Downloads · 30 days
0
0% of all-time downloads
expertQA_llama3.3-70b_exp1_2_finance_seed2
Flitto/expertQA_llama3.3-70b_exp1_2_finance_seed2
expertQA_llama3.3-70b_exp1_2_finance_seed2 is a machine learning model from Flitto. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as cc-by-nc-4.0.
SFT checkpoint from the EMNLP 2026 Industry Track submission A Factorial Ablation of a Speech-to-SFT Pipeline: Differential Effects on Data Quality and Downstream Transfer.
All-time downloads
2
Public
Repo size
846 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors829 MB · 98%
At a glance
- License
- cc-by-nc-4.0
- Access
- Public
- Created
- May 19, 2026
- Updated
- Jun 30, 2026
- SHA
- fa50ebf7
Base models
Model card
From the Hugging Face model README
expertQA_llama3.3-70b_exp1_2_finance_seed2
SFT checkpoint from the EMNLP 2026 Industry Track submission A Factorial Ablation of a Speech-to-SFT Pipeline: Differential Effects on Data Quality and Downstream Transfer.
| Field | Value |
|---|---|
| Pipeline condition | Exp 1-2 (Phase 2 only — quality refinement) |
| Domain | finance |
| Seed | 2 |
| Base model | meta-llama/Llama-3.3-70B-Instruct |
| Training | LoRA (rank 16, α=32, QLoRA 4-bit, lr 2e-4, 3 epochs) |
| Upstream STT | In-house STT (paper main pipeline) |
| License | CC BY-NC 4.0 (research and non-commercial use only) |
Intended use: research and non-commercial use only, matching the consent scope of the source audio.
Companion repository (code, configs, prompts, sample QA): https://github.com/flitto/speech-to-sft-ablation-paper
- License
- cc-by-nc-4.0
- Languages
- ko, en
- Created
- May 19, 2026
- Updated
- Jun 30, 2026