Establish Freedom Intelligence lab foundation and baseline research.
Add INTENT/SCOPE, daily-brief playbook, activity-core definition (disabled), workplans FI-WP-0001..0003, baseline field survey with open-weight collection recommendations, and inventory catalog candidates for the model reserve.
This commit is contained in:
parent
1dc1e09517
commit
b5f911140b
28 changed files with 2651 additions and 1 deletions
32
inventory/README.md
Normal file
32
inventory/README.md
Normal file
|
|
@ -0,0 +1,32 @@
|
|||
# Model inventory
|
||||
|
||||
In-repo **catalog of open-weight revisions** reserved (or nominated) for the lab.
|
||||
Weight blobs live on backup storage — see `docs/backup-storage-policy.md`.
|
||||
|
||||
## Layout
|
||||
|
||||
```text
|
||||
inventory/
|
||||
├── README.md # this file
|
||||
├── schema.yaml # field reference + example
|
||||
├── collection-policy.md # approval and eligibility rules
|
||||
└── catalog/
|
||||
└── *.yaml # one file per model revision
|
||||
```
|
||||
|
||||
## Status values
|
||||
|
||||
`candidate` → `approved` → `collecting` → `collected` → `verified`
|
||||
also: `superseded` | `evicted` | `rejected`
|
||||
|
||||
## Adding an entry
|
||||
|
||||
1. Confirm eligibility in `collection-policy.md`.
|
||||
2. Create `catalog/{org}__{name}__{short_revision}.yaml` using fields from `schema.yaml`.
|
||||
3. Set `status: candidate` (or `approved` if already signed off).
|
||||
4. After download and checksums: set `collected` / `verified` and `collection.storage_path`.
|
||||
|
||||
## Empty catalog
|
||||
|
||||
The catalog starts empty on purpose. First entries come from daily brief
|
||||
**collection candidates** after policy checks — not from bulk scraping.
|
||||
0
inventory/catalog/.gitkeep
Normal file
0
inventory/catalog/.gitkeep
Normal file
42
inventory/catalog/BAAI__bge-m3__candidate.yaml
Normal file
42
inventory/catalog/BAAI__bge-m3__candidate.yaml
Normal file
|
|
@ -0,0 +1,42 @@
|
|||
id: BAAI__bge-m3__candidate
|
||||
status: candidate
|
||||
name: bge-m3
|
||||
org: BAAI
|
||||
source:
|
||||
kind: huggingface
|
||||
url: https://huggingface.co/BAAI/bge-m3
|
||||
revision: main
|
||||
model_card_url: https://huggingface.co/BAAI/bge-m3
|
||||
license:
|
||||
spdx: MIT
|
||||
url: https://huggingface.co/BAAI/bge-m3
|
||||
allows_offline_retention: true
|
||||
allows_local_ops: true
|
||||
allows_fine_tune: true
|
||||
notes: ""
|
||||
size:
|
||||
total_bytes: 0
|
||||
total_human: "~2 GB"
|
||||
hardware_class:
|
||||
min_vram_gb_q4: 1
|
||||
min_vram_gb_fp16: 2
|
||||
notes: "Runs on CPU comfortably for many workloads"
|
||||
axes: [B]
|
||||
priority: high
|
||||
collection:
|
||||
approved_by: ""
|
||||
approved_at: null
|
||||
downloaded_at: null
|
||||
downloaded_by: ""
|
||||
storage_path: ""
|
||||
brief_refs:
|
||||
- research/2026-07-24-baseline-field-survey.md
|
||||
reason: "P0 multilingual embedding staple for local RAG (docs, ops notes, DE/EN)."
|
||||
tags: [embedding, multilingual, rag]
|
||||
companions: []
|
||||
notes: "Small download — within agent auto-collect band after license check once storage pinned."
|
||||
history:
|
||||
- at: "2026-07-24"
|
||||
event: nominated
|
||||
by: baseline-survey
|
||||
detail: "P0 recommendation from initial deep research."
