Experimenting with pre-training Arabic language + finetuning on instructions using the quantized model mistralai/Mistral-7B-v0.3 from unsloth. First time trying pre-training, expect issues and low quality outputs. The repo contains the merged, quantized model and a GGUF format.

See spaces demo example.

Example usage

llama-cpp-python

from llama_cpp import Llama

inference_prompt = """فيما يلي تعليمات تصف مهمة. اكتب استجابة تكمل الطلب بشكل مناسب.

### تعليمات:
{}

### إجابة:
"""

llm = Llama.from_pretrained(
    repo_id="nazimali/mistral-7b-v0.3-instruct-arabic",
    filename="Q4_K_M.gguf",
)

llm.create_chat_completion(
    messages = [
        {
            "role": "user",
            "content": inference_prompt.format("السلام عليكم كيف حالك؟")
        }
    ]
)

llama.cpp

./llama-cli \
  --hf-repo "nazimali/mistral-7b-v0.3-instruct-arabic" \
  --hf-file Q4_K_M.gguf \
  -p "السلام عليكم كيف حالك؟" \
  --conversation

Training

Pre-training data:

  • wikimedia/wikipedia
  • 20231101.ar
  • Used 6,096 rows, 0.05% of the total data

Finetuning data:

  • FreedomIntelligence/alpaca-gpt4-arabic
  • Used 49,969 rows, 100% of all the data

Finetuning instruction format:

finetune_prompt = """فيما يلي تعليمات تصف مهمة. اكتب استجابة تكمل الطلب بشكل مناسب.

### تعليمات:
{}

### إجابة:
"""
Downloads last month
138
Safetensors
Model size
3.87B params
Tensor type
FP16
·
F32
·
U8
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for nazimali/mistral-7b-v0.3-instruct-arabic

Quantized
(49)
this model
Finetunes
1 model

Datasets used to train nazimali/mistral-7b-v0.3-instruct-arabic

Space using nazimali/mistral-7b-v0.3-instruct-arabic 1