SargeDev commited on
Commit
4f287ea
·
verified ·
1 Parent(s): 72e0303

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +5 -2
README.md CHANGED
@@ -72,14 +72,17 @@ vllm serve <target-model> \
72
 
73
  6,903 rows generated on-policy from Arete-27B-Uncensored (loop rows
74
  quarantined), hidden states extracted from layers 6/20/34/48/62/64 of the
75
- target. Corpus: `SargeDev/jev-distill-corpus-v3` lineage.
 
 
 
76
 
77
  ## Provenance
78
 
79
  - Z-Lab drafter base: [z-lab/Qwen3.8-27B-DFlash2](https://huggingface.co/z-lab/Qwen3.8-27B-DFlash2)
80
  - incoai finetuned variant: [incoai/Qwen3.8-27B-DFlash2](https://huggingface.co/incoai/Qwen3.8-27B-DFlash2)
81
  - Target: [SargeDev/Arete-27B-Uncensored-V2](https://huggingface.co/SargeDev/Arete-27B-Uncensored-V2) (our uncensored build of [NousResearch/Arete-27B](https://huggingface.co/NousResearch/Arete-27B))
82
- - Training corpus: `SargeDev/jev-distill-corpus-v3`
83
  - Trainer: [vllm-project/speculators](https://github.com/vllm-project/speculators) 0.9.0a0, DFlash2 (dflash2) speculator type
84
 
85
  ## License
 
72
 
73
  6,903 rows generated on-policy from Arete-27B-Uncensored (loop rows
74
  quarantined), hidden states extracted from layers 6/20/34/48/62/64 of the
75
+ target. The exact training rows are published:
76
+ **[SargeDev/arete-dflash2-trainset](https://huggingface.co/datasets/SargeDev/arete-dflash2-trainset)**
77
+ (97.6 MB, jsonl: `id`, `primary_id`, `source`, `input_ids`, `loss_mask`,
78
+ `text`, `metadata`). Corpus lineage: `SargeDev/jev-distill-corpus-v3`.
79
 
80
  ## Provenance
81
 
82
  - Z-Lab drafter base: [z-lab/Qwen3.8-27B-DFlash2](https://huggingface.co/z-lab/Qwen3.8-27B-DFlash2)
83
  - incoai finetuned variant: [incoai/Qwen3.8-27B-DFlash2](https://huggingface.co/incoai/Qwen3.8-27B-DFlash2)
84
  - Target: [SargeDev/Arete-27B-Uncensored-V2](https://huggingface.co/SargeDev/Arete-27B-Uncensored-V2) (our uncensored build of [NousResearch/Arete-27B](https://huggingface.co/NousResearch/Arete-27B))
85
+ - Training corpus: [SargeDev/arete-dflash2-trainset](https://huggingface.co/datasets/SargeDev/arete-dflash2-trainset) (`SargeDev/jev-distill-corpus-v3` lineage)
86
  - Trainer: [vllm-project/speculators](https://github.com/vllm-project/speculators) 0.9.0a0, DFlash2 (dflash2) speculator type
87
 
88
  ## License