|
||||
43
inventory/catalog/BAAI__bge-reranker-v2-m3__candidate.yaml
Normal file
43
inventory/catalog/BAAI__bge-reranker-v2-m3__candidate.yaml
Normal file
|
|
@ -0,0 +1,43 @@
|
|||
id: BAAI__bge-reranker-v2-m3__candidate
|
||||
status: candidate
|
||||
name: bge-reranker-v2-m3
|
||||
org: BAAI
|
||||
source:
|
||||
kind: huggingface
|
||||
url: https://huggingface.co/BAAI/bge-reranker-v2-m3
|
||||
revision: main
|
||||
model_card_url: https://huggingface.co/BAAI/bge-reranker-v2-m3
|
||||
license:
|
||||
spdx: Apache-2.0
|
||||
url: https://huggingface.co/BAAI/bge-reranker-v2-m3
|
||||
allows_offline_retention: true
|
||||
allows_local_ops: true
|
||||
allows_fine_tune: true
|
||||
notes: "Confirm SPDX on card."
|
||||
size:
|
||||
total_bytes: 0
|
||||
total_human: "~1–2 GB (estimate)"
|
||||
hardware_class:
|
||||
min_vram_gb_q4: 1
|
||||
min_vram_gb_fp16: 2
|
||||
notes: "Companion to bge-m3"
|
||||
axes: [B]
|
||||
priority: medium
|
||||
collection:
|
||||
approved_by: ""
|
||||
approved_at: null
|
||||
downloaded_at: null
|
||||
downloaded_by: ""
|
||||
storage_path: ""
|
||||
brief_refs:
|
||||
- research/2026-07-24-baseline-field-survey.md
|
||||
reason: "P1 — cheap RAG quality win as companion to BGE-M3."
|
||||
tags: [reranker, rag]
|
||||
companions:
|
||||
- BAAI__bge-m3__candidate
|
||||
notes: ""
|
||||
history:
|
||||
- at: "2026-07-24"
|
||||
event: nominated
|
||||
by: baseline-survey
|
||||
detail: "P1 recommendation from initial deep research."
|
||||
42
inventory/catalog/Qwen__Qwen3-14B__candidate.yaml
Normal file
42
inventory/catalog/Qwen__Qwen3-14B__candidate.yaml
Normal file
|
|
@ -0,0 +1,42 @@
|
|||
id: Qwen__Qwen3-14B__candidate
|
||||
status: candidate
|
||||
name: Qwen3-14B
|
||||
org: Qwen
|
||||
source:
|
||||
kind: huggingface
|
||||
url: https://huggingface.co/Qwen/Qwen3-14B
|
||||
revision: main
|
||||
model_card_url: https://huggingface.co/Qwen/Qwen3-14B
|
||||
license:
|
||||
spdx: Apache-2.0
|
||||
url: https://huggingface.co/Qwen/Qwen3-14B
|
||||
allows_offline_retention: true
|
||||
allows_local_ops: true
|
||||
allows_fine_tune: true
|
||||
notes: "Confirm card at download."
|
||||
size:
|
||||
total_bytes: 0
|
||||
total_human: "~28 GB fp16 / ~9 GB Q4 (estimate)"
|
||||
hardware_class:
|
||||
min_vram_gb_q4: 10
|
||||
min_vram_gb_fp16: 28
|
||||
notes: "T2 quality step"
|
||||
axes: [B, C]
|
||||
priority: medium
|
||||
collection:
|
||||
approved_by: ""
|
||||
approved_at: null
|
||||
downloaded_at: null
|
||||
downloaded_by: ""
|
||||
storage_path: ""
|
||||
brief_refs:
|
||||
- research/2026-07-24-baseline-field-survey.md
|
||||
reason: "P1 — stronger single-GPU chat/code when quota allows after P0."
|
||||
tags: [instruct, qwen3]
|
||||
companions: []
|
||||
notes: ""
|
||||
history:
|
||||
- at: "2026-07-24"
|
||||
event: nominated
|
||||
by: baseline-survey
|
||||
detail: "P1 recommendation from initial deep research."
