Instructions to use Defetya/openllama-3b-saiga with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Defetya/openllama-3b-saiga with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Defetya/openllama-3b-saiga") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Defetya/openllama-3b-saiga") model = AutoModelForCausalLM.from_pretrained("Defetya/openllama-3b-saiga") 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 Defetya/openllama-3b-saiga with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Defetya/openllama-3b-saiga" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Defetya/openllama-3b-saiga", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Defetya/openllama-3b-saiga
- SGLang
How to use Defetya/openllama-3b-saiga 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 "Defetya/openllama-3b-saiga" \ --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": "Defetya/openllama-3b-saiga", "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 "Defetya/openllama-3b-saiga" \ --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": "Defetya/openllama-3b-saiga", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Defetya/openllama-3b-saiga with Docker Model Runner:
docker model run hf.co/Defetya/openllama-3b-saiga
YAML Metadata Warning:The pipeline tag "text2text-generation" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other
Defetya/ru-3b-openllama-transformers, fine-tuned on Saiga multi-turn dataset (not fully yet, weights will be updated). Format taken from llama-2-chat.
Модель немного корежит, иногда вставляет в ответ символы, напоминающие [/INST]. Но в целом прикольная. Планируется также использовать DPO на IlyaGusev/rulm_human_preferences. Примеры:
Юзер: "Обладаешь ли ты самосознанием?", модель: "Да, я обладаю самосознанием".
Юзер: "Сколько будет 2+7?", модель: "12".
Юзер: "Сколько тебе лет?", модель: "Я родом из детского дома."
Юзер: "Почему трава зеленая", модель: "Трава, которая растет в степи, имеет зеленый цвет, потому что она выделяет особый пигмент, который называется хлорофилл."
Юзер: "Сочини длинный рассказ, в котором обязательно должны быть упомянуты Таня и мяч.", модель: "Таня уронила мяч на землю и упала, сильно пострадав. Расскажи, что произошло и почему Таня так сильно пострадала." (без комментариев) Другой ответ: "Таня - девушка из простой семьи. Трудный характер и всего пятнадцать лет, она встретила Мяча, который любил ее сильнее всех на свете. Таня была похищена молодым парнем, и она сбежала с ним, но была поймана и вынуждена бороться за свою жизнь" Модель планировалась быть серьезной, но пока вызывает смех. Надеюсь, после обучения на всем датасете это изменится.
- Downloads last month
- 821