Downloads · 30 days
61
5% of all-time downloads
ReBatch_-_Reynaerde-7B-Instruct-gguf
RichardErkhov/ReBatch_-_Reynaerde-7B-Instruct-gguf
ReBatch_-_Reynaerde-7B-Instruct-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
1.2K
Public
Repo size
79.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf92.3 GB · 100%
At a glance
- Access
- Public
- Created
- Oct 10, 2024
- Updated
- Oct 10, 2024
- SHA
- c9e9d609
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Reynaerde-7B-Instruct - GGUF
- Model creator: https://huggingface.co/ReBatch/
- Original model: https://huggingface.co/ReBatch/Reynaerde-7B-Instruct/
| Name | Quant method | Size |
|---|---|---|
| Reynaerde-7B-Instruct.Q2_K.gguf | Q2_K | 2.54GB |
| Reynaerde-7B-Instruct.IQ3_XS.gguf | IQ3_XS | 2.82GB |
| Reynaerde-7B-Instruct.IQ3_S.gguf | IQ3_S | 0.17GB |
| Reynaerde-7B-Instruct.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| Reynaerde-7B-Instruct.IQ3_M.gguf | IQ3_M | 3.06GB |
| Reynaerde-7B-Instruct.Q3_K.gguf | Q3_K | 3.28GB |
| Reynaerde-7B-Instruct.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| Reynaerde-7B-Instruct.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| Reynaerde-7B-Instruct.IQ4_XS.gguf | IQ4_XS | 3.68GB |
| Reynaerde-7B-Instruct.Q4_0.gguf | Q4_0 | 3.83GB |
| Reynaerde-7B-Instruct.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| Reynaerde-7B-Instruct.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| Reynaerde-7B-Instruct.Q4_K.gguf | Q4_K | 4.07GB |
| Reynaerde-7B-Instruct.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| Reynaerde-7B-Instruct.Q4_1.gguf | Q4_1 | 4.24GB |
| Reynaerde-7B-Instruct.Q5_0.gguf | Q5_0 | 4.66GB |
| Reynaerde-7B-Instruct.Q5_K_S.gguf | Q5_K_S | 4.66GB |
| Reynaerde-7B-Instruct.Q5_K.gguf | Q5_K | 4.78GB |
| Reynaerde-7B-Instruct.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| Reynaerde-7B-Instruct.Q5_1.gguf | Q5_1 | 5.07GB |
| Reynaerde-7B-Instruct.Q6_K.gguf | Q6_K | 5.54GB |
| Reynaerde-7B-Instruct.Q8_0.gguf | Q8_0 | 7.17GB |
Original model description:
license: apache-2.0 base_model: mistralai/Mistral-7B-v0.3 tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
- trl
- sft
- generated_from_trainer datasets:
- ReBatch/ultrachat_400k_nl
- BramVanroy/stackoverflow-chat-dutch
- vandeju/no_robots_dutch model-index:
- name: Reynaerde-7B-Instruct results: []
<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
Reynaerde-7B-v3
This model is a fine-tuned version of mistralai/Mistral-7B-v0.3-Instruct on the ReBatch/ultrachat_400k_nl, the BramVanroy/stackoverflow-chat-dutch and the BramVanroy/no_robots_dutch datasets.
Model description
This model is a Dutch chat model, originally developed from Mistral 7B v0.3 Instruct and further finetuned first with SFT on multiple datasets.
Intended uses & limitations
The model could generate wrong, misleading, and potentially even offensive content. Use at your own risk. Use with mistrals chat template.
Training and evaluation data
It achieves the following results on the evaluation set:
- Loss: 0.8596
Training procedure
This model was trained with QLoRa in bfloat16 with Flash Attention 2 on one A100 PCIe, using the sft script from the alignment handbook on RunPod.
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 3
- eval_batch_size: 6
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 2
- total_train_batch_size: 6
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.2.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
Model Developer
The Mistral-7B-v0.3-Instruct model, on which this model is based, was created by Mistral AI. The finetuning was done by Julien Van den Avenne.
- Created
- Oct 10, 2024
- Updated
- Oct 10, 2024