malhajar_-_Mistral-7B-v0.1-arabic-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Mistral-7B-v0.1-arabic - GGUF

• Model creator: https://huggingface.co/malhajar/
• Original model: https://huggingface.co/malhajar/Mistral-7B-v0.1-arabic/

Original model description:

license: apache-2.0 datasets:

• malhajar/alpaca-gpt4-ar language:
• ar
• en

---

Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

malhajar/Mistral-7B-Instruct-v0.2-turkish is a finetuned version of Mistral-7B-v0.1 using SFT Training and Freeze method. This model can answer information in a chat format as it is finetuned specifically on instructions specifically alpaca-gpt4-ar

Model Description

• Developed by: Mohamad Alhajar
• Language(s) (NLP): Arabic
• Finetuned from model: mistralai/Mistral-7B-v0.1

Prompt Template

### Instruction:

<prompt> (without the <>)

### Response:

How to Get Started with the Model

Use the code sample provided in the original post to interact with the model.

from transformers import AutoTokenizer,AutoModelForCausalLM
 
model_id = "malhajar/Mistral-7B-v0.1-arabic"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
                                             device_map="auto",
                                             torch_dtype=torch.float16,
                                             revision="main")

tokenizer = AutoTokenizer.from_pretrained(model_id)

question: "ما هي الحياة؟"
# For generating a response
prompt = '''
### Instruction:  {question} ### Response:
'''
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
output = model.generate(inputs=input_ids,max_new_tokens=512,pad_token_id=tokenizer.eos_token_id,top_k=50, do_sample=True,repetition_penalty=1.3
        top_p=0.95,trust_remote_code=True,)
response = tokenizer.decode(output[0])

print(response)