Instructions to use malhajar/Mistral-7B-Instruct-v0.2-turkish with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use malhajar/Mistral-7B-Instruct-v0.2-turkish with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="malhajar/Mistral-7B-Instruct-v0.2-turkish")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("malhajar/Mistral-7B-Instruct-v0.2-turkish")
model = AutoModelForCausalLM.from_pretrained("malhajar/Mistral-7B-Instruct-v0.2-turkish")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use malhajar/Mistral-7B-Instruct-v0.2-turkish with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "malhajar/Mistral-7B-Instruct-v0.2-turkish"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "malhajar/Mistral-7B-Instruct-v0.2-turkish",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/malhajar/Mistral-7B-Instruct-v0.2-turkish

SGLang

How to use malhajar/Mistral-7B-Instruct-v0.2-turkish with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "malhajar/Mistral-7B-Instruct-v0.2-turkish" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "malhajar/Mistral-7B-Instruct-v0.2-turkish",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "malhajar/Mistral-7B-Instruct-v0.2-turkish" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "malhajar/Mistral-7B-Instruct-v0.2-turkish",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use malhajar/Mistral-7B-Instruct-v0.2-turkish with Docker Model Runner:
```
docker model run hf.co/malhajar/Mistral-7B-Instruct-v0.2-turkish
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

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)

Downloads last month: 20

Safetensors

Model size

7B params

Tensor type

F16

Model tree for malhajar/Mistral-7B-Instruct-v0.2-turkish

Adapters

1 model

Quantizations

3 models

malhajar
/

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

Model Card for Model ID

Model Description

Prompt Template

How to Get Started with the Model

Model tree for malhajar/Mistral-7B-Instruct-v0.2-turkish

Dataset used to train malhajar/Mistral-7B-Instruct-v0.2-turkish