Text-to-Speech
Transformers
Safetensors
qwen3_5_text
text-generation
tts
speech-synthesis
voice-cloning
autoregressive
vllm
Instructions to use nineninesix/gepard-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nineninesix/gepard-1.0 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="nineninesix/gepard-1.0")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("nineninesix/gepard-1.0") model = AutoModelForCausalLM.from_pretrained("nineninesix/gepard-1.0") - Notebooks
- Google Colab
- Kaggle
| { | |
| "backbone_config": { | |
| "pad_token_id": null, | |
| "bos_token_id": null, | |
| "eos_token_id": 248044, | |
| "tie_word_embeddings": true, | |
| "vocab_size": 248320, | |
| "max_position_embeddings": 262144, | |
| "hidden_size": 1024, | |
| "intermediate_size": 3584, | |
| "num_hidden_layers": 14, | |
| "num_attention_heads": 8, | |
| "num_key_value_heads": 2, | |
| "hidden_act": "silu", | |
| "initializer_range": 0.02, | |
| "rms_norm_eps": 1e-06, | |
| "use_cache": true, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "head_dim": 256, | |
| "rope_parameters": { | |
| "mrope_interleaved": true, | |
| "mrope_section": [ | |
| 11, | |
| 11, | |
| 10 | |
| ], | |
| "rope_type": "default", | |
| "rope_theta": 10000000, | |
| "partial_rotary_factor": 1.0 | |
| }, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "linear_conv_kernel_dim": 4, | |
| "linear_key_head_dim": 128, | |
| "linear_value_head_dim": 128, | |
| "linear_num_key_heads": 16, | |
| "linear_num_value_heads": 16, | |
| "return_dict": true, | |
| "output_hidden_states": false, | |
| "dtype": "bfloat16", | |
| "chunk_size_feed_forward": 0, | |
| "is_encoder_decoder": false, | |
| "architectures": [ | |
| "Qwen3_5ForCausalLM" | |
| ], | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "problem_type": null, | |
| "_name_or_path": "nineninesix/qwen3_5-full-attn-only-14", | |
| "transformers_version": "5.3.0", | |
| "attn_output_gate": true, | |
| "full_attention_interval": 4, | |
| "mamba_ssm_dtype": "float32", | |
| "mlp_only_layers": [], | |
| "model_type": "qwen3_5_text", | |
| "partial_rotary_factor": 1.0, | |
| "output_attentions": false | |
| }, | |
| "audio_heads": { | |
| "level_audio_0": 8, | |
| "level_audio_1": 7, | |
| "level_audio_2": 6, | |
| "level_audio_3": 6, | |
| "level_audio_4": 8, | |
| "level_audio_5": 7, | |
| "level_audio_6": 6, | |
| "level_audio_7": 6, | |
| "level_audio_8": 8, | |
| "level_audio_9": 7, | |
| "level_audio_10": 6, | |
| "level_audio_11": 6, | |
| "level_audio_12": 8, | |
| "level_audio_13": 7, | |
| "level_audio_14": 6, | |
| "level_audio_15": 6, | |
| "level_audio_16": 8, | |
| "level_audio_17": 7, | |
| "level_audio_18": 6, | |
| "level_audio_19": 6, | |
| "level_audio_20": 8, | |
| "level_audio_21": 7, | |
| "level_audio_22": 6, | |
| "level_audio_23": 6, | |
| "level_audio_24": 8, | |
| "level_audio_25": 7, | |
| "level_audio_26": 6, | |
| "level_audio_27": 6, | |
| "level_audio_28": 8, | |
| "level_audio_29": 7, | |
| "level_audio_30": 6, | |
| "level_audio_31": 6 | |
| }, | |
| "audio_embed_dim": 32, | |
| "partial_rotary_factor": 1.0, | |
| "special_tokens": { | |
| "tokeniser_length": 248077, | |
| "start_of_text": 248073, | |
| "end_of_text": 248074, | |
| "start_of_speech": 248070, | |
| "end_of_speech": 248071, | |
| "tts_pad": 248076 | |
| }, | |
| "stop_loss_weight": 2.0, | |
| "stop_pos_weight": 25.0, | |
| "model_dtype": "bfloat16", | |
| "codec": { | |
| "num_layers": 8, | |
| "fsq_levels": [ | |
| 8, | |
| 7, | |
| 6, | |
| 6 | |
| ], | |
| "do_unfold": true, | |
| "frame_rate_hz": 21.5, | |
| "codec_id": "nvidia/nemo-nano-codec-22khz-1.89kbps-21.5fps", | |
| "sample_rate": 22050 | |
| }, | |
| "text_repetition": { | |
| "enabled": true, | |
| "target_text_tokens": 16, | |
| "apply_below": 13, | |
| "max_repeats": 8, | |
| "mixed_keep_prob": 0.25, | |
| "seed": 0 | |
| }, | |
| "voice_cloning": { | |
| "enabled": true, | |
| "compressor": { | |
| "num_queries": 8, | |
| "num_layers": 2, | |
| "num_heads": 8, | |
| "d_model": 1024, | |
| "ffn_hidden_size_multiplier": 4, | |
| "dropout": 0.1 | |
| }, | |
| "training": { | |
| "cfg_dropout_prob": 0.15, | |
| "supcon": { | |
| "enabled": true, | |
| "use_projection": true, | |
| "projection_hidden_dim": 128, | |
| "projection_dim": 128 | |
| }, | |
| "diversity_loss": { | |
| "enabled": true | |
| } | |
| } | |
| }, | |
| "return_dict": true, | |
| "output_hidden_states": false, | |
| "dtype": null, | |
| "chunk_size_feed_forward": 0, | |
| "is_encoder_decoder": false, | |
| "architectures": null, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "problem_type": null, | |
| "_name_or_path": "", | |
| "transformers_version": "5.3.0", | |
| "model_type": "gepard", | |
| "output_attentions": false | |
| } | |