A "work-in-progress" collection of experimental SFT runs. Primary focus: minimizing catastrophic forgetting, testing LoRA vs. Full-Parameter tuning.
Francesco Albanese
Francesco-A
·
AI & ML interests
None yet
Recent Activity
updated
a model 10 days ago
Francesco-A/mistral-7b-instruct-v0.3-bnb-4bit published
a model 10 days ago
Francesco-A/mistral-7b-instruct-v0.3-bnb-4bit updated
a Space 11 days ago
Francesco-A/GaiaAgent_Final_Assignment Organizations
spaces 7
pinned
Sleeping
Argilla Course
✍
This is just a test space to experiment with Argilla
Sleeping
GAIA Agent
🕵
Run automated evaluations and submit answers to get scored
Sleeping
Trackio
🚀
Visualize and analyze machine learning experiment metrics in real-time
Sleeping
AlfredAgent
🤵
Generate answers and images using various tools
Sleeping
Simple Image Classification-v1
📸
Collection of Simple Image Classification Models
Build error
LangchainSummarization V1
🌖
models 20
Francesco-A/mistral-7b-instruct-v0.3-bnb-4bit
Updated
Francesco-A/smollm3-finetuned-test
Text Generation • Updated
Francesco-A/deberta-v3-large-LoRA-math-misunderstandings-v1
Updated
Francesco-A/BiomedNLP-PubMedBERT-base-uncased-abstract-bc5cdr-ner-LoRA-v1
Token Classification • Updated
• 2
Francesco-A/BiomedNLP-PubMedBERT-base-uncased-abstract-bc5cdr-ner-v1
Token Classification • 0.1B • Updated
• 9
Francesco-A/ppo-MountainCar-v0
Reinforcement Learning • Updated
Francesco-A/bert-finetuned-squad-v1
Question Answering • 0.1B • Updated
• 9
Francesco-A/dqn-SpaceInvadersNoFrameskip-v4
Reinforcement Learning • Updated
• 3
Francesco-A/a2c-PandaReachDense-v3
Reinforcement Learning • Updated
• 1
Francesco-A/finetuned-kde4-en-to-fr
Translation • Updated
• 1