Downloads · 30 days
38
2% of all-time downloads
RichardErkhov/hiig-piai_-_simba_best_092024-gguf
hiig-piai_-_simba_best_092024-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.
Downloads · 30 days
38
2% of all-time downloads
All-time downloads
1.7K
Public
Repo size
92.9 GB
Likes
0
Public
Click a slice to open those files.
.gguf108 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
simba_best_092024 - GGUF
| Name | Quant method | Size |
|---|---|---|
| simba_best_092024.Q2_K.gguf | Q2_K | 2.96GB |
| simba_best_092024.IQ3_XS.gguf | IQ3_XS | 3.28GB |
| simba_best_092024.IQ3_S.gguf | IQ3_S | 3.43GB |
| simba_best_092024.Q3_K_S.gguf | Q3_K_S | 3.41GB |
| simba_best_092024.IQ3_M.gguf | IQ3_M | 3.52GB |
| simba_best_092024.Q3_K.gguf | Q3_K | 3.74GB |
| simba_best_092024.Q3_K_M.gguf | Q3_K_M | 3.74GB |
| simba_best_092024.Q3_K_L.gguf | Q3_K_L | 4.03GB |
| simba_best_092024.IQ4_XS.gguf | IQ4_XS | 4.18GB |
| simba_best_092024.Q4_0.gguf | Q4_0 | 4.34GB |
| simba_best_092024.IQ4_NL.gguf | IQ4_NL | 4.38GB |
| simba_best_092024.Q4_K_S.gguf | Q4_K_S | 4.37GB |
| simba_best_092024.Q4_K.gguf | Q4_K | 4.58GB |
| simba_best_092024.Q4_K_M.gguf | Q4_K_M | 4.58GB |
| simba_best_092024.Q4_1.gguf | Q4_1 | 4.78GB |
| simba_best_092024.Q5_0.gguf | Q5_0 | 5.21GB |
| simba_best_092024.Q5_K_S.gguf | Q5_K_S | 5.21GB |
| simba_best_092024.Q5_K.gguf | Q5_K | 5.34GB |
| simba_best_092024.Q5_K_M.gguf | Q5_K_M | 5.34GB |
| simba_best_092024.Q5_1.gguf | Q5_1 | 5.65GB |
| simba_best_092024.Q6_K.gguf | Q6_K | 6.14GB |
| simba_best_092024.Q8_0.gguf | Q8_0 | 7.95GB |
license: apache-2.0 language:
We fine-tuned meta-llama/Meta-Llama-3-8B-Instruct with a set of ca. 800 newspaper articles which have been simplified by the Austrian Press Agency. Our aim was to have a model which can simplify German-language text.
This model works best for simplifying German-language newspaper articles (news items, not commentaries or editorials). It may work for other types of texts.
We have fine-tuned using only newspaper articles. We have not yet performed extensive out-of-domain testing, but believe that the model's capabilities could be improved by fine-tuning on more diverse data. Contact us if you have a dataset which you think could work (parallel texts, German standard & German simplified).
<!-- ### Out-of-Scope Use --> <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->As with most text generation models, the model sometimes produces information that is incorrect.
Please check manually that your output text corresponds to the input text, as factual inconsistencies may have arisen.
We offer two tools to interact with our model: an online app and a browser extension. They can be viewed and used here.
Alternatively, to load the model using transformers:
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
device = "cuda"
tokenizer = AutoTokenizer.from_pretrained("hiig-piai/simba_best_092024")
model = AutoModelForCausalLM.from_pretrained("hiig-piai/simba_best_092024", torch_dtype=torch.float16).to(device)
We used the following prompt at inference to test our model:
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
Du bist ein hilfreicher Assistent und hilfst dem User, Texte besser zu verstehen.<|eot_id|><|start_header_id|>user<|end_header_id|>
Kannst du bitte den folgenden Text zusammenfassen und sprachlich auf ein A2-Niveau in Deutsch vereinfachen? Schreibe maximal 5 Sätze.
{input_text}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
A sample of the data used to train our model can be found here.
simba -at- hiig.de