dpsk-v4-flash.sft3.step_900

AgentPTB sweep checkpoint. Cell dpsk-v4-flash — pi / DeepSeek v4-flash @ effort thinking.

field value
plot cell dpsk-v4-flash
driver pi / DeepSeek v4-flash
reasoning effort thinking
run boot (UTC) 2026-08-11T08:38:35Z
role intermediate
origin msr-spare/msr-agentic-ptb-dpsk-sft3-intermediates :: step_900
shards 1
base model Qwen/Qwen3.5-9B-Base
eos_token_id [248044] ⚠️ MISSING 248046

The local copy of this checkpoint was pruned from the PVC; it was recovered from the msr-spare backup listed under origin.

Downloads last month
2
Safetensors
Model size
9B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for agentic-ptb/dpsk-v4-flash.h040.sft3.step_900

Finetuned
(383)
this model