Llama-3-8B-Web
A Llama 3 8B instruction-model checkpoint fine-tuned on WebLINX web interactions and dialogue, predicting browser actions from a textual state representation.
AI-assisted editorial review against a primary source. This is a catalog annotation, not an independent reproduction or endorsement.
What is this resource?
- Resource type
- Models and checkpoints
- Environment
- web
- Topics
- web-navigation, imitation-learning, action-prediction
- Record publication date
- Not recorded
- Evidence retrieved
- 2026-10-17T12:34:10Z
- Resource ID
- url:7c3e8c4ba52428584079
What licenses are recorded?
Code, training data, weights, and documents can have different terms. A blank declaration means unknown, not unrestricted use.
- Code
- Not recorded
- Data
- Not recorded
- Document
- Not recorded
- Weights
- Meta Llama 3 Community License Agreement (Weight license text and card declaration are retained separately from framework code licensing.)
License review notes
- Weights: Weight license text and card declaration are retained separately from framework code licensing. Source 1 Source 2
Recorded specifications
- architecture
- LlamaForCausalLM
- availability
- Ungated complete weight/config/tokenizer manifest.
- parameter label
- 8B
- release revision
- 09856c28ec324cf3fe4c513bdc4437a75b78185f
- training data note
- Publisher describes a 24K curated subset of WebLINX interactions and dialogue; not a newly counted independent dataset.
Explore related topics
Scope and limitations
The ungated Hub manifest includes model.safetensors, pytorch_model.bin, config and tokenizer files; the two weight formats represent the same checkpoint and are not counted separately. The card describes an approximately 24K-example curated WebLINX training subset and evaluates dialogue-guided web navigation. Predictions still require parsing and execution in an external browser environment. The retained weight license is the Meta Llama 3 Community License Agreement, not WebLlama code MIT. No weights were downloaded, model used, or agreement accepted.
Related resources
- trained on: WebLINX
- documented by: WebLINX: Real-World Website Navigation with Multi-Turn Dialogue
Primary evidence and verification
Source retrieval is separate from experiment reproduction. Use the original publication or publisher page when citing claims about the resource.
- editorial primary review
Retrieved 2026-10-17T12:34:10Z. Supports: name, kind, summary, environments, topics, scope, notes, relations, licenses.weights.
Content fingerprint
1a445c7894c65c9a7c4247dba446c206c13ac2ecdc129ce93a0de943f2984a18 - editorial primary review
Retrieved 2026-10-17T12:34:10Z. Supports: identity, release_status, details.release_revision, details.architecture.
Content fingerprint
69fe17825db0d5f32ccaa84b67fabfa10018e1410da0c70ec0ea9509703feba2 - editorial primary review
Retrieved 2026-10-17T12:36:55Z. Supports: licenses.weights.
Content fingerprint
6bcca341999ab474e2973116128177b77f97cd64028eeace224035358ce6474f
Suggest a correction
Open a source-backed correction. Include this record ID and the original source. Read our editorial policy and coverage boundaries.