|
||||
42
inventory/catalog/Qwen__Qwen3-8B__candidate.yaml
Normal file
42
inventory/catalog/Qwen__Qwen3-8B__candidate.yaml
Normal file
|
|
@ -0,0 +1,42 @@
|
|||
id: Qwen__Qwen3-8B__candidate
|
||||
status: candidate
|
||||
name: Qwen3-8B
|
||||
org: Qwen
|
||||
source:
|
||||
kind: huggingface
|
||||
url: https://huggingface.co/Qwen/Qwen3-8B
|
||||
revision: main
|
||||
model_card_url: https://huggingface.co/Qwen/Qwen3-8B
|
||||
license:
|
||||
spdx: Apache-2.0
|
||||
url: https://huggingface.co/Qwen/Qwen3-8B
|
||||
allows_offline_retention: true
|
||||
allows_local_ops: true
|
||||
allows_fine_tune: true
|
||||
notes: "Confirm exact card license at download time; Qwen3 line generally Apache-2.0."
|
||||
size:
|
||||
total_bytes: 0
|
||||
total_human: "~16 GB fp16 / ~5 GB Q4 (estimate)"
|
||||
hardware_class:
|
||||
min_vram_gb_q4: 6
|
||||
min_vram_gb_fp16: 16
|
||||
notes: "Default T1–T2 general instruct and FT base"
|
||||
axes: [B, C]
|
||||
priority: high
|
||||
collection:
|
||||
approved_by: ""
|
||||
approved_at: null
|
||||
downloaded_at: null
|
||||
downloaded_by: ""
|
||||
storage_path: ""
|
||||
brief_refs:
|
||||
- research/2026-07-24-baseline-field-survey.md
|
||||
reason: "P0 spine — best default open general/tool model for local ops and QLoRA domain specialization."
|
||||
tags: [instruct, text, qwen3, ft-base]
|
||||
companions: []
|
||||
notes: "Prefer Instruct variant on card if separate repo; pin commit SHA at collection."
|
||||
history:
|
||||
- at: "2026-07-24"
|
||||
event: nominated
|
||||
by: baseline-survey
|
||||
detail: "P0 recommendation from initial deep research."
|
||||
|
|
@ -0,0 +1,42 @@
|
|||
id: deepseek-ai__DeepSeek-R1-Distill-Qwen-14B__candidate
|
||||
status: candidate
|
||||
name: DeepSeek-R1-Distill-Qwen-14B
|
||||
org: deepseek-ai
|
||||
source:
|
||||
kind: huggingface
|
||||
url: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
|
||||
revision: main
|
||||
model_card_url: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
|
||||
license:
|
||||
spdx: MIT
|
||||
url: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
|
||||
allows_offline_retention: true
|
||||
allows_local_ops: true
|
||||
allows_fine_tune: true
|
||||
notes: "R1 distill series MIT — confirm card at pin time."
|
||||
size:
|
||||
total_bytes: 0
|
||||
total_human: "~28 GB fp16 / ~9 GB Q4 (estimate)"
|
||||
hardware_class:
|
||||
min_vram_gb_q4: 10
|
||||
min_vram_gb_fp16: 28
|
||||
notes: "T2 Q4 preferred; fall back to 8B distill if VRAM tight"
|
||||
axes: [B, C]
|
||||
priority: high
|
||||
collection:
|
||||
approved_by: ""
|
||||
approved_at: null
|
||||
downloaded_at: null
|
||||
downloaded_by: ""
|
||||
storage_path: ""
|
||||
brief_refs:
|
||||
- research/2026-07-24-baseline-field-survey.md
|
||||
reason: "P0 local reasoning without full R1 MoE — agent/tool loops and harder offline tasks."
|
||||
tags: [reasoning, distill, deepseek]
|
||||
companions: []
|
||||
notes: "If disk/VRAM constrained, substitute DeepSeek-R1-Distill-Qwen-8B as P0 alternate."
|
||||
history:
|
||||
- at: "2026-07-24"
|
||||
event: nominated
|
||||
by: baseline-survey
|
||||
detail: "P0 recommendation from initial deep research."
