freedom-intelligence/inventory/catalog/deepseek-ai__DeepSeek-V4-Flash-0731__strategic.yaml
tegwick 8a65297d56 Stream model reserve to Scaleway without local weight staging
Assistant: codex
Assistant-Model: gpt-6-astra
Assistant-Session: 01a09cbd-43c1-79f3-809e-1ee97b40b64d
2026-09-14 00:17:15 +02:00

102 lines
4.7 KiB
YAML
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

id: deepseek-ai__DeepSeek-V4-Flash-0731__strategic
status: collecting
name: DeepSeek-V4-Flash-0731
org: deepseek-ai
source:
kind: huggingface
url: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731
revision: 7872f01b1d1fe23eabc4c98b48bffcef5a386062
model_card_url: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731
project_url: https://www.deepseek.com/
paper_url: https://arxiv.org/abs/2606.19348
license:
spdx: MIT
url: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731
allows_offline_retention: true
allows_local_ops: true
allows_fine_tune: true
notes: "Official card: repository and weights MIT. Confirm at pin."
profile:
summary: "S-tier open MIT MoE — 284B base / ~13B active (304B with DSpark); not a 12B dense model."
original_source: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731
use_cases:
- "Primary open-weight agentic / coding identity after Jul 2026"
- "Offline optionality if DeepSeek API access changes"
- "Future multi-GPU serve (vLLM DSpark / SGLang); not current R-spine"
- "Capability bar for daily briefs against closed frontier"
sweet_spots:
- "Best MIT-licensed open near-frontier that actually fits cheap Glacier (~167 GiB HF tree)"
- "Fits the €15/month Scaleway budget with room for K3"
- "Displaces DeepSeek-V3 as the collectable S1 identity"
not_ideal_for:
- "Current single-consumer-GPU daily ops (use R spine / Qwen3.8-27B)"
- "Treating 'Flash' as a 12B dense model (that reading was an executor error)"
capability_notes: >
Official V4-Flash release (2026-07-31). Same structure as
DeepSeek-V4-Flash-DSpark (speculative decoding module attached).
HF card reports 304B params (284B base + draft). ~13B active.
1M context. Terminal Bench 2.1 82.7. HF tree listed ~167 GB.
Automated briefs 2026-08-04…14 repeatedly called this a 12B dense
consumer-GPU model and once claimed it was already collected. It
was not. Size class is S, not R.
swot:
strengths:
- "MIT, official org, actually downloadable"
- "Near-frontier agentic scores at ~13B active"
- "Footprint (~167 GiB) is cheap on Glacier and was always inside the old 850 GiB quota"
weaknesses:
- "Serve needs multi-GPU / high unified memory, not T1T2"
- "Executor hallucinated it as 12B for two weeks — catalog must stay the authority"
opportunities:
- "First S pull onto Scaleway (FI-WP-0004-T09)"
- "Compressed / GGUF community packs exist if we want a later R experiment (not a substitute for the official tree)"
threats:
- "Successor V4.x could land while we still have no object on disk"
- "Quota-era deferral already cost a month of optionality"
size:
total_bytes: 166898547054
total_human: "166.9 GB / 155.4 GiB; 67 selected files at pinned commit, HF metadata 2026-09-14"
hardware_class:
min_vram_gb_q4: 0
min_vram_gb_fp16: 0
notes: "Beyond current lab run envelope (T3T4). Community 2-bit reports exist for 128 GB unified memory; not an R-spine claim."
axes: [A, B, D]
priority: high
collection:
approved_by: "grok"
approved_at: "2026-09-13"
downloaded_at: null
downloaded_by: ""
storage_path: ""
brief_refs:
- briefs/2026/08/2026-08-03.md
- briefs/2026/09/2026-09-13.md
- docs/decisions/2026-09-13-scaleway-object-reserve.md
reason: "S1 collectable — strongest MIT open MoE that fits the Scaleway euro budget; first pull after bucket create."
tags: [tier-s, strategic, moe, mit, beyond-run-envelope]
companions: []
notes: >
Do not confuse with a 12B dense checkpoint. There is no
deepseek-ai/DeepSeek-V4-Flash-0731-12B. Pull the official card repo.
Storage class at upload: strategic/ → Glacier.
history:
- at: "2026-08-03"
event: nominated
by: grok
detail: "Catch-up brief named V4-Flash-0731 as mid-tier open value leader."
- at: "2026-08-04"
event: misidentified
by: rein-aharness
detail: "Automated briefs treated it as 12B dense; never cataloged; 08-07 claimed on-disk collection that did not happen."
- at: "2026-09-13"
event: approved
by: grok
detail: "Corrected to 304B-class MoE ~167 GiB MIT. Approved for Scaleway Glacier once FI-WP-0004-T08 bucket exists."
- at: "2026-09-13"
event: collecting
by: grok
detail: "T08 bucket live. snapshot_download + Glacier upload started on workstation staging /home/worsch/vault/freedom-intelligence."
- at: "2026-09-14"
event: collecting
by: codex
detail: "Replaced WSL snapshot staging with diskless Railiance service fi-reserve-collect. 64 MiB parts, 512 MiB memory cap, no swap. Source pinned to 7872f01b1d1fe23eabc4c98b48bffcef5a386062; 67 selected files / 166898547054 bytes. Destination strategic/deepseek-ai__DeepSeek-V4-Flash-0731/<commit>/. Complete manifest pending; not collected or restore-verified."