Finish FI-WP-0002 and FI-WP-0003: daily rhythm and R-spine reserve.

Enable fi-daily-research-brief, prove fi_brief_status idempotence with the
2026-07-28 brief, approve R/S catalog entries, collect and verify embeds plus
Qwen3-8B and R1-Distill-14B on VAULT, and document residuals (HF-gated Llama,
deferred S giants, railiance ConfigMap apply).
This commit is contained in:
tegwick 2026-07-28 01:30:55 +02:00
parent 4d66ae96b5
commit 77d4ffe86e
20 changed files with 581 additions and 252 deletions

View file

@ -0,0 +1,71 @@
# Open-weight reserve status
**As of:** 2026-07-28
**Store:** `/mnt/d/vault/coulomb/freedom-intelligence/` (`D:\vault\coulomb\freedom-intelligence\`)
**Soft quota:** 850 GiB · **Hard stop:** 920 GiB
---
## Portfolio snapshot
| Class | Count | Status mix |
| ----- | ----: | ---------- |
| Catalog entries | 12 | see table |
| **verified** on disk | 4 | R embeds + Qwen3-8B + R1-Distill-14B |
| **approved** (pull deferred) | S giants + Llama edge | 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 |
| `models/BAAI__bge-m3/main` | R embed | ~2.1 GiB verified |
| `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.
---
## Decision matrix (2026-07-28)
| Id | Tier | Decision | Disk |
| -- | ---- | -------- | ---- |
| Qwen3-8B | R | **verified** | yes |
| Llama-3.2-3B-Instruct | R | **approved** | deferred — HF gate (need token) |
| 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 |
---
## Hardware coverage gaps
| Need | Status |
| ---- | ------ |
| Default local instruct (8B) | **Covered** (Qwen3-8B) |
| 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) |
| 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.
Tool: `scripts/collect_model.py` (weights-only, sequential, writes `MANIFEST.json`).

View file

@ -1,5 +1,5 @@
id: BAAI__bge-m3__candidate
status: candidate
status: verified
name: bge-m3
org: BAAI
source:
@ -50,9 +50,19 @@ swot:
threats:
- "Leaderboard churn; risk of holding a stale 'default' without re-eval"
- "Pipeline lock-in if vector DBs assume fixed dimension without migration plan"
artifacts:
- path: "pytorch_model.bin"
sha256: "b5e0ce3470abf5ef3831aa1bd5553b486803e83251590ab7ff35a117cf6aad38"
bytes: 2271145830
- path: "sentencepiece.bpe.model"
sha256: "cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865"
bytes: 5069051
- path: "tokenizer.json"
sha256: "21106b6d7dab2952c1d496fb21d5dc9db75c28ed361a05f5020bbba27810dd08"
bytes: 17098108
size:
total_bytes: 0
total_human: "~2 GB"
total_bytes: 2293331623
total_human: "2.14 GiB"
hardware_class:
min_vram_gb_q4: 1
min_vram_gb_fp16: 2
@ -60,11 +70,11 @@ hardware_class:
axes: [B]
priority: high
collection:
approved_by: ""
approved_at: null
downloaded_at: null
downloaded_by: ""
storage_path: ""
approved_by: "bernd"
approved_at: "2026-07-28"
downloaded_at: "2026-07-28"
downloaded_by: "grok"
storage_path: "/mnt/d/vault/coulomb/freedom-intelligence/models/BAAI__bge-m3/main"
brief_refs:
- research/2026-07-24-baseline-field-survey.md
reason: "P0/R multilingual embedding staple for local RAG (docs, ops notes, DE/EN)."
@ -81,3 +91,15 @@ history:
event: profile_swot_added
by: grok
detail: "schema 0.2 profile + SWOT."
- at: "2026-07-28"
event: approved
by: bernd
detail: "R multilingual embed"
- at: "2026-07-28"
event: collected
by: grok
detail: "snapshot_download weights-only to VAULT"
- at: "2026-07-28"
event: verified
by: grok
detail: "MANIFEST.json sha256 for weight files"

View file

@ -79,3 +79,7 @@ history:
event: profile_swot_added
by: grok
detail: "schema 0.2 profile + SWOT."
- at: "2026-07-28"
event: decision_pass
by: bernd
detail: "W — optional after BGE-M3 verified"

