Catch up field brief, catalog Kimi K3, and wire live daily recurrence.
Add 2026-08-03 week catch-up brief with Kimi K3 as S1 strategic (collection deferred on ~1454 GiB vs 850 GiB soft quota), document recurrence ops, and add a workstation due-notice consumer cron helper. Production schedule was applied to railiance ConfigMap and Temporal (weekdays 07:30 Europe/Berlin).
This commit is contained in:
parent
441de11a3e
commit
70cbfe0c6c
10 changed files with 389 additions and 38 deletions
|
|
@ -1,6 +1,6 @@
|
|||
# Open-weight reserve status
|
||||
|
||||
**As of:** 2026-07-28
|
||||
**As of:** 2026-08-03
|
||||
**Store:** `/mnt/d/vault/coulomb/freedom-intelligence/` (`D:\vault\coulomb\freedom-intelligence\`)
|
||||
**Soft quota:** 850 GiB · **Hard stop:** 920 GiB
|
||||
|
||||
|
|
@ -10,15 +10,13 @@
|
|||
|
||||
| Class | Count | Status mix |
|
||||
| ----- | ----: | ---------- |
|
||||
| Catalog entries | 12 | see table |
|
||||
| Catalog entries | 13 | + Kimi K3 S1 |
|
||||
| **verified** on disk | 4 | R embeds + Qwen3-8B + R1-Distill-14B |
|
||||
| **approved** (pull deferred) | S giants + Llama edge | capacity / HF gate |
|
||||
| **approved** (pull deferred) | S giants + Llama edge + **Kimi K3** | capacity / HF gate |
|
||||
| **candidate** (W) | 3 | headroom-gated |
|
||||
|
||||
### Disk use (model tree)
|
||||
|
||||
Run: `du -sh /mnt/d/vault/coulomb/freedom-intelligence/models`
|
||||
|
||||
| Path | Role | Approx |
|
||||
| ---- | ---- | ------ |
|
||||
| `models/nomic-ai__nomic-embed-text-v1.5/main` | R embed | ~0.5 GiB verified |
|
||||
|
|
@ -26,26 +24,29 @@ Run: `du -sh /mnt/d/vault/coulomb/freedom-intelligence/models`
|
|||
| `models/Qwen__Qwen3-8B/main` | R instruct | ~15.3 GiB verified |
|
||||
| `models/deepseek-ai__DeepSeek-R1-Distill-Qwen-14B/main` | R reason | ~27.5 GiB verified |
|
||||
|
||||
**~45 GiB** of soft 850 GiB used by verified R spine → **~800+ GiB** headroom for S.
|
||||
**~45 GiB** used → **~800+ GiB** soft-quota headroom (insufficient for full Kimi K3 ~1454 GiB).
|
||||
|
||||
VAULT free (2026-08-03): ~1.7 TB free of 1.9 TB — full K3 would still dominate the volume and **violate soft quota**.
|
||||
|
||||
---
|
||||
|
||||
## Decision matrix (2026-07-28)
|
||||
## Decision matrix (2026-08-03)
|
||||
|
||||
| Id | Tier | Decision | Disk |
|
||||
| -- | ---- | -------- | ---- |
|
||||
| Qwen3-8B | R | **verified** | yes |
|
||||
| Llama-3.2-3B-Instruct | R | **approved** | deferred — HF gate (need token) |
|
||||
| Llama-3.2-3B-Instruct | R | **approved** | deferred — HF gate |
|
||||
| BGE-M3 | R | **verified** | yes |
|
||||
| R1-Distill-Qwen-14B | R | **verified** | yes |
|
||||
| nomic-embed-text-v1.5 | R | **verified** | yes |
|
||||
| DeepSeek-V3 | S1 | **approved**, **collection deferred** | no — capacity / compressed plan later |
|
||||
| DeepSeek-R1 full | S2 | **approved**, **collection deferred** | no — distill covers runnable reason |
|
||||
| Qwen3-72B | S4 | **approved**, **collection deferred** | no — after R; pick vs Llama-70B |
|
||||
