RichardErkhov/ReBatch_-_Llama-3-8B-dutch-gguf
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
main
ReBatch_-_Llama-3-8B-dutch-…/README.md
ModelHub XC 9a52d1b74b 初始化项目，由ModelHub XC社区提供模型 
Model: RichardErkhov/ReBatch_-_Llama-3-8B-dutch-gguf
Source: Original Platform
2026-08-28 00:21:17 +08:00

115 lines
6.8 KiB
Markdown
Raw Permalink Blame History

Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
Llama-3-8B-dutch - GGUF
- Model creator: https://huggingface.co/ReBatch/
- Original model: https://huggingface.co/ReBatch/Llama-3-8B-dutch/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [Llama-3-8B-dutch.Q2_K.gguf](https://huggingface.co/RichardErkhov/ReBatch_-_Llama-3-8B-dutch-gguf/blob/main/Llama-3-8B-dutch.Q2_K.gguf) | Q2_K | 2.96GB |
| [Llama-3-8B-dutch.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/ReBatch_-_Llama-3-8B-dutch-gguf/blob/main/Llama-3-8B-dutch.IQ3_XS.gguf) | IQ3_XS | 3.28GB |
| [Llama-3-8B-dutch.IQ3_S.gguf](https://huggingface.co/RichardErkhov/ReBatch_-_Llama-3-8B-dutch-gguf/blob/main/Llama-3-8B-dutch.IQ3_S.gguf) | IQ3_S | 3.43GB |
| [Llama-3-8B-dutch.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/ReBatch_-_Llama-3-8B-dutch-gguf/blob/main/Llama-3-8B-dutch.Q3_K_S.gguf) | Q3_K_S | 3.41GB |
| [Llama-3-8B-dutch.IQ3_M.gguf](https://huggingface.co/RichardErkhov/ReBatch_-_Llama-3-8B-dutch-gguf/blob/main/Llama-3-8B-dutch.IQ3_M.gguf) | IQ3_M | 3.52GB |
| [Llama-3-8B-dutch.Q3_K.gguf](https://huggingface.co/RichardErkhov/ReBatch_-_Llama-3-8B-dutch-gguf/blob/main/Llama-3-8B-dutch.Q3_K.gguf) | Q3_K | 3.74GB |
| [Llama-3-8B-dutch.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/ReBatch_-_Llama-3-8B-dutch-gguf/blob/main/Llama-3-8B-dutch.Q3_K_M.gguf) | Q3_K_M | 3.74GB |
| [Llama-3-8B-dutch.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/ReBatch_-_Llama-3-8B-dutch-gguf/blob/main/Llama-3-8B-dutch.Q3_K_L.gguf) | Q3_K_L | 4.03GB |
| [Llama-3-8B-dutch.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/ReBatch_-_Llama-3-8B-dutch-gguf/blob/main/Llama-3-8B-dutch.IQ4_XS.gguf) | IQ4_XS | 4.18GB |
| [Llama-3-8B-dutch.Q4_0.gguf](https://huggingface.co/RichardErkhov/ReBatch_-_Llama-3-8B-dutch-gguf/blob/main/Llama-3-8B-dutch.Q4_0.gguf) | Q4_0 | 4.34GB |
| [Llama-3-8B-dutch.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/ReBatch_-_Llama-3-8B-dutch-gguf/blob/main/Llama-3-8B-dutch.IQ4_NL.gguf) | IQ4_NL | 4.38GB |
| [Llama-3-8B-dutch.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/ReBatch_-_Llama-3-8B-dutch-gguf/blob/main/Llama-3-8B-dutch.Q4_K_S.gguf) | Q4_K_S | 4.37GB |
| [Llama-3-8B-dutch.Q4_K.gguf](https://huggingface.co/RichardErkhov/ReBatch_-_Llama-3-8B-dutch-gguf/blob/main/Llama-3-8B-dutch.Q4_K.gguf) | Q4_K | 4.58GB |
| [Llama-3-8B-dutch.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/ReBatch_-_Llama-3-8B-dutch-gguf/blob/main/Llama-3-8B-dutch.Q4_K_M.gguf) | Q4_K_M | 4.58GB |
| [Llama-3-8B-dutch.Q4_1.gguf](https://huggingface.co/RichardErkhov/ReBatch_-_Llama-3-8B-dutch-gguf/blob/main/Llama-3-8B-dutch.Q4_1.gguf) | Q4_1 | 4.78GB |
| [Llama-3-8B-dutch.Q5_0.gguf](https://huggingface.co/RichardErkhov/ReBatch_-_Llama-3-8B-dutch-gguf/blob/main/Llama-3-8B-dutch.Q5_0.gguf) | Q5_0 | 5.21GB |
| [Llama-3-8B-dutch.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/ReBatch_-_Llama-3-8B-dutch-gguf/blob/main/Llama-3-8B-dutch.Q5_K_S.gguf) | Q5_K_S | 5.21GB |
| [Llama-3-8B-dutch.Q5_K.gguf](https://huggingface.co/RichardErkhov/ReBatch_-_Llama-3-8B-dutch-gguf/blob/main/Llama-3-8B-dutch.Q5_K.gguf) | Q5_K | 5.34GB |
