Binyuan Hui
huybery
AI & ML interests
Large Language Models, Code Generation, Semantic Parsing
Organizations
huybery's activity
Tokenizer config uses the wrong type which causes breaks with txt-gen-inf
3
#3 opened about 1 month ago
by
samulrich1
Help regarding model training
1
#5 opened about 1 month ago
by
iamshowyou
Hotfix JSON syntax
#6 opened 19 days ago
by
ganler
Base model should not use chat template.
1
#4 opened about 1 month ago
by
ganler
Model surprisingly good at EvalPlus
1
#17 opened about 1 month ago
by
cristian-rodriguez
Impressive 7B model beating out those 33B previous SOTAs
1
#13 opened about 1 month ago
by
Yhyu13
Prompt template?
1
#12 opened about 1 month ago
by
smchapman54
Model name typo in README
1
#1 opened about 1 month ago
by
kepkar
What are the diffences of this with Qwen/CodeQwen1.5-7B
6
#5 opened about 1 month ago
by
Kalemnor
EXL2 Quants are up
2
#2 opened about 2 months ago
by
Dracones
Fine tuning this model with Proprietary Code
1
#6 opened about 1 month ago
by
vtraghu
Can code snake in python, first model at this size after deekseekcoder-instruct-6.7b (With caveat)
2
#7 opened about 1 month ago
by
rombodawg
comparing to Qwen1.5, the tokenizer is changed. Why?
1
#9 opened about 1 month ago
by
J22
training data
2
#10 opened about 1 month ago
by
winddude
GGUF models
1
#1 opened about 2 months ago
by
MaziyarPanahi
is 14b coming?
4
#3 opened about 2 months ago
by
rombodawg
(Rebuked: this claim proven false) "Fake coding scores" .73 at best
8
#4 opened about 2 months ago
by
rombodawg
⚠️ You might be exposing a secret token, is this intended?
#1 opened 5 months ago
by
token-scanner
fix: Ch2 Q1 answer check
1
#1 opened 6 months ago
by
P051T1V3
Update README.md
#1 opened 6 months ago
by
reach-vb