lhl PRO
leonardlin
AI & ML interests
None yet
Recent Activity
liked a model 6 days ago
AngelSlim/Hy4-preview-GGUF liked a model 7 days ago
zai-org/GLM-5.3 updated a model 11 days ago
shisa-ai/Qwen3.8-27B-Q4_K_M-DMS-W8192Organizations
No speculative decoding, No QAT
8
#21 opened 13 days ago
by
engrtipusultan
Qwen 3.8 27b wins?
👍 2
3
#14 opened 15 days ago
by
Tdamre
mtp.* tensors look like random init, not trained weights
🧠👍 9
16
#10 opened 16 days ago
by
EryriLabs
FastDMS: Full DMS implementation running faster than vLLM BF16/FP8
👍 1
#2 opened 4 months ago
by
leonardlin
Speed differences for different quants
👍 4
2
#21 opened about 1 year ago
by
leonardlin
Shisa Model Review Video
🚀 1
1
#1 opened about 1 year ago
by
fahdmirzac
Improve language tag
#1 opened over 1 year ago
by
lbourdois
Improve language tag
#1 opened over 1 year ago
by
lbourdois
Improve language tag
#1 opened over 1 year ago
by
lbourdois
Improve language tag
#2 opened over 1 year ago
by
lbourdois
Improve language tag
#1 opened over 1 year ago
by
lbourdois
Broken tokenizer output on Japanese benchmarks?
1
#14 opened over 1 year ago
by
leonardlin
GGUF Issues
1
#1 opened over 2 years ago
by
leonardlin
MT-Bench Scores
❤️ 1
19
#1 opened over 2 years ago
by
leonardlin
MT-Bench Results
👍 2
5
#2 opened over 2 years ago
by
leonardlin
Are there MT-Bench metrics produced for this model?
11
#4 opened over 2 years ago
by
Jaredc
Add chat_template to tokenizer_config.json?
👍 1
4
#1 opened over 2 years ago
by
leonardlin
Does this tokenizer work?
3
#1 opened over 2 years ago
by
kik0220
tokenizer.chat_template
1
#2 opened over 2 years ago
by
leonardlin