ethicalabs/Echo-DSRN-114M-v0.1.2-Base
Text Generation • 0.1B • Updated • 1.47k
Massimo Roberto Scamarcia PRO
mrs83
AI & ML interests
Natural Language Processing, Text Generation, Question Answering, Data Augmentation, Knowledge Transfer, Chain-of-Thought, ResearchOps, MLOps
Recent Activity
updated a model about 5 hours ago
ethicalabs/Echo-DSRN-114M-v0.1.2-Base updated a model about 5 hours ago
ethicalabs/Echo-DSRN-114M-v0.1.2 updated a model 1 day ago
ethicalabs/FlowerTune-Echo-DSRN-114M-Finance-PEFTOrganizations
updated 2
models about 5 hours ago
updated 2
models 1 day ago
Echo-SmolTools-114M-NSFW-CLF-PEFT
#3 opened 1 day ago
by mrs83
reacted to qgallouedec's post with 🚀 8 days ago
Post
7846
TRL v1.3 ships day-one training support for Qwen 3.6 🚀
The new Qwen 3.6 family (
Qwen/Qwen3.6-27B, Qwen/Qwen3.6-35B-A3B) reuses the Qwen3.5-MoE architecture but ships a slightly different chat template, so we updated the stack end-to-end: new training template with {% generation %} markers, tool-call response schema routing, tiny test models for the VLM matrix.SFT with assistant-only loss works out of the box:
from trl import SFTConfig, SFTTrainer
trainer = SFTTrainer(
model="Qwen/Qwen3.6-27B",
args=SFTConfig(assistant_only_loss=True),
train_dataset=dataset,
)
trainer.train()So does GRPO tool-calling — just hand
tools=[...] to GRPOTrainer.v1.3 also brings a new experimental TPO trainer (Triple Preference Optimization), speculative decoding in
trl vllm-serve (Qwen3 MTP / Eagle3 drafts), 12 more KTO ↔ DPO alignment PRs (KTO promotion to stable is now in reach), three more {% generation %} chat templates (Gemma/Gemma 2, Phi-3, GLM-4-MoE), and a chunky SFT entropy bug fix.Full release notes: https://github.com/huggingface/trl/releases/tag/v1.3.0
published 3
buckets 8 days ago
updated a
Space 8 days ago
updated a
Space 10 days ago
published a
Space 10 days ago
updated a
bucket 10 days ago
published 2
buckets 10 days ago
liked a
dataset 10 days ago
replied to their post 10 days ago
thanks! I updated the app today. Both the model and the app are Apache-2.0 licensed, so feel free to build with them and experiment. While the model probably won't be as good as a conversational assistant, we can only understand where it really shines through experimentation. apparently, it works very well as "semantic compressor" and with classification tasks. maybe with audio? let's see
updated a
Space 10 days ago
updated 2
collections 10 days ago