|
||||
|
|
@ -0,0 +1,42 @@
|
|||
id: deepseek-ai__DeepSeek-R1-Distill-Qwen-32B__candidate
|
||||
status: candidate
|
||||
name: DeepSeek-R1-Distill-Qwen-32B
|
||||
org: deepseek-ai
|
||||
source:
|
||||
kind: huggingface
|
||||
url: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
|
||||
revision: main
|
||||
model_card_url: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
|
||||
license:
|
||||
spdx: MIT
|
||||
url: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
|
||||
allows_offline_retention: true
|
||||
allows_local_ops: true
|
||||
allows_fine_tune: true
|
||||
notes: ""
|
||||
size:
|
||||
total_bytes: 0
|
||||
total_human: "~65 GB fp16 / ~20 GB Q4 (estimate)"
|
||||
hardware_class:
|
||||
min_vram_gb_q4: 20
|
||||
min_vram_gb_fp16: 64
|
||||
notes: "T2–T3; only if hardware envelope supports"
|
||||
axes: [B, C]
|
||||
priority: medium
|
||||
collection:
|
||||
approved_by: ""
|
||||
approved_at: null
|
||||
downloaded_at: null
|
||||
downloaded_by: ""
|
||||
storage_path: ""
|
||||
brief_refs:
|
||||
- research/2026-07-24-baseline-field-survey.md
|
||||
reason: "P1 stronger local reasoner — approve only with VRAM + quota headroom."
|
||||
tags: [reasoning, distill, deepseek]
|
||||
companions: []
|
||||
notes: "Do not collect full DeepSeek-V3/R1 MoE under this id."
|
||||
history:
|
||||
- at: "2026-07-24"
|
||||
event: nominated
|
||||
by: baseline-survey
|
||||
detail: "P1 recommendation from initial deep research."
|
||||
|
|
@ -0,0 +1,42 @@
|
|||
id: meta-llama__Llama-3.2-3B-Instruct__candidate
|
||||
status: candidate
|
||||
name: Llama-3.2-3B-Instruct
|
||||
org: meta-llama
|
||||
source:
|
||||
kind: huggingface
|
||||
url: https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct
|
||||
revision: main
|
||||
model_card_url: https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct
|
||||
license:
|
||||
spdx: custom
|
||||
url: https://ai.meta.com/llama/license/
|
||||
allows_offline_retention: true
|
||||
allows_local_ops: true
|
||||
allows_fine_tune: true
|
||||
notes: "Llama Community License — not MIT; review terms before commercial redistribution."
|
||||
size:
|
||||
total_bytes: 0
|
||||
total_human: "~6 GB fp16 / ~2 GB Q4 (estimate)"
|
||||
hardware_class:
|
||||
min_vram_gb_q4: 3
|
||||
min_vram_gb_fp16: 8
|
||||
notes: "T0–T1 edge / always-on"
|
||||
axes: [B]
|
||||
priority: high
|
||||
collection:
|
||||
approved_by: ""
|
||||
approved_at: null
|
||||
downloaded_at: null
|
||||
downloaded_by: ""
|
||||
storage_path: ""
|
||||
brief_refs:
|
||||
- research/2026-07-24-baseline-field-survey.md
|
||||
reason: "P0 edge instruct — tiny, huge ecosystem, good CPU/GPU floor for agents."
|
||||
tags: [instruct, edge, llama]
|
||||
companions: []
|
||||
notes: "HF gated model — need accepted license on account before download."
|
||||
history:
|
||||
- at: "2026-07-24"
|
||||
event: nominated
|
||||
by: baseline-survey
|
||||
detail: "P0 recommendation from initial deep research."
|
||||
|
|
@ -0,0 +1,42 @@
|
|||
id: nomic-ai__nomic-embed-text-v1.5__candidate
|
||||
status: candidate
|
||||
name: nomic-embed-text-v1.5
|
||||
org: nomic-ai
|
||||
source:
|
||||
kind: huggingface
|
||||
url: https://huggingface.co/nomic-ai/nomic-embed-text-v1.5
|
||||
revision: main
|
||||
model_card_url: https://huggingface.co/nomic-ai/nomic-embed-text-v1.5
|
||||
license:
|
||||
spdx: Apache-2.0
|
||||
url: https://huggingface.co/nomic-ai/nomic-embed-text-v1.5
|
||||
allows_offline_retention: true
|
||||
allows_local_ops: true
|
||||
allows_fine_tune: true
|
||||
notes: ""
|
||||
size:
|
||||
total_bytes: 0
|
||||
total_human: "<1 GB"
|
||||
hardware_class:
|
||||
min_vram_gb_q4: 1
|
||||
min_vram_gb_fp16: 1
|
||||
notes: "CPU-friendly"
|
||||
axes: [B]
|
||||
priority: high
|
||||
collection:
|
||||
approved_by: ""
|
||||
approved_at: null
|
||||
downloaded_at: null
|
||||
downloaded_by: ""
|
||||
storage_path: ""
|
||||
brief_refs:
|
||||
- research/2026-07-24-baseline-field-survey.md
|
||||
reason: "P0 lightweight embed for A/B with BGE-M3; long-context text retrieval."
