tegwick
77d4ffe86e
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).
120 lines
4.6 KiB
YAML
120 lines
4.6 KiB
YAML
id: Qwen__Qwen3-8B__candidate
|
||
status: verified
|
||
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
|
||
project_url: https://qwenlm.github.io/
|
||
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."
|
||
profile:
|
||
summary: "Default mid-small open instruct for local ops, tools, and domain fine-tunes."
|
||
original_source: https://huggingface.co/Qwen/Qwen3-8B
|
||
use_cases:
|
||
- "Local NetKingdom / Coulomb assistant (chat, docs, runbooks)"
|
||
- "Tool-using agent loops on consumer GPU"
|
||
- "QLoRA / LoRA domain specialization base"
|
||
- "Multilingual (incl. DE/EN) drafting and summarization"
|
||
- "Offline code help when 14B+ is too heavy"
|
||
sweet_spots:
|
||
- "Best balance of quality vs VRAM in the ~8B open class for many 2026 stacks"
|
||
- "Instruction + tool-use oriented workflows"
|
||
- "Homelab fine-tune target (axis C)"
|
||
- "Runnable spine default when one model must wear many hats"
|
||
not_ideal_for:
|
||
- "Hardest SWE-bench-class multi-file engineering (use larger or closed frontier)"
|
||
- "Deep multi-step math/reason vs R1-class distill or full reasoners"
|
||
- "Embedding / retrieval (use BGE-M3 or nomic)"
|
||
capability_notes: >
|
||
Flagship small-mid dense open generalist in the Qwen3 line. Strong multilingual
|
||
and instruct behavior for its size; primary R-tier workhorse for the lab. Prefer
|
||
Instruct sibling on the card if separate repo exists at pin time.
|
||
swot:
|
||
strengths:
|
||
- "High capability density at 8B; Apache-friendly licensing typical"
|
||
- "Good multilingual + tool/instruct posture for local agents"
|
||
- "Excellent FT base for domain specialization"
|
||
weaknesses:
|
||
- "Still far from frontier closed models on hard agentic coding"
|
||
- "8B ceiling on long-horizon planning and rare knowledge"
|
||
opportunities:
|
||
- "Domain LoRAs (security, ops, railiance) on NAS-held base"
|
||
- "Pair with BGE-M3 RAG for grounded NetKingdom answers"
|
||
threats:
|
||
- "Rapid supersession by next Qwen/peer 8–14B 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: 16397459696
|
||
total_human: "15.27 GiB"
|
||
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: "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."
|
||
tags: [tier-r, 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."
|
||
- at: "2026-07-24"
|
||
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"
|