BuiDoan
BuiDoan
AI & ML interests
None yet
Recent Activity
new activity about 2 hours ago
incoai/Qwen3.8-27B-DFlash2:Shall I reduce the num of spec tokens? liked a model about 9 hours ago
incoai/Qwen3.8-27B-DFlash2 liked a Space 1 day ago
OpenEvals/leaderboard-watcherOrganizations
Shall I reduce the num of spec tokens?
2
#9 opened 10 days ago
by
Nunodonato
How exactly is this model used?
2
#1 opened 2 months ago
by
Aloooom
THANK YOU
1
#1 opened 19 days ago
by
BuiDoan
Poor results
#1 opened 23 days ago
by
BuiDoan
Absolute legend!
🔥❤️ 20
#30 opened 24 days ago
by
BuiDoan
K-Quant-17GB
1
#14 opened 28 days ago
by
BuiDoan
Going completely mad
🚀🔥 45
11
#1 opened about 1 month ago
by
xiezirock
Looping
18
#1 opened about 2 months ago
by
jbourny
DFlash draft acceptance ~10% (greedy) after the 07-23 yarn_attn_factor re-quant — does the draft need regenerating?
3
#21 opened about 2 months ago
by
Conrz
Additional Benchmarks & KL Divergence vs. Base Model
2
#4 opened about 1 month ago
by
BuiDoan
效果好差
👍 2
5
#2 opened about 2 months ago
by
AlexLee111
IDEA: Bitnet 1.58 (a4.8) version in future variants would be so incredible!
❤️ 4
3
#10 opened 2 months ago
by
apiarium
Avg Draft acceptance rate: 0.0%
2
#1 opened 4 months ago
by
BuiDoan
RuntimeError: expected mat1 and mat2 to have the same dtype, but got: float != c10::Half
3
#10 opened 4 months ago
by
mancub
Request for 4-bit Quantization
👍 1
#1 opened 4 months ago
by
BuiDoan
Error compressed tensor sglang
➕ 9
3
#1 opened 5 months ago
by
amartinOnepoint
Quantization request
❤️ 1
#1 opened 4 months ago
by
BuiDoan
New activity in Sociopacific/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-GPTQ-Int4 4 months ago
Anyone got experience with it?
#1 opened 4 months ago
by
BuiDoan
Avg Draft acceptance rate is low.
17
#2 opened 5 months ago
by
fouvy
Any reason no more 35b-a3b model release?
3
#4 opened 5 months ago
by
prunusis