|
||||
tags: [embedding, rag]
|
||||
companions: []
|
||||
notes: "If v2 text is preferred at collection time, update id/url and supersede this candidate."
|
||||
history:
|
||||
- at: "2026-07-24"
|
||||
event: nominated
|
||||
by: baseline-survey
|
||||
detail: "P0 recommendation from initial deep research."
|
||||
134
inventory/collection-policy.md
Normal file
134
inventory/collection-policy.md
Normal file
|
|
@ -0,0 +1,134 @@
|
|||
# Collection policy — open-weight reserve
|
||||
|
||||
**Status:** foundation
|
||||
**Related:** `schema.yaml`, `docs/backup-storage-policy.md`, `INTENT.md`
|
||||
|
||||
---
|
||||
|
||||
## Purpose
|
||||
|
||||
Decide **what** enters the open-weight reserve, **who** may approve it, and
|
||||
**when** a daily-brief candidate becomes a catalog entry with blobs on backup
|
||||
storage.
|
||||
|
||||
---
|
||||
|
||||
## Goals
|
||||
|
||||
* Keep a **small, high-leverage** reserve — not a Hugging Face mirror
|
||||
* Enforce **license and integrity** before download completes
|
||||
* Match capacity to the backup storage soft quota
|
||||
* Prefer models that serve axes **B** and **C**, plus strategic **A** open releases
|
||||
|
||||
---
|
||||
|
||||
## Eligibility (must pass all)
|
||||
|
||||
1. **Open weights** — weights obtainable under terms that allow offline retention for lab use
|
||||
2. **Clear license** — SPDX or linkable license text; `allows_offline_retention: true`
|
||||
3. **Stable provenance** — official org, tagged release, or commit revision (not anonymous drive-by reupload as sole source)
|
||||
4. **Lab rationale** — written `reason` tied to at least one axis A–D (usually B/C)
|
||||
5. **Capacity** — estimated size fits under remaining soft quota (see backup storage policy)
|
||||
|
||||
Fail any gate → status `rejected` with reason, or never enter catalog.
|
||||
|
||||
---
|
||||
|
||||
## Priority rubric
|
||||
|
||||
| Priority | Guidance |
|
||||
| -------- | -------- |
|
||||
| **high** | Rare or strategically important; license/access risk of disappearance; uniquely strong for B/C at our hardware class; hard to re-obtain |
|
||||
| **medium** | Clear lab use within 1–2 quarters; good quality/cost; easy enough to re-download but worth having cold |
|
||||
| **low** | Nice to have; only collect if quota headroom is large and pull is cheap |
|
||||
|
||||
Daily brief **collection candidates** should set a suggested priority; approval may change it.
|
||||
|
||||
---
|
||||
|
||||
## Approval rule of thumb
|
||||
|
||||
| Estimated total size | Approval |
|
||||
| -------------------- | -------- |
|
||||
| **< 5 GiB** | Operator or lab agent may collect after license check; catalog entry required before or immediately after |
|
||||
| **5–40 GiB** | Explicit operator approval (chat, workplan task, or signed catalog `approved_by`) |
|
||||
| **> 40 GiB** | Operator approval **plus** check against soft quota and whether a smaller quant/variant suffices |
|
||||
| **Any size if quota ≥ 70% used** | Operator approval required regardless of size |
|
||||
| **Unclear license or ToS risk** | Do not collect; status `rejected` |
|
||||
|
||||
“Operator” means the human lab owner (or a documented delegate). Agents may
|
||||
**nominate** (`status: candidate`) freely from briefs; they may **collect** only
|
||||
within the < 5 GiB band when licenses are unambiguous — otherwise stop at
|
||||
`candidate` / `approved`.
