ducthang1703

crpd-qwen3-1p7b-to-0p6b-smoke-student-ref

README

License: apache-2.0

crpd-qwen3-1p7b-to-0p6b-smoke-student_ref

ChunkRatio-PD SMOKE TEST (tiny data, not a usable model) artifact, role student_ref, pair Qwen3-1.7B -> Qwen3-0.6B. Pilot settings are assumptions, not NARVAL's; see pilot_assumptions in the bundled config. No benchmark result is claimed.

code revision: e074a7e6185861667f278a0eb23981227e5d4826
data revisions: {"preference_dataset": "3949bf5f8c17c394422ccfab0c31ea9c20bdeb85", "reward_model": "94fad49f1b3227aa8b566f415a335adb68ec544c", "sft_dataset": "fdb88575d6d3b0e5b8fc9934778b62313c7837ba", "student_base_model": "da87bfb608c14b7cf20ba1ce41287e8de496c0cd", "teacher_base_model": "ea980cb0a6c2ae4b936e82123acc929f1cec04c1"}
scale: smoke; EOS <|im_end|>; chat template with enable_thinking=false

Available on FriendliAI

Dedicated Endpoints

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

Learn more

Model Details

Model Provider

ducthang1703

Model Tree

Base

Qwen/Qwen3-0.6B-Base

Fine-tuned

this model

Input Modalities

Text

Output Modalities

Text

Supported Functionality

Dedicated Endpoints

Explore FriendliAI today

Get started Talk to an engineer

README

License: apache-2.0

crpd-qwen3-1p7b-to-0p6b-smoke-student_ref

code revision: e074a7e6185861667f278a0eb23981227e5d4826
data revisions: {"preference_dataset": "3949bf5f8c17c394422ccfab0c31ea9c20bdeb85", "reward_model": "94fad49f1b3227aa8b566f415a335adb68ec544c", "sft_dataset": "fdb88575d6d3b0e5b8fc9934778b62313c7837ba", "student_base_model": "da87bfb608c14b7cf20ba1ce41287e8de496c0cd", "teacher_base_model": "ea980cb0a6c2ae4b936e82123acc929f1cec04c1"}
scale: smoke; EOS <|im_end|>; chat template with enable_thinking=false