Swahili_Gemma

Mollel/Swahili_Gemma

Swahili_Gemma is a text generation model from Mollel. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.

- Developed by: Mollel - License: apache-2.0 - Finetuned from model : gemma-7b-bnb-4bit

Downloads · 30 days

1% of all-time downloads

All-time downloads

4.3K

Public

Repo size

34.2 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin17.1 GB · 100%

At a glance

Task: Text Generation
Library: transformers
License: apache-2.0
Model type: gemma
Access: Public
Created: Apr 8, 2024
Updated: May 7, 2024
SHA: 249c456f

Try a prompt

Base models

gemma-7b-bnb-4bit

Model card

From the Hugging Face model README

Uploaded model

Developed by: Mollel
License: apache-2.0
Finetuned from model : gemma-7b-bnb-4bit


from llama_index.llms.huggingface import HuggingFaceLLM
llm = HuggingFaceLLM(
 context_window=4096,
 max_new_tokens=256,
 generate_kwargs={"temperature": 0.7, "do_sample": False},  
 tokenizer_name="Mollel/Swahili_Gemma",
 model_name="Mollel/Swahili_Gemma",
 device_map="auto",
 stopping_ids=[50278, 50279, 50277, 1, 0],
 tokenizer_kwargs={"max_length": 4096},
 model_kwargs={"torch_dtype": torch.float16}
)

Examples

Load Lora and use for evaluation kaggle GitRepo
Supervised Finetuning Dataset Creation using Swahili Gemma kaggle GitRepo
Rag using Swahili gemma Kaggle GitRepo

Task: Text Generation
Library: transformers
Type: gemma
License: apache-2.0
Languages: en
Created: Apr 8, 2024
Updated: May 7, 2024