Instructions to use Aivesa/123065a1-9b3c-4f1d-9da6-851c05141cb8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Aivesa/123065a1-9b3c-4f1d-9da6-851c05141cb8 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("TitanML/tiny-mixtral") model = PeftModel.from_pretrained(base_model, "Aivesa/123065a1-9b3c-4f1d-9da6-851c05141cb8") - Notebooks
- Google Colab
- Kaggle
File size: 846 Bytes
986a7a5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 | {
"_attn_implementation_autoset": true,
"_name_or_path": "TitanML/tiny-mixtral",
"architectures": [
"MixtralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"head_dim": 32,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 3584,
"max_position_embeddings": 131072,
"model_type": "mixtral",
"num_attention_heads": 32,
"num_experts_per_tok": 2,
"num_hidden_layers": 2,
"num_key_value_heads": 8,
"num_local_experts": 8,
"output_router_logits": false,
"rms_norm_eps": 1e-05,
"rope_theta": 1000000.0,
"router_aux_loss_coef": 0.001,
"router_jitter_noise": 0.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.47.1",
"use_cache": false,
"vocab_size": 32000
}
|