Instructions to use evilfreelancer/o1_t-lite-it-1.0_gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use evilfreelancer/o1_t-lite-it-1.0_gguf with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf evilfreelancer/o1_t-lite-it-1.0_gguf:F16
# Run inference directly in the terminal:
llama cli -hf evilfreelancer/o1_t-lite-it-1.0_gguf:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf evilfreelancer/o1_t-lite-it-1.0_gguf:F16
# Run inference directly in the terminal:
llama cli -hf evilfreelancer/o1_t-lite-it-1.0_gguf:F16

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 evilfreelancer/o1_t-lite-it-1.0_gguf:F16
# Run inference directly in the terminal:
./llama-cli -hf evilfreelancer/o1_t-lite-it-1.0_gguf:F16

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 evilfreelancer/o1_t-lite-it-1.0_gguf:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf evilfreelancer/o1_t-lite-it-1.0_gguf:F16

Use Docker

docker model run hf.co/evilfreelancer/o1_t-lite-it-1.0_gguf:F16

LM Studio
Jan
Ollama
How to use evilfreelancer/o1_t-lite-it-1.0_gguf with Ollama:
```
ollama run hf.co/evilfreelancer/o1_t-lite-it-1.0_gguf:F16
```

Unsloth Studio

How to use evilfreelancer/o1_t-lite-it-1.0_gguf 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 evilfreelancer/o1_t-lite-it-1.0_gguf 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 evilfreelancer/o1_t-lite-it-1.0_gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for evilfreelancer/o1_t-lite-it-1.0_gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use evilfreelancer/o1_t-lite-it-1.0_gguf with Docker Model Runner:
```
docker model run hf.co/evilfreelancer/o1_t-lite-it-1.0_gguf:F16
```

Lemonade

How to use evilfreelancer/o1_t-lite-it-1.0_gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull evilfreelancer/o1_t-lite-it-1.0_gguf:F16

Run and chat with the model

lemonade run user.o1_t-lite-it-1.0_gguf-F16

List all available models

lemonade list

Russian o1 / T-lite-it-1.0 GGUF

https://huggingface.co/evilfreelancer/o1_t-lite-it-1.0_lora

LoRA-адаптер для модели T-lite-it-1.0 обученный на датасете Egor-AI/Russian_thinking_dataset (машинный перевод на русский язык датасета BintangFortuna/OpenO1-SFT-EN-SY).

Обученная модель способна имитировать логические размышлению на русском языке по аналогии с тем, как это делает o1 от OpenAI.

Необходимо использовать следующего вида системный промт:

Вы — ИИ-помощник. Отформатируйте свои ответы следующим образом: <Thought> Ваши мысли (понимание, рассуждения) </Thought> <output> Ваш ответ </output>

W&B отчёт: https://api.wandb.ai/links/evilfreelancer/fd7kpwjx

Обучение производилось при помощи утилиты impruver используя конфигурацию T-lite-it/7B_lora_thinking.

На всё про всё ушло примерно 20 часов, при этом понадобилось 23Гб видеопамяти.

output_dir: ./models/T-lite-it_7B_lora_thinking
train_path: ./train.T-lite-it_7B_lora_thinking.jsonl
val_path: ./val.T-lite-it_7B_lora_thinking.jsonl

datasets:
  - name: Egor-AI/Russian_thinking_dataset
    converter: impruver.instruction_to_messages
    add_global_bos: false
    add_global_eos: false
    mapping:
      system: system
      instruction: prompt
      output: response

model:
  class: transformers.AutoModelForCausalLM
  name: t-tech/T-lite-it-1.0
  load_in_4bit: true
  load_in_8bit: false
  dtype: bf16

lora:
  r: 16
  lora_alpha: 16
  lora_dropout: 0
  bias: none
  target_modules: [ q_proj, k_proj, v_proj, o_proj, gate_proj, down_proj, up_proj ]
  task_type: CAUSAL_LM

tokenizer:
  class: transformers.AutoTokenizer
  name: t-tech/T-lite-it-1.0
  max_tokens_count: 1500

trainer:
  eval_strategy: steps
  save_strategy: steps
  eval_steps: 100
  save_steps: 100
  per_device_train_batch_size: 1
  per_device_eval_batch_size: 1
  gradient_accumulation_steps: 8
  logging_steps: 10
  learning_rate: 0.0004
  num_train_epochs: 3
  lr_scheduler_type: cosine
  warmup_steps: 16
  optim: adamw_torch_4bit
  metric_for_best_model: eval_loss
  load_best_model_at_end: true
  save_total_limit: 2
  seed: 42
  remove_unused_columns: false
  max_grad_norm: 1.0
  weight_decay: 0.08
  torch_compile: false