|
||||
|
||||
---
|
||||
|
||||
## Lifecycle
|
||||
|
||||
```text
|
||||
brief nominates
|
||||
→ candidate (catalog YAML, no blobs required)
|
||||
→ approved (license + size + quota OK)
|
||||
→ collecting (download in staging/)
|
||||
→ collected (blobs complete, checksums recorded, storage_path set)
|
||||
→ verified (optional re-hash / smoke load)
|
||||
→ superseded|evicted (replaced or removed; metadata kept)
|
||||
```
|
||||
|
||||
Rejected candidates stay in catalog only if useful as a decision record; otherwise omit.
|
||||
|
||||
---
|
||||
|
||||
## What we prefer to collect
|
||||
|
||||
* Small/mid instruct and code models that fit the hardware envelope
|
||||
* Strong embedding / rerank models for local RAG
|
||||
* Base models known to fine-tune well under QLoRA/LoRA on lab GPUs
|
||||
* Official quant releases when they are the supported distribution
|
||||
* Adapters and tokenizers that unlock a reserved base (as companions)
|
||||
|
||||
## What we usually skip
|
||||
|
||||
* Duplicate quants of the same revision already reserved
|
||||
* Huge models with no near-term local run/train path and no access-risk story
|
||||
* Merges/repacks without provenance
|
||||
* Datasets larger than model weights unless separately justified (default: out of band)
|
||||
* Anything requiring acceptance flows we cannot satisfy offline
|
||||
|
||||
---
|
||||
|
||||
## Companions
|
||||
|
||||
Tokenizers, LoRA adapters, and small eval fixtures may be collected when:
|
||||
|
||||
* they are required to use a reserved base, or
|
||||
* they are small (< 1 GiB) and high leverage
|
||||
|
||||
Link via `companions` in the catalog schema.
|
||||
|
||||
---
|
||||
|
||||
## Brief integration
|
||||
|
||||
1. Brief section **Collection candidates** nominates items.
|
||||
2. Operator/agent opens `inventory/catalog/{id}.yaml` with `status: candidate`.
|
||||
3. Approval and download follow this policy and `docs/backup-storage-policy.md`.
|
||||
4. Brief `brief_refs` on the entry point back to the nominating day(s).
|
||||
|
||||
---
|
||||
|
||||
## Eviction rule of thumb
|
||||
|
||||
When over quota or cleaning:
|
||||
|
||||
1. `low` priority, easily re-obtainable from still-live official URLs
|
||||
2. Superseded revisions with a newer `verified` replacement
|
||||
3. Never silent-delete: set `status: evicted`, clear or note `storage_path`, append `history`
|
||||
|
||||
---
|
||||
|
||||
## Non-goals
|
||||
|
||||
* Automatic bulk mirrors of entire orgs
|
||||
* Collecting on every brief mention without priority
|
||||
* Bypassing license gates for “research only” convenience
|
||||
118
inventory/schema.yaml
Normal file
118
inventory/schema.yaml
Normal file
|
|
@ -0,0 +1,118 @@
|
|||
# Freedom Intelligence — open-weight inventory entry schema
|
||||
# Each collected (or tracked) model revision is one YAML file under catalog/
|
||||
# Filename suggestion: {org}__{name}__{short_revision}.yaml
|
||||
#
|
||||
# Schema version documents field meaning for humans and future validators.
|
||||
schema_version: "0.1.0"
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Example entry (illustrative only — not a real collection claim)
