bineric
/

NorskGPT-Llama-7B-v0.1

@@ -1,112 +1,50 @@
 ---
 base_model: meta-llama/Llama-2-7b-chat-hf
 tags:
-- generated_from_trainer
-model-index:
-- name: llama-le-out
-  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. -->
-[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
-# llama-le-out
-This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.6239
-## Model description
-More information needed
-## Intended uses & limitations
-More information needed
-## Training and evaluation data
-More information needed
-## Training procedure
-### Training hyperparameters
-The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 4
-- eval_batch_size: 4
-- seed: 42
-- distributed_type: multi-GPU
-- num_devices: 4
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 32
-- total_eval_batch_size: 16
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 10
-- num_epochs: 3
-### Training results
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.9364        | 0.06  | 100  | 0.8000          |
-| 0.809         | 0.12  | 200  | 0.7724          |
-| 0.8695        | 0.18  | 300  | 0.7571          |
-| 0.7512        | 0.24  | 400  | 0.7406          |
-| 0.8266        | 0.3   | 500  | 0.7327          |
-| 0.7898        | 0.35  | 600  | 0.7238          |
-| 0.9163        | 0.41  | 700  | 0.7135          |
-| 0.6955        | 0.47  | 800  | 0.7025          |
-| 0.7887        | 0.53  | 900  | 0.7009          |
-| 0.7361        | 0.59  | 1000 | 0.6911          |
-| 0.7736        | 0.65  | 1100 | 0.6897          |
-| 0.7135        | 0.71  | 1200 | 0.6859          |
-| 0.8138        | 0.77  | 1300 | 0.6788          |
-| 0.7172        | 0.83  | 1400 | 0.6720          |
-| 0.7387        | 0.89  | 1500 | 0.6695          |
-| 0.7042        | 0.95  | 1600 | 0.6688          |
-| 0.7231        | 1.0   | 1700 | 0.6652          |
-| 0.7136        | 1.06  | 1800 | 0.6626          |
-| 0.694         | 1.12  | 1900 | 0.6583          |
-| 0.7401        | 1.18  | 2000 | 0.6551          |
-| 0.63          | 1.24  | 2100 | 0.6519          |
-| 0.6506        | 1.3   | 2200 | 0.6478          |
-| 0.7436        | 1.36  | 2300 | 0.6457          |
-| 0.5903        | 1.42  | 2400 | 0.6452          |
-| 0.6861        | 1.48  | 2500 | 0.6399          |
-| 0.6576        | 1.54  | 2600 | 0.6412          |
-| 0.6327        | 1.59  | 2700 | 0.6357          |
-| 0.6634        | 1.65  | 2800 | 0.6378          |
-| 0.6419        | 1.71  | 2900 | 0.6349          |
-| 0.6573        | 1.77  | 3000 | 0.6344          |
-| 0.7052        | 1.83  | 3100 | 0.6327          |
-| 0.6438        | 1.89  | 3200 | 0.6292          |
-| 0.713         | 1.95  | 3300 | 0.6283          |
-| 0.6357        | 2.01  | 3400 | 0.6293          |
-| 0.5736        | 2.07  | 3500 | 0.6302          |
-| 0.591         | 2.13  | 3600 | 0.6307          |
-| 0.6995        | 2.19  | 3700 | 0.6295          |
-| 0.6708        | 2.24  | 3800 | 0.6277          |
-| 0.6329        | 2.3   | 3900 | 0.6262          |
-| 0.6138        | 2.36  | 4000 | 0.6271          |
-| 0.6316        | 2.42  | 4100 | 0.6266          |
-| 0.6022        | 2.48  | 4200 | 0.6260          |
-| 0.7221        | 2.54  | 4300 | 0.6252          |
-| 0.6943        | 2.6   | 4400 | 0.6256          |
-| 0.6616        | 2.66  | 4500 | 0.6246          |
-| 0.6185        | 2.72  | 4600 | 0.6247          |
-| 0.6417        | 2.78  | 4700 | 0.6239          |
-| 0.6238        | 2.84  | 4800 | 0.6237          |
-| 0.6024        | 2.89  | 4900 | 0.6236          |
-| 0.6059        | 2.95  | 5000 | 0.6239          |
-### Framework versions
-- Transformers 4.34.1
-- Pytorch 2.0.1+cu118
-- Datasets 2.14.6
-- Tokenizers 0.14.1

 ---
 base_model: meta-llama/Llama-2-7b-chat-hf
 tags:
+  - mistral
+  - instruct
+  - finetune
+language:
+  - no
+license: cc-by-nc-sa-4.0
+---
+# NorskGPT-Mistral-7b
+This model is a Norwegian variant of Llama-2-7b-chat-hf, fine-tuned on a carefully selected mix of Norwegian instruction pairs. The model is tuned to understand and generate text in Norwegain.
+## Intended Use
+This model is intended for personal and research use in Norwegian and can be used as an assistant-like chat.
+## Prompt Template
+```
+### Instruction:
+Summarize following text.
+### Input:
+Text to be summarized
+### Response:
+```
+## Limitations
+*   This is an LLM, not a knowledge model. It can not be expected to have more information about Norway than the base model.
+*   It will generally preform better on tasks that involves summarization, question answering and chat, than on tasks that requires more knowledge about Norway, specific domains, or tasks where the model can answer freely.
+*   The model is released as is, and would in most cases need prompt tuning to achieve optimal results.
+## License
+[Attribution-NonCommercial-ShareAlike 4.0 International](https://creativecommons.org/licenses/by-nc-sa/4.0/)
+ You are free to:
+    Share — copy and redistribute the material in any medium or format
+    Adapt — remix, transform, and build upon the material
+    The licensor cannot revoke these freedoms as long as you follow the license terms.
+Under the following terms:
+    Attribution — You must give appropriate credit , provide a link to the license, and indicate if changes were made . You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
+    NonCommercial — You may not use the material for commercial purposes .
+    ShareAlike — If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.
+    No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.