Update README.md

2
#29 opened 4 months ago by youkad
New activity in berkeley-nest/Starling-RM-7B-alpha 4 months ago

Prompt Format

3
#4 opened 6 months ago by ekurtulus
New activity in berkeley-nest/Starling-LM-7B-alpha 4 months ago

Code/paper release

3
#26 opened 5 months ago by andrewzh

Beta or V2 release?

3
#27 opened 4 months ago by rjmehta
New activity in berkeley-nest/Starling-RM-7B-alpha 4 months ago

Missing import for inference
#5 opened 5 months ago by davide221
New activity in berkeley-nest/Starling-LM-7B-alpha 5 months ago

Hyperparameters?

1
#23 opened 6 months ago by ekurtulus

What could be instruction fine tuning prompt for this model?

5
#22 opened 6 months ago by andreaKIM

中文能力如何？

1
#24 opened 5 months ago by xxmhjk
New activity in TheBloke/NexusRaven-V2-13B-GGUF 6 months ago

Could you please help change the license?

2
#1 opened 6 months ago by banghua
New activity in berkeley-nest/Starling-LM-7B-alpha 6 months ago

extremely variable response time for inference?

9
#21 opened 6 months ago by silvacarl

Short responses when deployed as Inference Endpoint

5
#20 opened 6 months ago by iraklip
New activity in Nexusflow/NexusRaven-V2-13B 6 months ago

Scenario issue

2
#1 opened 6 months ago by eramax
New activity in berkeley-nest/Starling-LM-7B-alpha 6 months ago

Cant wait for Beta Version

5
#19 opened 6 months ago by rjmehta

Won't stop spitting training data

6
#18 opened 6 months ago by topastop

best model params

11
#8 opened 6 months ago by eramax

Can use chatml format?

1
#15 opened 6 months ago by lucasjin

License

6
#11 opened 6 months ago by mrfakename

Prompt template for adding RAG Context block

5
#13 opened 6 months ago by rjmehta

Chat adopted version

2
#14 opened 6 months ago by onix135
New activity in berkeley-nest/Starling-RM-7B-alpha 6 months ago

Model usage

2
#2 opened 6 months ago by onix135
New activity in berkeley-nest/Starling-LM-7B-alpha 6 months ago

Maybe you could try on Yi-34B

1
#12 opened 6 months ago by Yhyu13

Added code examples that correspond to each prompt format

1
#10 opened 6 months ago by macadeliccc
New activity in TheBloke/Starling-LM-7B-alpha-GGUF 6 months ago

Tokenizer issue?

27
#1 opened 6 months ago by sleepyjoecheated
New activity in berkeley-nest/Starling-LM-7B-alpha 6 months ago

Amazing model

9
#3 opened 6 months ago by rjmehta

The Model move betwwen languages

1
#9 opened 6 months ago by eramax
New activity in berkeley-nest/Starling-RM-7B-alpha 6 months ago

Fix issues in sample code: Invalid reward_tokenizer and issue in returning scores

1
#1 opened 6 months ago by amitness
New activity in berkeley-nest/Starling-LM-7B-alpha 6 months ago

Pytorch format available?

3
#7 opened 6 months ago by vmajor

Add OpenChat3.5 chat template

1
#6 opened 6 months ago by khu

Paragraph Breaks

3
#4 opened 6 months ago by Shasho423

tokenizer.model

3
#5 opened 6 months ago by bartowski

Would be nice to have the openchat.json config directly in the repo

1
#2 opened 6 months ago by mlaprise

Surprisingly impressive!

1
#1 opened 6 months ago by Cypherfox
New activity in teknium/OpenHermes-2.5-Mistral-7B 6 months ago

Inconsistent Eval Results with Openchat 3.5?

2
#7 opened 6 months ago by banghua
New activity in ICML2023/ICML2023_papers 11 months ago

Update papers.csv

3
#1 opened 11 months ago by banghua