19 lines
468 B
Markdown
19 lines
468 B
Markdown
|
---
|
||
|
|
license: apache-2.0
|
||
|
|
base_model: Qwen/Qwen2.5-1.5B
|
||
|
|
tags:
|
||
|
|
- bittensor
|
||
|
|
- evolai
|
||
|
|
- colosso
|
||
|
|
- sn47
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
---
|
||
|
|
|
||
|
|
# Colosso SN47 EvolAI Qwen2.5 1.5B
|
||
|
|
|
||
|
|
Colosso-owned merged model for SN47 EvolAI miner bootstrap.
|
||
|
|
|
||
|
|
This model was produced from the local SBE LoRA adapter `evolai-qwen25-15b-lora-acceptance-20260605T103709` merged into `Qwen/Qwen2.5-1.5B`.
|
||
|
|
|
||
|
|
Training summary: 512 rows, 9000 steps, first loss 3.8946, last loss 0.2176, quality gate pass.
|