View file

@ -80,3 +80,7 @@ history:
event: profile_swot_added
by: grok
detail: "schema 0.2 profile + SWOT."
- at: "2026-07-28"
event: decision_pass
by: bernd
detail: "W — stay candidate until R+S headroom"

View file

@ -1,5 +1,5 @@
id: Qwen__Qwen3-72B__strategic
status: candidate
status: approved
name: Qwen3-72B
org: Qwen
source:
@ -59,8 +59,8 @@ hardware_class:
axes: [A, B, C]
priority: high
collection:
approved_by: ""
approved_at: null
approved_by: "bernd"
approved_at: "2026-07-28"
downloaded_at: null
downloaded_by: ""
storage_path: ""
@ -81,3 +81,11 @@ history:
event: profile_swot_added
by: grok
detail: "schema 0.2 profile + SWOT."
- at: "2026-07-28"
event: approved
by: bernd
detail: "S4 dense Qwen — deferred after R fill; pick vs Llama-70B"
- at: "2026-07-28"
event: collection_deferred
by: grok
detail: "S4 dense Qwen — deferred after R fill; pick vs Llama-70B"

View file

@ -1,5 +1,5 @@
id: Qwen__Qwen3-8B__candidate
status: candidate
status: verified
name: Qwen3-8B
org: Qwen
source:
@ -51,9 +51,34 @@ swot:
threats:
- "Rapid supersession by next Qwen/peer 814B release"
- "Quant quality variance across third-party GGUF repacks"
artifacts:
- path: "merges.txt"
sha256: "8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5"
bytes: 1671853
- path: "model-00001-of-00005.safetensors"
sha256: "31d6a825ae35f11fb85b195b4c42c146c051e446433125a215336abdf95cbf5f"
bytes: 3996250744
- path: "model-00002-of-00005.safetensors"
sha256: "5991236cea6fe21f3d43cab0f0e84448734fbbe0789816202989f2ddc9d18282"
bytes: 3993160032
- path: "model-00003-of-00005.safetensors"
sha256: "c5185c4794be2d8a9784d5753c9922db38df478ce11f9ed0b415b7304d896836"
bytes: 3959604768
- path: "model-00004-of-00005.safetensors"
sha256: "b5ee7de71fbf17db3d5704e0c8f2bc7d005ca9e1d7ca2aeb19827b0cfcaa917a"
bytes: 3187841392
- path: "model-00005-of-00005.safetensors"
sha256: "20c2d6366ab85c90786ccdd829cd2b9e7d30ef3b2ebbb998280e7e4014b542ff"
bytes: 1244659840
- path: "tokenizer.json"
sha256: "aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4"
bytes: 11422654
- path: "vocab.json"
sha256: "ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910"
bytes: 2776833
size:
total_bytes: 0
total_human: "~16 GB fp16 / ~5 GB Q4 (estimate)"
total_bytes: 16397459696
total_human: "15.27 GiB"
hardware_class:
min_vram_gb_q4: 6
min_vram_gb_fp16: 16
@ -61,11 +86,11 @@ hardware_class:
axes: [B, C]
priority: high
collection:
approved_by: ""
approved_at: null
downloaded_at: null
downloaded_by: ""
storage_path: ""
approved_by: "bernd"
approved_at: "2026-07-28"
downloaded_at: "2026-07-28"
downloaded_by: "grok"
storage_path: "/mnt/d/vault/coulomb/freedom-intelligence/models/Qwen__Qwen3-8B/main"
brief_refs:
- research/2026-07-24-baseline-field-survey.md
reason: "P0/R spine — best default open general/tool model for local ops and QLoRA domain specialization."
@ -81,3 +106,15 @@ history:
event: profile_swot_added
by: grok
detail: "schema 0.2 profile + SWOT."
- at: "2026-07-28"
event: approved
by: bernd
detail: "R1 default instruct"
- at: "2026-07-28"
event: collected
by: grok
detail: "snapshot_download weights-only to VAULT"
- at: "2026-07-28"
event: verified
by: grok
detail: "MANIFEST.json sha256 for weight files"

