andy s
andysalerno
AI & ML interests
None yet
Recent Activity
liked
a model
about 8 hours ago
allenai/Llama-3.1-Tulu-3-8B
liked
a model
10 days ago
Qwen/Qwen2.5-Coder-32B-Instruct
liked
a model
21 days ago
meetkai/functionary-small-v2.5
Organizations
andysalerno's activity
Phi-3 models must be re-converted after recent llama.cpp commit
#4 opened 4 months ago
by
andysalerno
New activity in
mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-2bitgs8-metaoffload-HQQ
8 months ago
Either README is wrong, or the wrong model file is uploaded?
1
#1 opened 8 months ago
by
andysalerno
Adding Evaluation Results
#1 opened 9 months ago
by
leaderboard-pr-bot
Adding Evaluation Results
#1 opened 9 months ago
by
leaderboard-pr-bot
Adding Evaluation Results
#1 opened 9 months ago
by
leaderboard-pr-bot
chat format does not match the paper
1
#18 opened 9 months ago
by
andysalerno
prompt format in readme does not match tokenizer_config.json
2
#1 opened 10 months ago
by
andysalerno
Add MT-Bench, with Mixtral-8x7b judge?
1
#558 opened 10 months ago
by
andysalerno
Model follows ChatML format, but does not have the special tokens for ChatML
24
#3 opened 10 months ago
by
andysalerno
Could you share the training script?
1
#1 opened 10 months ago
by
andysalerno
ChatML format
1
#1 opened 11 months ago
by
andysalerno
Future feature: system prompt and chat support
21
#459 opened 11 months ago
by
clefourrier
[FLAG] fblgit/una-xaberius-34b-v1beta
125
#444 opened 12 months ago
by
XXXGGGNEt
Prompt Template?
13
#1 opened about 1 year ago
by
fakezeta
Mistral-Instruct can't count characters
2
#79 opened about 1 year ago
by
KeithCu
Add column "Added on" or "Last benchmarked" with date?
2
#99 opened over 1 year ago
by
andysalerno
Gibberish on 'latest', with recent qwopqwop GPTQ/triton and ooba?
7
#2 opened over 1 year ago
by
andysalerno
Possibility of 13b weights?
3
#4 opened over 1 year ago
by
andysalerno
Possibility of 13b weights?
3
#4 opened over 1 year ago
by
andysalerno
Possibility of 13b weights?
3
#4 opened over 1 year ago
by
andysalerno