music_generation_model API & Inference Endpoint

🧩 Configuration

yaml

slices:  - sources:      - model: TheBloke/openchat_3.5-GPTQ        layer_range: [0, 32]      - model: asigalov61/Allegro-Music-Transformer        layer_range: [0, 32]merge_method: slerpbase_model: TheBloke/openchat_3.5-GPTQparameters:  t:    - filter: self_attn      value: [0, 0.5, 0.3, 0.7, 1]    - filter: mlp      value: [1, 0.5, 0.7, 0.3, 0]    - value: 0.5dtype: bfloat16

💻 Usage

python

!pip install -qU transformers accelerate from transformers import AutoTokenizerimport transformersimport torch model = "nagayama0706/music_generation_model"messages = [{"role": "user", "content": "What is a large language model?"}] tokenizer = AutoTokenizer.from_pretrained(model)prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)pipeline = transformers.pipeline(    "text-generation",    model=model,    torch_dtype=torch.float16,    device_map="auto",) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)print(outputs[0]["generated_text"])

🧩 Configuration

yaml

slices:  - sources:      - model: TheBloke/openchat_3.5-GPTQ        layer_range: [0, 32]      - model: asigalov61/Allegro-Music-Transformer        layer_range: [0, 32]merge_method: slerpbase_model: TheBloke/openchat_3.5-GPTQparameters:  t:    - filter: self_attn      value: [0, 0.5, 0.3, 0.7, 1]    - filter: mlp      value: [1, 0.5, 0.7, 0.3, 0]    - value: 0.5dtype: bfloat16

slices:  - sources:      - model: TheBloke/openchat_3.5-GPTQ        layer_range: [0, 32]      - model: asigalov61/Allegro-Music-Transformer        layer_range: [0, 32]merge_method: slerpbase_model: TheBloke/openchat_3.5-GPTQparameters:  t:    - filter: self_attn      value: [0, 0.5, 0.3, 0.7, 1]    - filter: mlp      value: [1, 0.5, 0.7, 0.3, 0]    - value: 0.5dtype: bfloat16

💻 Usage

python

!pip install -qU transformers accelerate from transformers import AutoTokenizerimport transformersimport torch model = "nagayama0706/music_generation_model"messages = [{"role": "user", "content": "What is a large language model?"}] tokenizer = AutoTokenizer.from_pretrained(model)prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)pipeline = transformers.pipeline(    "text-generation",    model=model,    torch_dtype=torch.float16,    device_map="auto",) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)print(outputs[0]["generated_text"])

music_generation_model

README

🧩 Configuration

💻 Usage

Explore FriendliAI today

README

🧩 Configuration

💻 Usage