Teklia/Newspapers-finlam-La-Liberte
Viewer • Updated • 8.84k • 81 • 2
John Locke
johnlockejrr
AI & ML interests
OCR, HTR, ATR, NLP, AI
Recent Activity
liked a dataset about 1 hour ago
Teklia/Newspapers-finlam-La-Liberte liked a dataset about 1 hour ago
Teklia/Newspapers-finlam liked a dataset about 24 hours ago
liminghao1630/DocBankOrganizations
liked 2
datasets about 1 hour ago
liked a
dataset about 24 hours ago
liked a
dataset 1 day ago
reacted to Crownelius's post with 🤯 1 day ago
Post
3413
Day 4-6 [05/05/2026]
Howdy,
Is anybody else willing to put a second mortgage on their house, just to spend 40k USD in compute credits? Just me? k...
I got dreams, man. The datasets I could build with 40k would be insane.
Somebody called me a genius the other day, they'd be shocked to find out, that I would put my house on the line for 30 days of runpod usage.
What would you do with it?
I would turn arxiv into a dataset. Turn each arxiv paper into a QnA.
Or... maybe if I got 40k USD in credit's Id end up like those 16 lost scientists.
Food for thought.
Anyways, I think I'm going to make a post once a week.
In the meantime you can find me building small llm's in discord here:
https://discord.gg/4DdwS9D8x9
Howdy,
Is anybody else willing to put a second mortgage on their house, just to spend 40k USD in compute credits? Just me? k...
I got dreams, man. The datasets I could build with 40k would be insane.
Somebody called me a genius the other day, they'd be shocked to find out, that I would put my house on the line for 30 days of runpod usage.
What would you do with it?
I would turn arxiv into a dataset. Turn each arxiv paper into a QnA.
Or... maybe if I got 40k USD in credit's Id end up like those 16 lost scientists.
Food for thought.
Anyways, I think I'm going to make a post once a week.
In the meantime you can find me building small llm's in discord here:
https://discord.gg/4DdwS9D8x9
- 6 replies
liked a
model 3 days ago
Finetuning scripts
❤️ 2
1
#5 opened 9 days ago
by johnlockejrr
Amazing hallucinations :)
🔥 1
4
#1 opened 5 days ago
by johnlockejrr
Pickle format
1
#1 opened 6 days ago
by johnlockejrr
liked a
model 6 days ago
liked a
model 7 days ago
liked a
model 8 days ago
liked a
model 9 days ago
liked a
dataset 9 days ago
reacted to qgallouedec's post with 🚀 10 days ago
Post
7895
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
updated a
dataset 10 days ago
published a
dataset 10 days ago
liked 2
models 11 days ago
liked a
model 15 days ago