| Llama-3.3-70B-Instruct | S4 | **approved**, **collection deferred** | no — gated + vs Qwen-72B |
|
||||
| Qwen3-14B | W | **remain candidate** | no |
|
||||
| R1-Distill-32B | W | **remain candidate** | no |
|
||||
| bge-reranker-v2-m3 | W | **remain candidate** | no |
|
||||
| **Kimi-K3** | **S1** | **approved**, **collection deferred** | no — ~1454 GiB > soft quota |
|
||||
| DeepSeek-V3 | S1→secondary | **approved**, deferred | no — K3 is primary open SOTA identity |
|
||||
| DeepSeek-R1 full | S2 | **approved**, deferred | no |
|
||||
| Qwen3-72B | S4 | **approved**, deferred | no |
|
||||
| Llama-3.3-70B-Instruct | S4 | **approved**, deferred | no |
|
||||
| Qwen3-14B | W | candidate | no |
|
||||
| R1-Distill-32B | W | candidate | no |
|
||||
| bge-reranker-v2-m3 | W | candidate | no |
|
||||
|
||||
---
|
||||
|
||||
|
|
@ -57,15 +58,16 @@ Run: `du -sh /mnt/d/vault/coulomb/freedom-intelligence/models`
|
|||
| Edge micro-agent | Llama-3.2-3B blocked on HF auth |
|
||||
| Multilingual RAG embed | **Covered** (BGE-M3 + nomic) |
|
||||
| Local reason | **Covered** (R1-Distill-14B) |
|
||||
| Frontier-open general MoE offline | Deferred S1 (V3 class) |
|
||||
| Frontier-open general MoE offline | **Cataloged** Kimi K3 — pull blocked on capacity |
|
||||
| Full open reasoner MoE | Deferred S2 |
|
||||
|
||||
---
|
||||
|
||||
## Next pulls (operator)
|
||||
|
||||
1. Set `HF_TOKEN` and pull Llama-3.2-3B-Instruct.
|
||||
2. Reassess soft quota; pick **one** of Qwen3-72B vs Llama-3.3-70B before any S1 giant.
|
||||
3. For S1/S2: prefer **official compressed** distributions under soft quota.
|
||||
1. **Capacity decision for Kimi K3** (raise soft quota / dedicate disk / official compressed only).
|
||||
2. Set `HF_TOKEN` and pull Llama-3.2-3B-Instruct.
|
||||
3. Optional S4: one of Qwen3-72B vs Llama-3.3-70B under remaining quota.
|
||||
4. DeepSeek V4-Flash-0731 as mid open value candidate (catalog later if desired).
|
||||
|
||||
Tool: `scripts/collect_model.py` (weights-only, sequential, writes `MANIFEST.json`).
|
||||
|
|
|
|||
104
inventory/catalog/moonshotai__Kimi-K3__strategic.yaml
Normal file
104
inventory/catalog/moonshotai__Kimi-K3__strategic.yaml
Normal file
|
|
@ -0,0 +1,104 @@
|
|||
id: moonshotai__Kimi-K3__strategic
|
||||
status: approved
|
||||
name: Kimi-K3
|
||||
org: moonshotai
|
||||
source:
|
||||
kind: huggingface
|
||||
url: https://huggingface.co/moonshotai/Kimi-K3
|
||||
revision: main
|
||||
model_card_url: https://huggingface.co/moonshotai/Kimi-K3
|
||||
project_url: https://www.kimi.com/
|
||||
paper_url: https://huggingface.co/papers/2607.24653
|
||||
license:
|
||||
spdx: LicenseRef-Kimi-K3
|
||||
url: https://huggingface.co/moonshotai/Kimi-K3
|
||||
allows_offline_retention: true
|
||||
allows_local_ops: true
|
||||
allows_fine_tune: true
|
||||
notes: >
|
||||
Custom Kimi K3 License (not plain MIT/Apache). Review commercial SaaS
|
||||
revenue thresholds and attribution before external product embedding.
|
||||
Confirm card text at pin time.
|
||||
profile:
|
||||
summary: "S1 open frontier MoE (2.8T) — best open general/agentic class mid-2026."
