Jaro
JustJaro
AI & ML interests
GNNs, transformers, multimodal models, model explainability, graphs of knowledge, advanced prompting (graph of prompts, experts, etc.)
Recent Activity
updated
a model
6 days ago
JustJaro/gte-multilingual-reranker-base-onnx-op19-opt-gpu
published
a model
6 days ago
JustJaro/gte-multilingual-reranker-base-onnx-op19-opt-gpu
updated
a model
10 days ago
JustJaro/gte-multilingual-reranker-base-onnx-op14-opt-gpu
Organizations
JustJaro's activity

New activity in
ConfidentialMind/Mistral-Small-24B-Instruct-2501_GPTQ_G128_W4A16_MSE
about 1 month ago
Any plan for 8bit version?
2
#1 opened about 2 months ago
by
jm4n21
the weights?
1
#1 opened 4 months ago
by
MaziyarPanahi

no weights?
8
#1 opened 4 months ago
by
KnutJaegersberg

Performance on MTEB
2
#4 opened 4 months ago
by
JustJaro

Apologies for no concrete evals - those will be coming in later quants as we set up the automations.
#1 opened 4 months ago
by
JustJaro

Un-censoring methods and effects on performance
1
#2 opened 5 months ago
by
JustJaro

Could you publish results compared to Sonnet 3.5?
3
#3 opened 9 months ago
by
JustJaro

Safetensor format
2
#14 opened 5 months ago
by
JustJaro

How to inference the model?
2
#3 opened 6 months ago
by
frankgu3528
support vllm
3
#10 opened 7 months ago
by
CarrotAI

Multi-token Prediction Models for Large Language Models: Code and Discussion
2
#2 opened 10 months ago
by
ashishpatel26
