lhl PRO
leonardlin
AI & ML interests
None yet
Recent Activity
updated
a model
2 days ago
shisa-ai/ablation-191-finalsft2-shisa-v2-qwen2.5-7b
published
a model
2 days ago
shisa-ai/ablation-191-finalsft2-shisa-v2-qwen2.5-7b
updated
a model
2 days ago
shisa-ai/ablation-192-a175.finaldpo2.8e7-shisa-v2-llama-3.1-8b
Organizations
leonardlin's activity
Broken tokenizer output on Japanese benchmarks?
1
#14 opened about 1 month ago
by
leonardlin

GGUF Issues
1
#1 opened 11 months ago
by
leonardlin

MT-Bench Scores
1
19
#1 opened about 1 year ago
by
leonardlin

MT-Bench Results
2
5
#2 opened about 1 year ago
by
leonardlin

Are there MT-Bench metrics produced for this model?
11
#4 opened over 1 year ago
by
Jaredc
Add chat_template to tokenizer_config.json?
1
4
#1 opened over 1 year ago
by
leonardlin

Does this tokenizer work?
3
#1 opened over 1 year ago
by
kik0220
tokenizer.chat_template
1
#2 opened over 1 year ago
by
leonardlin

Apply for community grant: Personal project (gpu and storage)
17
#1 opened over 1 year ago
by
leonardlin

Quants
1
#2 opened over 1 year ago
by
leonardlin

llama.cpp doesn't work w/ Shisa, has a bug that affects certain BPE tokenizers like ours
1
3
#1 opened over 1 year ago
by
leonardlin

Tracking a few improvements TODO:
1
#2 opened over 1 year ago
by
leonardlin

Apply for community grant: Personal project (gpu and storage)
17
#1 opened over 1 year ago
by
leonardlin

Apply for community grant: Personal project (gpu and storage)
17
#1 opened over 1 year ago
by
leonardlin
