Žinutės

Dabar man ieško ką galima pagerint Ollama su 27B qwen lokaliu modeliu su šitos repositorijos informacija:
https://github.com/Niko1221/Strata

i mean i have gpu. and i already using ollama for embeding etc. so via same gpu i can access ollama cloud models; )

Sveiki ✌🏼 have u tried llama.cpp , why ollama

OLLAMA.com -

su llama leistum pvz -ts 3,1 75% ant 3090, 25% ant 1080 pabaigt

dirba kolega ties windows install instrukcijom 😄 jeigu SaaS tai nesvarbu os jeigu local, tai rerankerio reik embederio reik tai TEI ir OLLAMA ir t.t. daug reikalu 😉 + gpu reik nes su cpu tai nepavelka 🙂

Combined mean for these stress cases:

Ollama semantic: 26.172s
TEI semantic: 4.287s
TEI lexical: 1.181s
TEI made semantic 6.11x faster than Ollama.
Semantic still cost 3.63x lexical with TEI.

ollama *** and must die 😄

liudesiukas ollama tiesa sakant 🙂

tai kad isnaudot gpu su ollama reik 4-8 procesu ir dar balansavimo prieki 🙂

embedingui jo ollama

Bet šis panašu naudoja Ollama, ne pačio rekomenduotą TEI.

nu TEI vietoj ollama, tiek kad jis turi dar ir /rerank endpoint

ir 1 procesas runina 1 modeli skirtingai nei ollama

ir siaip kiek pazystamu benchmark rodo 1 procesas geriau utilizuoja gpu nei ollama

TEI tai rai text embeding interface, biski idomesnis u ollama ir performina geriau

qdarnt + ollama

sqlite + chromadb + local ollama su bge-m3 jokiu servisu except ta viena tavo

su claude code, memory ir t.t. per ollama api

as per ollama glm-5.2:cloud pabandziau

- taskman_open_node_match: session work overlaps OPEN taskman node(s): problem:taskman-stale-confirmed-contract-revalidation-deadlock, problem:taskman-stored-contract-signature-not-reverified, problem:mastermind-gate-items-survive-verified-remedy - re-run each node's verify and POST /api/node/<id>/status {done, proof} (or a progress note) so a future agent does not re-burn tokens on already-done work (mpro-taskman-mandatory.md).
[AGENT-CLEARABLE] Clearable by you: do what the item names (attach the artifact, run the command, or make the edit), then re-run node tools/eidos/mastermind-ask.js agent --quick --json to confirm it cleared.
- commit_outside_project_lane: CROSS-LANE COMMIT from the shared root: files span harness + docs + autonomous + coach + eidos + ecommerce + taskman + seo + ventures. Split it into one commit per lane and work each in its own worktree (node tools/scripts/project-lane.js ensure harness). Measured 2026-07-25: sharing one root cost 272 minutes of lock waiting in a day.
[ENVIRONMENTAL] A commit in this tree fell outside the project lane. Not attributable to your turn - report it, do not revert a peer.
- report_not_delivered: REPORT-WORTHY task answered as CHAT with NO HTML report auto-opened in the CEO Chrome. CEO directive 2026-07-04: after a report-worthy task, write a docs/<topic>/index.html report AND open it in the kiaulakis.lt Chrome (bash tools/scripts/open-in-ceo-chrome.sh "<http url>"), then give the full link. A chat wall is not a deliverable (ceo-output-preferences.md §1/§2b).
[AGENT-CLEARABLE] Clearable by you: do what the item names (attach the artifact, run the command, or make the edit), then re-run node tools/eidos/mastermind-ask.js agent --quick --json to confirm it cleared.
- taskman_done_not_verified: 19 node(s) marked DONE but NOT VERIFIED: problem:c68.dsr-declared-file-list-bypasses-the-unscorable-guard, problem:codex.successor-launcher-env-override-is-a-116ms-oneshot, task:harness.cross-vendor-mcp-registry, fix:mastermind.strip-harness-markup-dead-code, problem:c68.verdict-collector-broken-at-head-blocks-all-validation, problem:codex.recovery-node-ref-minted-without-taskman-confirmation, problem:harness.hand-filed-findings-carry-no-measured-at-or-reprobe, problem:agent-trap.claude-code.unproven-claims-foreign-buffer, problem:jest.nested-pg-copy-crashes-batch-process-fleet-wide, problem:mastermind-session-watcher-orphan-oom-failopen, task:mastermind.report-ui-style-gate, harness.scorecard-aggregate-read-side, problem:host.two-memory-mcp-servers-pegged-88h, problem:zen-tool-registry-missing-modules, task:governance-alert.commit-approval-path-modules, fix:nonstop.health-probe-catchall-reason-and-retry, problem:codex.managed-hook-drift-silently-makes-committed-hook-fixes-inert, problem:mastermind.stop-gate-multiagent-attribution-treadmill, problem:obsbus.mastermind-gate-gate-miss-commit-outside-project-lane. On :3018 done is a CLAIM; VERIFIED is finished (verified-not-done.md, CEO 2026-07-17). Get a real cross-model review (claude / codex / grok / kimi / k3 - never the implementing model reviewing itself; opencode + ollama are OPINION only, not a verification) and/or earn validation from a signed deliverable-edge contract. Do not report these to the CEO as finished.
[AGENT-CLEARABLE] Clearable by you: do what the item names (attach the artifact, run the command, or make the edit), then re-run node tools/eidos/mastermind-ask.js agent --quick --json to confirm it cleared.

Claude, Codex, Kimi, Grok, OpenCode (specialiai, kad bet kurį jame esantį modelį pajungus) ir Ollama (lokaliam mažai protingam modeliui)

Todėl kimi ir opencode su ollama kompe

ollama api lyg

glm 5.2 bandziau su claude per ollama cloud, nusivylimas kodinimui ;)

as ollama turiu

mh o tai per ollama api lyg kogeruojasi thinking ar ne?

nepagalvojau is kart ollama launch claude —model ;D tai claude cli gi turi memory ^^

ollama pasidariau i rnaudoju bge-m3 modeli embedingui ne ta kuris buvo default

kad jau baiges tokenai.. puiki proga isbandyt ollama hermes su glm 5.2 cloud 🙂

tai dar davaibinau self hosted bge-m3 ollama kad palaikytu

gal uzteks kolkas man tada ollama cloud su glm-5.2 bei gemma4:31b del vision 😄

tai ziuresim kiek uzteks ollama cloud uz 20$/men 🙂

jeigu kam idomu ka as cia buildintu, tai "Free opensource" :) https://github.com/atvirokodosprendimai/forumchat galima rasti cia , uztenka docker compose pasileist ir/arba tiesiog docker cmd kad patestuot "puse featuru" ( nes .env reik aprasyt local ollama kad pasiekt modelius )