| [Llama-3-8B-dutch.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/ReBatch_-_Llama-3-8B-dutch-gguf/blob/main/Llama-3-8B-dutch.Q5_K_M.gguf) | Q5_K_M | 5.34GB |
| [Llama-3-8B-dutch.Q5_1.gguf](https://huggingface.co/RichardErkhov/ReBatch_-_Llama-3-8B-dutch-gguf/blob/main/Llama-3-8B-dutch.Q5_1.gguf) | Q5_1 | 5.65GB |
| [Llama-3-8B-dutch.Q6_K.gguf](https://huggingface.co/RichardErkhov/ReBatch_-_Llama-3-8B-dutch-gguf/blob/main/Llama-3-8B-dutch.Q6_K.gguf) | Q6_K | 6.14GB |
| [Llama-3-8B-dutch.Q8_0.gguf](https://huggingface.co/RichardErkhov/ReBatch_-_Llama-3-8B-dutch-gguf/blob/main/Llama-3-8B-dutch.Q8_0.gguf) | Q8_0 | 7.95GB |
Original model description:
---
license: llama3
base_model: meta-llama/Meta-Llama-3-8B
tags:
- ORPO
- llama 3 8B
- conversational
datasets:
- BramVanroy/ultra_feedback_dutch
model-index:
- name: ReBatch/Llama-3-8B-dutch
results: []
language:
- nl
pipeline_tag: text-generation
---
<p align="center" style="margin:0;padding:0">
<img src="llama3-8b-dutch-banner.jpeg" alt="Llama 3 dutch banner" width="400" height="400"/>
</p>
<div style="margin:auto; text-align:center">
<h1 style="margin-bottom: 0">Llama 3 8B - Dutch</h1>
<em>A conversational model for Dutch, based on Llama 3 8B</em>
<p><em><a href="https://huggingface.co/spaces/ReBatch/Llama-3-Dutch">Try chatting with the model!</a></em></p>
</div>
This model is a [QLORA](https://huggingface.co/blog/4bit-transformers-bitsandbytes) and [ORPO](https://huggingface.co/docs/trl/main/en/orpo_trainer) fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the synthetic feedback dataset [BramVanroy/ultra_feedback_dutch](https://huggingface.co/datasets/BramVanroy/ultra_feedback_dutch)
## Model description
This model is a Dutch chat model, originally developed from Llama 3 8B and further refined through a feedback dataset with [ORPO](https://huggingface.co/docs/trl/main/en/orpo_trainer) and trained on [BramVanroy/ultra_feedback_dutch](https://huggingface.co/datasets/BramVanroy/ultra_feedback_dutch)
## Intended uses & limitations
Although the model has been aligned with gpt-4-turbo output, which has strong content filters, the model could still generate wrong, misleading, and potentially even offensive content. Use at your own risk.
## Training procedure
The model was trained in bfloat16 with QLORA with flash attention 2 on one GPU - H100 80GB SXM5 for around 24 hours on RunPod.
## Evaluation Results
The model was evaluated using [scandeval](https://scandeval.com/dutch-nlg/)
The model showed mixed results across different benchmarks; it exhibited slight improvements on some while experiencing a decrease in scores on others. This occurred despite being trained on only 200,000 samples for a single epoch. We are curious to see whether its performance could be enhanced by training with more data or additional epochs.
| Model| conll_nl | dutch_social | scala_nl | squad_nl | wiki_lingua_nl | mmlu_nl | hellaswag_nl |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:
meta-llama/Meta-Llama-3-8B-Instruct | 68.72 | 14.67 | 32.91 | 45.36 | 67.62 | 36.18 | 33.91
ReBatch/Llama-3-8B-dutch | 58.85 | 11.14 | 15.58 | 59.96 | 64.51 | 36.27 | 28.34
meta-llama/Meta-Llama-3-8B | 62.26 | 10.45| 30.3| 62.99| 65.17 | 36.38| 28.33
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 8e-06
- train_batch_size: 2
- eval_batch_size: 2
- num_devices: 1
- gradient_accumulation_steps: 4
- optimizer: paged_adamw_8bit
- lr_scheduler_type: linear
- warmup_steps: 10
- num_epochs: 1.0
- r: 16
- lora_alpha: 32
- lora_dropout: 0.05
Reference in New Issue View Git Blame Copy Permalink