web-llm-v1.8 is an open-weight model from Quachttohai. Its published files total 2.5 GB.
Parameters—
Context—
Weights2.3 GB
License—
AccessOpen weights
Monthly Downloads—
Model Card
The publisher has not written a card for this model.
Identity and Version
- Repository
- quachtohai/web-llm-v1.8
- Publisher
- Quachttohai
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 6e5da3c774837c25a627d117ffa39890e17edb06
- First published
- 2026-09-25
- Last updated
- 2026-09-25
Files and Weights
60 files, 2.5 GB in total. The weights are 16 files totalling 2.3 GB in pt.
Weights16 files · 2.3 GB
Configuration29 files · 2.6 MB
Tokenizer2 files · 409.8 KB
Other12 files · 209.7 MB
Repository1 file · 2.0 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| checkpoints/v18_training/step_0025.pt | Weights | 167.1 MB | 338f6ba70630 |
| checkpoints/v18_training/step_0050.pt | Weights | 167.1 MB | e276e447b297 |
| checkpoints/v18_training/step_0075.pt | Weights | 167.1 MB | 12d64a58b5af |
| checkpoints/v18_training/step_0100.pt | Weights | 167.1 MB | 80de1142768e |
| checkpoints/v18_training/step_0125.pt | Weights | 167.1 MB | dfb1c42ea8a2 |
| checkpoints/v18_training/step_0150.pt | Weights | 167.1 MB | 978aa5b29d17 |
| checkpoints/v18_training/step_0175.pt | Weights | 167.1 MB | 5c59e4592373 |
| checkpoints/v18_training/step_0200.pt | Weights | 167.1 MB | 07e8707fcae6 |
| checkpoints/v18_training/step_0225.pt | Weights | 167.1 MB | e8b61c1c9eef |
| checkpoints/v18_training/step_0250.pt | Weights | 167.1 MB | d0f059b7639e |
| checkpoints/v18_training/step_0257.pt | Weights | 167.1 MB | aa357336ccef |
| checkpoints/v18_training/v1.8_final.pt | Weights | 167.1 MB | eafabf25e973 |
| forensics/v18_pretraining_state.pt | Weights | 60.0 MB | 6b455fe55e19 |
| model/v18_initialized_from_v17.pt | Weights | 53.6 MB | 11bcbc7c53c7 |
| raw/v1.7_release/model/v1.7_l3_only_model.pt | Weights | 53.6 MB | 359b26135628 |
| token_cache/v18_causal_lm_examples.pt | Weights | 104.1 MB | c72e2f067778 |
| data/evaluation_manifest.json | Configuration | 759 B | — |
| data/instruction_train_augmentation_manifest.json | Configuration | 323 B | — |
| data/splits/split_manifest.json | Configuration | 655 B | — |
| data/token_length_audit.json | Configuration | 6.3 KB | — |
| data/v17_compatibility_train_manifest.json | Configuration | 663 B | — |
| data/v18_canonical_mixture_manifest.json | Configuration | 679 B | — |
| data/v18_initial_mixture_manifest.json | Configuration | 849 B | — |
| forensics/context_overflow_forensic.json | Configuration | 6.9 KB | — |
| forensics/prompt_compression_forensic.json | Configuration | 11.5 KB | — |
| forensics/v17_compatibility_token_audit.json | Configuration | 595 B | — |
| forensics/v17_exact_serializer.json | Configuration | 862 B | — |
| forensics/v18_canonical_mixture_token_audit.json | Configuration | 815 B | — |
| forensics/v18_exact_v17_initialization.json | Configuration | 889 B | — |
| forensics/v18_final_checkpoint_integrity.json | Configuration | 2.0 KB | — |
| forensics/v18_final_dataset_integrity.json | Configuration | 725 B | — |
| forensics/v18_final_token_context_audit.json | Configuration | 843 B | — |
| forensics/v18_frozen_v17_baseline.json | Configuration | 1.9 KB | — |
| forensics/v18_model_config.json | Configuration | 421 B | — |
| forensics/v18_split_collision_forensic.json | Configuration | 3.1 KB | — |
| forensics/v18_training_config.json | Configuration | 1.7 KB | — |
| forensics/v18_training_report.json | Configuration | 910 B | — |
| forensics/v18_training_target_audit.json | Configuration | 645 B | — |
| forensics/v18_v17_behavioral_equivalence.json | Configuration | 1.8 KB | — |
| forensics/v18_v17_model_recovery_manifest.json | Configuration | 553 B | — |
| raw/v1.7_release/data/data/dynamic_259_input_v1.4.json | Configuration | 1.3 MB | — |
| raw/v1.7_release/data/dynamic_259_input_v1.4.json | Configuration | 1.3 MB | — |
| raw/v1.7_release/forensics/forensics/v1.7_training_manifest.json | Configuration | 576 B | — |
| raw/v1.7_release/release_manifest.json | Configuration | 2.2 KB | — |
| token_cache/v18_causal_lm_manifest.json | Configuration | 1.4 KB | — |
| data/instruction_test.jsonl | Other | 1.1 MB | — |
| data/instruction_train_augmented.jsonl | Other | 37.8 MB | b2594ea6d7b6 |
| data/instruction_validation.jsonl | Other | 1.1 MB | — |
| data/splits/implementation_test.jsonl | Other | 2.2 MB | — |
| data/splits/implementation_train.jsonl | Other | 18.5 MB | 068e06a0d22e |
| data/splits/implementation_val.jsonl | Other | 2.2 MB | — |
| data/v17_compatibility_train.jsonl | Other | 8.8 MB | — |
| data/v18_canonical_mixture.jsonl | Other | 45.9 MB | 58530fde0a03 |
| data/v18_initial_mixture_manifest.jsonl | Other | 46.5 MB | 5ecdd107faa9 |
| metadata_v17_manifest.txt | Other | 348 B | — |
| raw/v1.7_release/data/data/semantic_train_v1.4.jsonl | Other | 22.8 MB | f659a8ff2c76 |
| raw/v1.7_release/data/semantic_train_v1.4.jsonl | Other | 22.8 MB | f659a8ff2c76 |
| .gitattributes | Repository | 2.0 KB | — |
| raw/v1.7_release/tokenizer/tokenizer.json | Tokenizer | 204.9 KB | — |
| raw/v1.7_release/tokenizer/tokenizer/tokenizer.json | Tokenizer | 204.9 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 2.3 GB
Download from Quachttohai
Released by Quachttohai through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 2.3 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.