Instructions to use Rudblest/projedanismanai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Rudblest/projedanismanai with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Rudblest/projedanismanai",
	filename="mistral-nemo-instruct-2407.Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Rudblest/projedanismanai with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Rudblest/projedanismanai:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Rudblest/projedanismanai:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Rudblest/projedanismanai:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Rudblest/projedanismanai:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Rudblest/projedanismanai:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Rudblest/projedanismanai:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Rudblest/projedanismanai:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Rudblest/projedanismanai:Q4_K_M

Use Docker

docker model run hf.co/Rudblest/projedanismanai:Q4_K_M

LM Studio
Jan

vLLM

How to use Rudblest/projedanismanai with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Rudblest/projedanismanai:Q4_K_M

Ollama
How to use Rudblest/projedanismanai with Ollama:
```
ollama run hf.co/Rudblest/projedanismanai:Q4_K_M
```

Unsloth Studio new

How to use Rudblest/projedanismanai with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Rudblest/projedanismanai to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Rudblest/projedanismanai to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Rudblest/projedanismanai to start chatting

Pi new

How to use Rudblest/projedanismanai with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Rudblest/projedanismanai:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Rudblest/projedanismanai:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Rudblest/projedanismanai with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Rudblest/projedanismanai:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Rudblest/projedanismanai:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Rudblest/projedanismanai with Docker Model Runner:
```
docker model run hf.co/Rudblest/projedanismanai:Q4_K_M
```

Lemonade

How to use Rudblest/projedanismanai with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Rudblest/projedanismanai:Q4_K_M

Run and chat with the model

lemonade run user.projedanismanai-Q4_K_M

List all available models

lemonade list

ProjeDanışmanAi

TEKNOFEST ve TÜBİTAK yarışmacıları için Türkçe yapay zeka danışmanı.

Mistral-Nemo-Instruct-2407 (12B) modeli, TEKNOFEST ve TÜBİTAK yarışma süreçlerine özel Türkçe veri setiyle fine-tune edilmiştir.

Model Detayları

Özellik	Değer
Temel Model	mistralai/Mistral-Nemo-Instruct-2407
Yöntem	QLoRA 4-bit + unsloth
LoRA Rank	64 (alpha=128, rsLoRA=True)
Eğitim Verisi	3043 Türkçe instruction-output çifti
Epoch	5
Max Seq Length	3072
Train Loss	0.3591

Kullanım Alanları

TEKNOFEST KTR/PTR teknik rapor yazımı
TÜBİTAK başvuru hazırlığı
Proje fikri netleştirme
Risk analizi ve uygulanabilirlik değerlendirmesi
Başlık ve özet üretimi
Jüri ve sunum hazırlığı

Veri Seti

3043 Türkçe örnekten oluşan özel veri seti:

Kategori	Örnek Sayısı
rapor_yazimi	761
sifirdan_proje	730
genel_ozet	593
strateji	505
hata_duzeltme	324
red (alan dışı red)	130

Kullanım

GGUF (Ollama ile)

ollama create projedanismanai -f Modelfile
ollama run projedanismanai

Python (unsloth ile)

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name     = "Rudblest/projedanismanai",
    max_seq_length = 3072,
    dtype          = None,
    load_in_4bit   = True,
)
FastLanguageModel.for_inference(model)

prompt = "<s>[INST] TEKNOFEST KTR raporunda risk analizi nasıl yazılır? [/INST] "
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
output = model.generate(**inputs, max_new_tokens=512, temperature=0.7)
print(tokenizer.decode(output[0], skip_special_tokens=True))

Sınırlamalar

Yalnızca Türkçe cevap verir
Alan dışı sorular (yemek, borsa, sağlık vb.) reddedilir
TEKNOFEST/TÜBİTAK dışı mühendislik konularında performans düşebilir

Lisans

Apache 2.0 — Mistral-Nemo temel modeli lisansına uygun.

Downloads last month: 326

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for Rudblest/projedanismanai

Base model

mistralai/Mistral-Nemo-Base-2407

Finetuned

mistralai/Mistral-Nemo-Instruct-2407

Quantized

(173)

this model