Dontopedia

randygpt

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)

randygpt has 18 facts recorded in Dontopedia across 8 references, with 2 live disagreements.

18 facts·11 predicates·8 sources·2 in dispute

Mostly:rdf:type(4), has variant(4), command line(1)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (3)

Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.

mentionsEntityMentions Entity(1)

mentionsToolMentions Tool(1)

partOfRandyGptProjectPart of Randy Gpt Project(1)

Other facts (17)

The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.

17 facts
PredicateValueRef
Rdf:typeSoftware Tool[5]
Rdf:typeSoftware Project[6]
Rdf:typeSoftware Model[7]
Rdf:typeModel[8]
Has VariantRandygpt Ds[8]
Has VariantRandygpt Ds2[8]
Has VariantRandygpt Ds2 Moe[8]
Has VariantRandygpt 8 L 4 H 128 D[8]
Command Line./target/release/randygpt --bpe 1000 --generate "The quest began" "Ajax looked at" "The machine" "In the darkness"[1]
Generates From PromptsPrompt the Quest Began[1]
Uses Bpe1000[1]
Produces Lengthy RepliesVery[2]
Has Context Window Size256[2]
Context Limited256 Tokens[2]
Contextually Related to Hf DeploymentHf Spaces[3]
Supports Resume FlagTrue[4]
Owned byOther Users[8]

Timeline

Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.

18 undated
—
commandLineblah/random/part-26
./target/release/randygpt --bpe 1000 --generate "The quest began" "Ajax looked at" "The machine" "In the darkness"
—
generatesFromPromptsblah/random/part-26
ex:prompt-the-quest-began
—
usesBpeblah/random/part-26
1000
—
producesLengthyRepliesblah/training-and-evals/part-8
ex:very
—
hasContextWindowSizeblah/training-and-evals/part-8
256
—
contextLimitedblah/training-and-evals/part-8
ex:256-tokens
—
contextuallyRelatedToHfDeploymentblah/training-and-evals/part-18
ex:hf-spaces
—
supportsResumeFlagblah/random/part-25
ex:true
—
typeblah/random/26
ex:SoftwareTool
—
typeblah/random/28
ex:SoftwareProject
—
typeblah/training-and-evals/8
ex:SoftwareModel
—
typeblah/training-and-evals/36
ex:Model
—
labelblah/training-and-evals/36
randygpt
—
ownedByblah/training-and-evals/36
ex:other-users
—
hasVariantblah/training-and-evals/36
ex:randygpt-ds
—
hasVariantblah/training-and-evals/36
ex:randygpt-ds2
—
hasVariantblah/training-and-evals/36
ex:randygpt-ds2-moe
—
hasVariantblah/training-and-evals/36
ex:randygpt-8L-4H-128D

References (8)

8 references
  1. [1]Part 263 facts
    ctx:discord/blah/random/part-26
  2. [2]Part 83 facts
    ctx:discord/blah/training-and-evals/part-8
  3. [3]Part 181 fact
    ctx:discord/blah/training-and-evals/part-18
  4. [4]Part 251 fact
    ctx:discord/blah/random/part-25
  5. [5]261 fact
    ctx:discord/blah/random/26
    • full textrandom-26
      text/plain2 KBdoc:agent/random-26/5a36b1b4-32d2-4f8a-ab06-c46ec2a2e6df
      Show excerpt
      [2026-02-17 14:19] xenonfun: had it make a model-xs and your 2nd set of books, will see if it comes up with same basic result, not quite sure your combo or parms couldn't get exact. ``` # Custom prompts …
  6. [6]281 fact
    ctx:discord/blah/random/28
    • full textrandom-28
      text/plain2 KBdoc:agent/random-28/d1c103cf-de94-477e-9407-903eb1cdff93
      Show excerpt
      [2026-02-17 19:43] xenonfun: stalled here: ``` Iter 4300 | Loss: 3.7543 | Val: 3.7114 (ppl 40.9) | LR: 0.000030 | Best val: 3.6677 | 877ms/iter | 1353s elapsed | ETA 6750s | Patience: 20/20 Early stopping: val loss hasn't improved for 20 …
  7. [7]81 fact
    ctx:discord/blah/training-and-evals/8
    • full texttraining-and-evals-8
      text/plain3 KBdoc:agent/training-and-evals-8/899f7569-fa48-4e31-97e1-95543997fb9f
      Show excerpt
      [2026-02-20 00:31] ajaxdavis: reminder to self: check how much that cost with gpt5.2 (files: Screenshot_2026-02-20_at_10.31.22_AM.png) [2026-02-20 03:52] ajaxdavis: https://evals.blah.dev/chatroom chatroom is running more reliably [2026-02-…
  8. [8]367 facts
    ctx:discord/blah/training-and-evals/36
    • full texttraining-and-evals-36
      text/plain2 KBdoc:agent/training-and-evals-36/e61090f7-7431-47f0-b835-781e4bbe98b3
      Show excerpt
      [2026-03-08 06:59] foxhop.: i attempted to upload my latest models and ended up loaded like 30 so i attempt to clean up and claude removed everything...  Shell cwd was reset to /home/fox/git/uncloseai-cli …

See also

Keep researching

Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.

↑