|
||||
# ---------------------------------------------------------------------------
|
||||
# id: meta-llama__Llama-3.2-3B-Instruct__abc1234
|
||||
# status: candidate | approved | collecting | collected | verified | superseded | evicted | rejected
|
||||
# name: Llama-3.2-3B-Instruct
|
||||
# org: meta-llama
|
||||
# source:
|
||||
# kind: huggingface # huggingface | github_release | direct_url | other
|
||||
# url: https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct
|
||||
# revision: abc1234def... # commit sha, tag, or release id
|
||||
# model_card_url: https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct
|
||||
# license:
|
||||
# spdx: llama3.2 # or MIT, Apache-2.0, etc.; use "custom" + notes if needed
|
||||
# url: https://...
|
||||
# allows_offline_retention: true
|
||||
# allows_local_ops: true
|
||||
# allows_fine_tune: true
|
||||
# notes: ""
|
||||
# artifacts:
|
||||
# - path: blobs/model.safetensors
|
||||
# sha256: "..."
|
||||
# bytes: 0
|
||||
# size:
|
||||
# total_bytes: 0
|
||||
# total_human: "0 B"
|
||||
# hardware_class:
|
||||
# # Rough lab guidance — not a guarantee
|
||||
# min_vram_gb_q4: 4
|
||||
# min_vram_gb_fp16: 8
|
||||
# notes: "fits consumer 8GB at Q4"
|
||||
# axes: # why this matters to the lab
|
||||
# - B
|
||||
# - C
|
||||
# priority: medium # low | medium | high
|
||||
# collection:
|
||||
# approved_by: ""
|
||||
# approved_at: null # ISO-8601 date
|
||||
# downloaded_at: null
|
||||
# downloaded_by: ""
|
||||
# storage_path: "" # absolute or facility-relative path on backup storage
|
||||
# brief_refs: # briefs that nominated this candidate
|
||||
# - briefs/2026/07/2026-07-23.md
|
||||
# reason: "Strong small instruct base; clear license; homelab-fit."
|
||||
# tags:
|
||||
# - instruct
|
||||
# - text
|
||||
# companions: [] # optional related catalog ids (adapters, tokenizers)
|
||||
# notes: ""
|
||||
# history:
|
||||
# - at: "2026-07-23"
|
||||
# event: nominated
|
||||
# by: operator
|
||||
# detail: "From daily brief collection candidates."
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Required fields by status (normative for humans; tooling may enforce later)
|
||||
# ---------------------------------------------------------------------------
|
||||
# candidate: id, status, name, org, source.url, source.revision, license, reason, priority
|
||||
# approved: + collection.approved_by, collection.approved_at
|
||||
# collected: + collection.downloaded_at, collection.storage_path, size, artifacts[].sha256
|
||||
# verified: + checksums re-read OK (notes or history event)
|
||||
# rejected: + reason (why rejected)
|
||||
# superseded / evicted: + history event; storage_path may be empty after eviction
|
||||
|
||||
field_reference:
|
||||
id:
|
||||
type: string
|
||||
description: Stable catalog id; prefer {org}__{name}__{short_revision}
|
||||
status:
|
||||
type: enum
|
||||
values: [candidate, approved, collecting, collected, verified, superseded, evicted, rejected]
|
||||
name:
|
||||
type: string
|
||||
org:
|
||||
type: string
|
||||
source:
|
||||
type: object
|
||||
fields: [kind, url, revision, model_card_url]
|
||||
license:
|
||||
type: object
|
||||
fields: [spdx, url, allows_offline_retention, allows_local_ops, allows_fine_tune, notes]
|
||||
artifacts:
|
||||
type: list
|
||||
item_fields: [path, sha256, bytes]
|
||||
size:
|
||||
type: object
|
||||
fields: [total_bytes, total_human]
|
||||
hardware_class:
|
||||
type: object
|
||||
fields: [min_vram_gb_q4, min_vram_gb_fp16, notes]
|
||||
axes:
|
||||
type: list
|
||||
values: [A, B, C, D]
|
||||
priority:
|
||||
type: enum
|
||||
values: [low, medium, high]
|
||||
collection:
|
||||
type: object
|
||||
fields: [approved_by, approved_at, downloaded_at, downloaded_by, storage_path, brief_refs]
|
||||
reason:
|
||||
type: string
|
||||
tags:
|
||||
type: list
|
||||
companions:
|
||||
type: list
|
||||
notes:
|
||||
type: string
|
||||
history:
|
||||
type: list
|
||||
item_fields: [at, event, by, detail]
|
||||
Loading…
Add table
Add a link
Reference in a new issue