Model AtlasA selection map of agent foundation models 中文
Start researchModelsPapersGuideCompare 中文

Search the atlas

Esc to close · Cmd/Ctrl + K to open
OpenAI / GPT-3.5

text-davinci-003

Instruction-tuned · 2022-11-28 · Verified
Research summary

Research summary

Good for
Pending verification
Not suitable / limits
LoRA, SFT, RL
How to get it
No
Hardware tier
Inference: API only · LoRA: API only
Paper adoption
3 · Paper adoption
Reproduction risk
Some key facts need verification
Evidence state
Verified · Some key facts need verification
Model positioningGeneralReasoning

Access and distribution ladder

ProductPending verificationPending verification
APIPending verificationPending verification
WeightsNoNo
BaseNoNo
Finetuning allowedNoNo
Derivative distributionNoNo

At a glance

Model positioning
General, Reasoning
Architecture
Other
Parameters
Not disclosed parameters
Active parameters
Not disclosed
Experts
Not disclosed
Experts / token
Not disclosed
Context length
Not reported
Modalities
Text
Open weights
No
Base checkpoint
No
Finetuning allowed
No
Derivatives allowed
No
Commercial use
Yes
License
Not disclosed

Unresolved fields

These fields stay explicit instead of being guessed; verify them against the source or model card.

10 key fields need verification

How to read unknown states

These states intentionally preserve evidence boundaries; they are not false, zero, or definite facts.

Not disclosedThe official source does not disclose this; do not infer that it is absent.
The official source does not disclose this; do not infer that it is absent.
Not applicableThis field does not apply to this record; it is not missing or negative.
This field does not apply to this record; it is not missing or negative.
Not reportedThe source or paper did not report it; this is not false, zero, or confirmed absence.
The source or paper did not report it; this is not false, zero, or confirmed absence.
Not verifiedThe field is retained, but current evidence is not verified; add first-party evidence before relying on it.
The field is retained, but current evidence is not verified; add first-party evidence before relying on it.
Conflicting evidenceFirst-party sources conflict; no single value is selected.
First-party sources conflict; no single value is selected.
Not publishedThe record is not published yet; this is not the same as a broken source link.
The record is not published yet; this is not the same as a broken source link.
UnavailableThe current source is unavailable; do not infer that the fact does not exist.
The current source is unavailable; do not infer that the fact does not exist.

Specializations & research readiness

GeneralReasoning
Inference
Unavailable
LoRA
No
SFT
No
RL
No
Transformers
Not applicable
vLLM
Not applicable
SGLang
Not applicable
veRL recipe
No

Hardware tiers

Inference
API only
LoRA
API only
Full-parameter SFT
API only
RL
API only

Paper adoption

AdaPlanner: Adaptive Planning from Feedback with Language Models

Policy

2023-05-26

CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing

Critic

2023-05-19

WebArena: A Realistic Web Environment for Building Autonomous Agents

Baseline

2023-07-25

Replacement candidates and family versions

Candidates are derived from catalog family, generation, and release metadata; this is not a quality score or a substitute for experiments.