View file

@ -1,5 +1,5 @@
id: deepseek-ai__DeepSeek-R1-Distill-Qwen-14B__candidate
status: candidate
status: verified
name: DeepSeek-R1-Distill-Qwen-14B
org: deepseek-ai
source:
@ -51,9 +51,25 @@ swot:
threats:
- "Newer distill or mid-size reasoners may obsolete this checkpoint"
- "VRAM growth of defaults may push lab to 32B distill instead"
artifacts:
- path: "model-00001-of-000004.safetensors"
sha256: "9a080ebff55b277c0e106f19e4496a88b9f5db4059ea0a6b8ea7d9bb3ad4d0ca"
bytes: 8714116464
- path: "model-00002-of-000004.safetensors"
sha256: "b8bc983706e8db5b270c319be58762f53c6222e0c6cd785c6fd8fd33c2e783e8"
bytes: 8667059663
- path: "model-00003-of-000004.safetensors"
sha256: "557341a00d5c2a75c24e03961d0e716571517d39c70a040633180d9edcbfe285"
bytes: 8667059711
- path: "model-00004-of-000004.safetensors"
sha256: "6ba8a9c8251b8f6c6beef7325102665f22b17c1f52ef76eaaa938bfeab1bd18c"
bytes: 3491898034
- path: "tokenizer.json"
sha256: "88145e3c3249adc2546ede277e9819d6e405e19072456e4b521cbc724bd60773"
bytes: 7031660
size:
total_bytes: 0
total_human: "~28 GB fp16 / ~9 GB Q4 (estimate)"
total_bytes: 29547234556
total_human: "27.52 GiB"
hardware_class:
min_vram_gb_q4: 10
min_vram_gb_fp16: 28
@ -61,11 +77,11 @@ hardware_class:
axes: [B, C]
priority: high
collection:
approved_by: ""
approved_at: null
downloaded_at: null
downloaded_by: ""
storage_path: ""
approved_by: "bernd"
approved_at: "2026-07-28"
downloaded_at: "2026-07-28"
downloaded_by: "grok"
storage_path: "/mnt/d/vault/coulomb/freedom-intelligence/models/deepseek-ai__DeepSeek-R1-Distill-Qwen-14B/main"
brief_refs:
- research/2026-07-24-baseline-field-survey.md
reason: "P0/R local reasoning without full R1 MoE — agent/tool loops and harder offline tasks."
@ -82,3 +98,15 @@ history:
event: profile_swot_added
by: grok
detail: "schema 0.2 profile + SWOT."
- at: "2026-07-28"
event: approved
by: bernd
detail: "R local reason"
- at: "2026-07-28"
event: collected
by: grok
detail: "snapshot_download weights-only to VAULT"
- at: "2026-07-28"
event: verified
by: grok
detail: "MANIFEST.json sha256 for weight files"

View file

@ -80,3 +80,7 @@ history:
event: profile_swot_added
by: grok
detail: "schema 0.2 profile + SWOT."
- at: "2026-07-28"
event: decision_pass
by: bernd
detail: "W — stay candidate; need VRAM+quota"

View file

@ -1,5 +1,5 @@
id: deepseek-ai__DeepSeek-R1__strategic
status: candidate
status: approved
name: DeepSeek-R1
org: deepseek-ai
source:
@ -60,8 +60,8 @@ hardware_class:
axes: [A, B, C]
priority: high
collection:
approved_by: ""
approved_at: null
approved_by: "bernd"
approved_at: "2026-07-28"
downloaded_at: null
downloaded_by: ""
storage_path: ""
@ -82,3 +82,11 @@ history:
event: profile_swot_added
by: grok
detail: "schema 0.2 profile + SWOT."
- at: "2026-07-28"
event: approved
by: bernd
detail: "S2 full reasoner — deferred; 14B distill covers runnable reason"
- at: "2026-07-28"
event: collection_deferred
by: grok
detail: "S2 full reasoner — deferred; 14B distill covers runnable reason"

