fenyo

Qwen2.5-7B-base2instruct-SFT

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more
Container

Run this model inference with full control and performance in your environment.

Learn more

Get help setting up a custom Dedicated Endpoints.

Talk with our engineer to get a quote for reserved GPU instances with discounts.

README

License: apache-2.0

Entraînement

Full fine-tuning (TRL SFTTrainer), format ChatML, loss sur la réponse assistant uniquement (assistant_only_loss + balises {% generation %}), liger-kernel, packing, bf16, attention SDPA. 1 epoch, lr 5e-6 cosine, seq_len 4096. Données : allenai/tulu-3-sft-mixture (180k).

Résultats (lm-eval, backend vLLM)

Table
étapeIFEval (prompt strict)GSM8K (flexible)MMLU
base Qwen2.5-7B27.483.071.8
+ SFT (ce modèle)44.977.569.1
+ DPO44.777.169.9
+ RLVR45.177.469.9

C'est le SFT qui apporte l'essentiel du gain en suivi d'instructions (IFEval 27→45). Détails et analyse : dépôt GitHub.

Usage

Format ChatML, via tokenizer.apply_chat_template. Voir l'exemple sur le modèle final.

Model provider

fenyo

Model tree

Base

Qwen/Qwen2.5-7B

Fine-tuned

this model

Modalities

Input

Text

Output

Text

Pricing

Dedicated Endpoints

View details

Supported Functionality

Model APIs

Dedicated Endpoints

Container

More information

Explore FriendliAI today