Quantization made by Richard Erkhov.

Mistral-7B-Instruct-v0.2-turkish - GGUF

Model creator: https://huggingface.co/malhajar/
Original model: https://huggingface.co/malhajar/Mistral-7B-Instruct-v0.2-turkish/

Name	Quant method	Size
Mistral-7B-Instruct-v0.2-turkish.Q2_K.gguf	Q2_K	2.53GB
Mistral-7B-Instruct-v0.2-turkish.IQ3_XS.gguf	IQ3_XS	2.81GB
Mistral-7B-Instruct-v0.2-turkish.IQ3_S.gguf	IQ3_S	2.96GB
Mistral-7B-Instruct-v0.2-turkish.Q3_K_S.gguf	Q3_K_S	2.95GB
Mistral-7B-Instruct-v0.2-turkish.IQ3_M.gguf	IQ3_M	3.06GB
Mistral-7B-Instruct-v0.2-turkish.Q3_K.gguf	Q3_K	3.28GB
Mistral-7B-Instruct-v0.2-turkish.Q3_K_M.gguf	Q3_K_M	3.28GB
Mistral-7B-Instruct-v0.2-turkish.Q3_K_L.gguf	Q3_K_L	3.56GB
Mistral-7B-Instruct-v0.2-turkish.IQ4_XS.gguf	IQ4_XS	3.67GB
Mistral-7B-Instruct-v0.2-turkish.Q4_0.gguf	Q4_0	3.83GB
Mistral-7B-Instruct-v0.2-turkish.IQ4_NL.gguf	IQ4_NL	3.87GB
Mistral-7B-Instruct-v0.2-turkish.Q4_K_S.gguf	Q4_K_S	3.86GB
Mistral-7B-Instruct-v0.2-turkish.Q4_K.gguf	Q4_K	4.07GB
Mistral-7B-Instruct-v0.2-turkish.Q4_K_M.gguf	Q4_K_M	4.07GB
Mistral-7B-Instruct-v0.2-turkish.Q4_1.gguf	Q4_1	4.24GB
Mistral-7B-Instruct-v0.2-turkish.Q5_0.gguf	Q5_0	4.65GB
Mistral-7B-Instruct-v0.2-turkish.Q5_K_S.gguf	Q5_K_S	4.65GB
Mistral-7B-Instruct-v0.2-turkish.Q5_K.gguf	Q5_K	4.78GB
Mistral-7B-Instruct-v0.2-turkish.Q5_K_M.gguf	Q5_K_M	4.78GB
Mistral-7B-Instruct-v0.2-turkish.Q5_1.gguf	Q5_1	5.07GB
Mistral-7B-Instruct-v0.2-turkish.Q6_K.gguf	Q6_K	5.53GB
Mistral-7B-Instruct-v0.2-turkish.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0 datasets: - malhajar/alpaca-gpt4-tr language: - tr - en

Model Card for Model ID

malhajar/Mistral-7B-Instruct-v0.2-turkish is a finetuned version of Mistral-7B-Instruct-v0.2 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-tr

Model Description

Developed by: Mohamad Alhajar
Language(s) (NLP): Turkish
Finetuned from model: mistralai/Mistral-7B-Instruct-v0.2

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-Instruct-v0.2-turkish"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
                                             device_map="auto",
                                             torch_dtype=torch.float16,
                                             revision="main")

tokenizer = AutoTokenizer.from_pretrained(model_id)

question: "Türkiyenin en büyük şehir nedir?"
# 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)