|
||||
original_source: https://huggingface.co/moonshotai/Kimi-K3
|
||||
use_cases:
|
||||
- "Long-horizon coding and agent workflows (offline optionality)"
|
||||
- "Strategic reserve if closed APIs are unavailable or restricted"
|
||||
- "Future multi-GPU / training-facility inference when hardware catches up"
|
||||
- "Capability baseline against closed frontier for daily briefs"
|
||||
- "Native vision + 1M-context knowledge work (when runnable)"
|
||||
sweet_spots:
|
||||
- "Top open-weight intelligence class after Jul 2026 weight release"
|
||||
- "Agentic / coding / long-context open MoE identity"
|
||||
- "Displaces prior S1 DeepSeek-V3 as primary open general target"
|
||||
not_ideal_for:
|
||||
- "Current single-GPU or small multi-GPU lab serve (far beyond run envelope)"
|
||||
- "Fitting under 850 GiB soft quota at full precision (~1.45 TiB tree)"
|
||||
- "Casual always-on chat (use R spine)"
|
||||
capability_notes: >
|
||||
Moonshot Kimi K3: ~2.8T total MoE parameters, sparse activation (~16/896
|
||||
experts), Kimi Delta Attention + Attention Residuals, native multimodal,
|
||||
~1M context. Official HF tree measured ~1454 GiB (96 shards). Collection
|
||||
deferred until capacity exception or official compressed distribution.
|
||||
swot:
|
||||
strengths:
|
||||
- "Leading open-weight general/agentic capability at release"
|
||||
- "Open weights enable true offline retention optionality"
|
||||
- "Strong coding / long-horizon / vision narrative"
|
||||
weaknesses:
|
||||
- "Disk footprint (~1.45 TiB) exceeds current soft quota and most lab GPUs"
|
||||
- "Custom license with commercial thresholds"
|
||||
- "Serve cost multi-node enterprise class"
|
||||
opportunities:
|
||||
- "Hold identity in catalog; pull compressed later if published"
|
||||
- "Anchor daily briefs / evals against open SOTA"
|
||||
- "Displace V3 as primary S1 when space allows"
|
||||
threats:
|
||||
- "Quota: full pull blocks all other S niches on VAULT"
|
||||
- "Rapid supersession by K3.x or peer open giants"
|
||||
- "Third-party quant quality variance if forced to unofficial packs"
|
||||
size:
|
||||
total_bytes: 1560998984390
|
||||
total_human: "~1454 GiB official HF tree (measured 2026-08-03); compressed TBD"
|
||||
hardware_class:
|
||||
min_vram_gb_q4: 0
|
||||
min_vram_gb_fp16: 0
|
||||
notes: "Beyond current lab run envelope (multi-node). Strategic reserve only."
|
||||
axes: [A, B, C, D]
|
||||
priority: high
|
||||
collection:
|
||||
approved_by: "bernd"
|
||||
approved_at: "2026-08-03"
|
||||
downloaded_at: null
|
||||
downloaded_by: ""
|
||||
storage_path: ""
|
||||
brief_refs:
|
||||
- briefs/2026/08/2026-08-03.md
|
||||
- research/2026-07-24-nas-strategic-collection-plan.md
|
||||
- docs/decisions/2026-07-24-nas-strategic-reserve.md
|
||||
reason: >
|
||||
S1 strategic — best open-weight general/agentic model class after Jul 2026
|
||||
release; keep capability identity even though full tree exceeds soft quota.
|
||||
tags: [tier-s, strategic, beyond-run-envelope, moe, general, vision, kimi, s1]
|
||||
companions: []
|
||||
notes: >
|
||||
Do not bulk-download full tree under 850 GiB soft quota. Prefer official
|
||||
compressed if/when available. Revisit capacity exception with operator.
|
||||
history:
|
||||
- at: "2026-08-03"
|
||||
event: nominated
|
||||
by: grok
|
||||
detail: "Week catch-up brief — Kimi K3 open weights Jul 27 as new open SOTA."
|
||||
- at: "2026-08-03"
|
||||
event: approved
|
||||
by: bernd
|
||||
detail: "Operator direction: catalog and plan; collection deferred on capacity."
|
||||
- at: "2026-08-03"
|
||||
event: collection_deferred
|
||||
by: grok
|
||||
detail: "Official tree ~1454 GiB > soft quota 850 GiB; await capacity decision or compressed release."
|
||||
- at: "2026-08-03"
|
||||
event: profile_swot_added
|
||||
by: grok
|
||||
detail: "schema 0.2 profile + SWOT."
|
||||
Loading…
Add table
Add a link
Reference in a new issue