View file

@ -1,5 +1,5 @@
id: deepseek-ai__DeepSeek-V3__strategic
status: candidate
status: approved
name: DeepSeek-V3
org: deepseek-ai
source:
@ -60,8 +60,8 @@ hardware_class:
axes: [A, B, C]
priority: high
collection:
approved_by: ""
approved_at: null
approved_by: "bernd"
approved_at: "2026-07-28"
downloaded_at: null
downloaded_by: ""
storage_path: ""
@ -81,3 +81,11 @@ history:
event: profile_swot_added
by: grok
detail: "schema 0.2 profile + SWOT."
- at: "2026-07-28"
event: approved
by: bernd
detail: "S1 primary giant — deferred full pull (capacity; prefer official compressed later)"
- at: "2026-07-28"
event: collection_deferred
by: grok
detail: "S1 primary giant — deferred full pull (capacity; prefer official compressed later)"

View file

@ -1,5 +1,5 @@
id: meta-llama__Llama-3.2-3B-Instruct__candidate
status: candidate
status: approved
name: Llama-3.2-3B-Instruct
org: meta-llama
source:
@ -60,8 +60,8 @@ hardware_class:
axes: [B]
priority: high
collection:
approved_by: ""
approved_at: null
approved_by: "bernd"
approved_at: "2026-07-28"
downloaded_at: null
downloaded_by: ""
storage_path: ""
@ -80,3 +80,7 @@ history:
event: profile_swot_added
by: grok
detail: "schema 0.2 profile + SWOT."
- at: "2026-07-28"
event: approved
by: bernd
detail: "R edge (HF gated — pull when token available)"

View file

@ -1,5 +1,5 @@
id: meta-llama__Llama-3.3-70B-Instruct__strategic
status: candidate
status: approved
name: Llama-3.3-70B-Instruct
org: meta-llama
source:
@ -60,8 +60,8 @@ hardware_class:
axes: [A, B, C]
priority: high
collection:
approved_by: ""
approved_at: null
approved_by: "bernd"
approved_at: "2026-07-28"
downloaded_at: null
downloaded_by: ""
storage_path: ""
@ -82,3 +82,11 @@ history:
event: profile_swot_added
by: grok
detail: "schema 0.2 profile + SWOT."
- at: "2026-07-28"
event: approved
by: bernd
detail: "S4 dense Llama — deferred; gated + quota vs Qwen-72B"
- at: "2026-07-28"
event: collection_deferred
by: grok
detail: "S4 dense Llama — deferred; gated + quota vs Qwen-72B"

View file

@ -1,5 +1,5 @@
id: nomic-ai__nomic-embed-text-v1.5__candidate
status: candidate
status: verified
name: nomic-embed-text-v1.5
org: nomic-ai
source:
@ -48,9 +48,13 @@ swot:
threats:
- "Becomes redundant if one embed wins all lab evals"
- "Upstream rename/deprecation of v1.5"
artifacts:
- path: "model.safetensors"
sha256: "9e7d262b1fe5ea350782829496efa831901b77486bbde1cea54a4c822d010d5c"
bytes: 546938168
size:
total_bytes: 0
total_human: "<1 GB"
total_bytes: 547958078
total_human: "0.51 GiB"
hardware_class:
min_vram_gb_q4: 1
min_vram_gb_fp16: 1
@ -58,11 +62,11 @@ hardware_class:
axes: [B]
priority: high
collection:
approved_by: ""
approved_at: null
downloaded_at: null
downloaded_by: ""
storage_path: ""
approved_by: "bernd"
approved_at: "2026-07-28"
downloaded_at: "2026-07-28"
downloaded_by: "grok"
storage_path: "/mnt/d/vault/coulomb/freedom-intelligence/models/nomic-ai__nomic-embed-text-v1.5/main"
brief_refs:
- research/2026-07-24-baseline-field-survey.md
reason: "P0/R lightweight embed for A/B with BGE-M3; long-context text retrieval."
@ -79,3 +83,15 @@ history:
event: profile_swot_added
by: grok
detail: "schema 0.2 profile + SWOT."
- at: "2026-07-28"
event: approved
by: bernd
detail: "R light embed"
- at: "2026-07-28"
event: collected
by: grok
detail: "snapshot_download weights-only to VAULT"
- at: "2026-07-28"
event: verified
by: grok
detail: "MANIFEST.json sha256 for weight files"