This checkpoint should be loaded into BartForConditionalGeneration.frompretrained. See the BART docs for more information.
Open-weight model · Summarization
Qwen3-0.6B-TLDR-Lora
by Pierre-Hugues Husson phh/Qwen3-0.6B-TLDR-Lora
Source code available at https://github.com/phhusson/llm-rl/blob/main/grpo-tldr.py
Parameters—
Context—
Weights18.5 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads2k
Model Card
By Pierre-Hugues Husson, published under apache-2.0, revision 0f3953420282.
Source code available at https://github.com/phhusson/llm-rl/blob/main/grpo-tldr.py
Read Pierre-Hugues Husson's full model card
Source code available at https://github.com/phhusson/llm-rl/blob/main/grpo-tldr.py
Identity and Version
- Repository
- phh/Qwen3-0.6B-TLDR-Lora
- Publisher
- Pierre-Hugues Husson
- Task
- Summarization
- Modality
- Text
- Library
- peft
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 0f39534202828516c2645f1aeb8c5e9e9a0f6801
- First published
- 2025-05-01
- Last updated
- 2025-05-01
Files and Weights
16 files, 34.4 MB in total. The weights are 6 files totalling 18.5 MB in bin, gguf, pt, pth, safetensors.
Weights6 files · 18.5 MB
Configuration4 files · 40.7 KB
Tokenizer4 files · 15.9 MB
Documentation1 file · 213 B
Repository1 file · 1.6 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| Qwen3-0.6B-tldr-lora-f16.gguf | Weights | 4.6 MB | bf991b0f9fc5 |
| adapter_model.safetensors | Weights | 4.6 MB | 05246882d23a |
| optimizer.pt | Weights | 9.3 MB | e60f193253c0 |
| rng_state.pth | Weights | 14.2 KB | 0596da8c3c9a |
| scheduler.pt | Weights | 1.1 KB | f657ace31ad1 |
| training_args.bin | Weights | 5.8 KB | 634da9b317c6 |
| adapter_config.json | Configuration | 769 B | — |
| added_tokens.json | Configuration | 707 B | — |
| special_tokens_map.json | Configuration | 613 B | — |
| trainer_state.json | Configuration | 38.6 KB | — |
| README.md | Documentation | 213 B | — |
| .gitattributes | Repository | 1.6 KB | — |
| merges.txt | Tokenizer | 1.7 MB | — |
| tokenizer.json | Tokenizer | 11.4 MB | 67cc0080ffd7 |
| tokenizer_config.json | Tokenizer | 9.7 KB | — |
| vocab.json | Tokenizer | 2.8 MB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 18.5 MB
Download from Pierre-Hugues Husson
Released by Pierre-Hugues Husson through its official repository on Hugging Face. Read the license.
Built From
- Adapter of Qwen/Qwen3-0.6B
- Derived from Qwen/Qwen3-0.6B
- Trained on (disclosed) trl-lib/tldr
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 18.5 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Qwen3-0.6B-TLDR-Lora
Can I use Qwen3-0.6B-TLDR-Lora commercially?
Yes. Qwen3-0.6B-TLDR-Lora is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Similar Models
Original TF 1 code here Authors: Jingqing Zhang, Yao Zhao, Mohammad Saleh and Peter J. Liu on Dec 18, 2019 The following is copied from the authors' README. We train a pegasus model with sampled gap sentence ratios on both C4 and HugeNews, and stochastically sample important sentences. The updated the results are reported in this table. The "Mixed & Stochastic" model has the following changes: - trained on both C4 and HugeNews (dataset mixture is weighted by their number of examples). - trained for 1.5M instead of 500k (we observe slower convergence on pretraining perplexity). - the model uniformly sample a gap sentence ratio between 15% and 45%. - importance sentences are sampled using a…
This model was trained using Amazon SageMaker and the new Hugging Face Deep Learning container.
This checkpoint should be loaded into BartForConditionalGeneration.frompretrained. See the BART docs for more information.
This repository contains the mT5 checkpoint finetuned on the 45 languages of XL-Sum dataset. For finetuning details and scripts, see the paper and the official repository. Scores on the XL-Sum test sets are as follows: Language | ROUGE-1 / ROUGE-2 / ROUGE-L Amharic | 20.0485 / 7.4111 / 18.0753 Arabic | 34.9107 / 14.7937 / 29.1623 Azerbaijani | 21.4227 / 9.5214 / 19.3331 Bengali | 29.5653 / 12.1095 / 25.1315 Burmese | 15.9626 / 5.1477 / 14.1819 Chinese (Simplified) | 39.4071 / 17.7913 / 33.406 Chinese (Traditional) | 37.1866 / 17.1432 / 31.6184 English | 37.601 / 15.1536 / 29.8817 French | 35.3398 / 16.1739 / 28.2041 Gujarati | 21.9619 / 7.7417 / 19.86 Hausa | 39.4375 / 17.6786 / 31.6667…