Nguyen Bach
nguyenbh
AI & ML interests
None yet
Organizations
nguyenbh's activity
Irrelvant response
3
#64 opened 26 days ago
by
aravindpai
"small" is so different from "mini" and "medium"
1
#8 opened 14 days ago
by
J22
"bos_token": "<s>" vs. "<|endoftext|>"
1
#20 opened 3 days ago
by
tanliboy
Published paper
1
#28 opened 9 days ago
by
Napron
Endless blank space generation
1
#20 opened 14 days ago
by
mascIT
RuntimeError: FlashAttention only supports Ampere GPUs or newer.
1
#11 opened 16 days ago
by
pravinkarpe
phi3 vision visual encoder
9
#2 opened 18 days ago
by
the-future-dev
Unable to load the model
7
#10 opened 17 days ago
by
armandal
Unable to Reproduce Results of Any Model on the Evaluation Leaderboard
4
#9 opened 17 days ago
by
tcy6
model destroyed by deleting tokens?
1
#52 opened about 1 month ago
by
NickyNicky
clarification on the usage of `short_factor` and `long_factor`?
1
#49 opened about 1 month ago
by
J22
Probably Memory Leak issue?
2
#46 opened about 1 month ago
by
Tieni
Update sample_finetune.py
#70 opened 17 days ago
by
amcguinness
Any base models?
1
#9 opened 14 days ago
by
Defetya
Correct chat template, system?
4
#4 opened 17 days ago
by
Orenguteng
about multilingual label
4
#8 opened 15 days ago
by
StatPan
Target_module of this phi-3-small model
8
#3 opened 17 days ago
by
hackint0sh
the model can't stop generating for content extraction
8
#8 opened 17 days ago
by
tankstarwar
sdpa supported?
1
#7 opened 17 days ago
by
penut85420
Update README.md
#14 opened 15 days ago
by
Criztov
How to give it a system prompt?
2
#1 opened 18 days ago
by
catworld1212
Difference in chat templates between Phi-3-small-8k-instruct and Phi-3-medium-4k-instruct
1
#4 opened 17 days ago
by
tanliboy
`<|endoftext|>` in other model variants
2
#6 opened 16 days ago
by
yumemio
Inference via TGI
2
#4 opened 17 days ago
by
abrakaa
is it possible to use vision model with V100?
2
#3 opened 18 days ago
by
textToSQL
Update sample_finetune.py
#3 opened 17 days ago
by
damajercakms
Update sample_finetune.py
#69 opened 17 days ago
by
damajercakms
Update sample_finetune.py
#65 opened 17 days ago
by
damajercakms
Update sample_finetune.py
#6 opened 17 days ago
by
damajercakms
Phi3-V for detection/segmentation
1
#6 opened 17 days ago
by
CocoSun
Model can't stop from explaining itself
9
#53 opened about 1 month ago
by
fedeparra
gguf
30
#24 opened about 2 months ago
by
LaferriereJC
Clarification about multilingual training data
1
#1 opened 18 days ago
by
bofenghuang
Why no base models?
1
#2 opened 18 days ago
by
rombodawg
Benchmark seems confused in terms of Llama-70B VS 8B
2
#1 opened 18 days ago
by
Blackroot
Cannot deploy Phi-3-mini-4k-instruct model on AWS Sagemaker
2
#51 opened about 1 month ago
by
MajTad
Phi-3 instruct model continuously repeating the answer
2
#55 opened about 1 month ago
by
bitmman-nch
Is there a plan to release the pretrained base model for Phi-3?
1
#60 opened about 1 month ago
by
leestevennz
Quantization
#34 opened about 1 month ago
by
areumtecnologia
Looking forward to small and medium!
1
#33 opened about 1 month ago
by
DrNicefellow
Indian languages support
1
#20 opened about 2 months ago
by
bh4
Does it support Flash Attention-2?
4
#12 opened about 2 months ago
by
deshwalmahesh
Function calling capabilities?
1
#18 opened about 2 months ago
by
TeddyB
generate +6 min, +20GB V-ram
2
#17 opened about 2 months ago
by
NickyNicky
ollama q4_0 model starts generating garbage for longer generations
10
#4 opened about 2 months ago
by
eugeneware
a few edits for your model card (sorry I'm a grammar/writing nerd)
2
#16 opened about 2 months ago
by
luke-data-leader
Thank you
1
#13 opened about 2 months ago
by
ehartford
❤️ Thank You!
1
#14 opened about 2 months ago
by
sumuks
Base model ?
1
#11 opened about 2 months ago
by
edmond
Quantized
1
#13 opened about 2 months ago
by
wrosko
Fix newlines in templates
#1 opened about 2 months ago
by
nguyenbh
Fix new line in chat format
#6 opened about 2 months ago
by
nguyenbh
Update chat format
#2 opened about 2 months ago
by
nguyenbh
Update the chat format
#1 opened about 2 months ago
by
nguyenbh
Update the chat format
#1 opened about 2 months ago
by
nguyenbh