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).
112 lines
4.3 KiB
YAML
112 lines
4.3 KiB
YAML
id: deepseek-ai__DeepSeek-R1-Distill-Qwen-14B__candidate
|
|
status: verified
|
|
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
|
|
project_url: https://github.com/deepseek-ai/DeepSeek-R1
|
|
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."
|
|
profile:
|
|
summary: "Local reasoning-specialist distill — hard tasks without full R1 MoE."
|
|
original_source: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
|
|
use_cases:
|
|
- "Offline multi-step reasoning (math, logic, planning sketches)"
|
|
- "Harder agent tool-selection and self-checks"
|
|
- "Local alternative when DeepSeek API is unavailable"
|
|
- "Eval harness baseline for 'reason' quality on lab tasks"
|
|
- "QLoRA experiments on reason-style behavior"
|
|
sweet_spots:
|
|
- "Reasoning quality above plain 14B chat models at similar size"
|
|
- "Single enthusiast GPU (Q4) without multi-node MoE"
|
|
- "MIT-friendly open reason lineage"
|
|
not_ideal_for:
|
|
- "Cheapest always-on chat (use 3B/8B)"
|
|
- "Full parity with frontier closed reasoners or full R1"
|
|
- "Pure embedding"
|
|
capability_notes: >
|
|
Distilled from DeepSeek-R1 into a Qwen-14B-class dense student. Captures much
|
|
of the reasoner value proposition for homelab VRAM budgets. Primary R-tier
|
|
reason model; full R1 remains strategic S-tier.
|
|
swot:
|
|
strengths:
|
|
- "Strong open reasoner at single-GPU scale"
|
|
- "MIT distill story; clear provenance from R1 line"
|
|
- "Complements general 8B chat without replacing it"
|
|
weaknesses:
|
|
- "Heavier and slower than 8B for routine chat"
|
|
- "Distill ≠ full R1; still loses on hardest problems"
|
|
- "May overthink simple tasks if not prompted carefully"
|
|
opportunities:
|
|
- "Route only hard queries here; keep 8B as default"
|
|
- "Domain FT for structured ops decision checklists"
|
|
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: 29547234556
|
|
total_human: "27.52 GiB"
|
|
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: "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."
|
|
tags: [tier-r, reasoning, distill, deepseek]
|
|
companions:
|
|
- deepseek-ai__DeepSeek-R1__strategic
|
|
notes: "If disk/VRAM constrained, substitute DeepSeek-R1-Distill-Qwen-8B as R alternate."
|
|
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: "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"
|