Text Generation
PEFT
Safetensors
llama4_text
finance
defi
wallet-risk
autoscientist
lora
foresight-ai
conversational
4-bit precision
bitsandbytes
Instructions to use samscript18/adaption_defi_wallet_risk_classif_3d6e6540 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use samscript18/adaption_defi_wallet_risk_classif_3d6e6540 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("togethercomputer/Llama-4-Scout-17B-16E-Instruct_bnb_4bit") model = PeftModel.from_pretrained(base_model, "samscript18/adaption_defi_wallet_risk_classif_3d6e6540") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "Llama4ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_chunk_size": 8192, | |
| "attention_dropout": 0.0, | |
| "attn_scale": 0.1, | |
| "attn_temperature_tuning": true, | |
| "bos_token_id": 200000, | |
| "cache_implementation": "hybrid", | |
| "dtype": "bfloat16", | |
| "eos_token_id": 200008, | |
| "floor_scale": 8192, | |
| "for_llm_compressor": false, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "interleave_moe_layer_step": 1, | |
| "intermediate_size": 8192, | |
| "intermediate_size_mlp": 16384, | |
| "layer_types": [ | |
| "chunked_attention", | |
| "chunked_attention", | |
| "chunked_attention", | |
| "full_attention", | |
| "chunked_attention", | |
| "chunked_attention", | |
| "chunked_attention", | |
| "full_attention", | |
| "chunked_attention", | |
| "chunked_attention", | |
| "chunked_attention", | |
| "full_attention", | |
| "chunked_attention", | |
| "chunked_attention", | |
| "chunked_attention", | |
| "full_attention", | |
| "chunked_attention", | |
| "chunked_attention", | |
| "chunked_attention", | |
| "full_attention", | |
| "chunked_attention", | |
| "chunked_attention", | |
| "chunked_attention", | |
| "full_attention", | |
| "chunked_attention", | |
| "chunked_attention", | |
| "chunked_attention", | |
| "full_attention", | |
| "chunked_attention", | |
| "chunked_attention", | |
| "chunked_attention", | |
| "full_attention", | |
| "chunked_attention", | |
| "chunked_attention", | |
| "chunked_attention", | |
| "full_attention", | |
| "chunked_attention", | |
| "chunked_attention", | |
| "chunked_attention", | |
| "full_attention", | |
| "chunked_attention", | |
| "chunked_attention", | |
| "chunked_attention", | |
| "full_attention", | |
| "chunked_attention", | |
| "chunked_attention", | |
| "chunked_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 10485760, | |
| "model_type": "llama4_text", | |
| "moe_layers": [ | |
| 0, | |
| 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, | |
| 35, | |
| 36, | |
| 37, | |
| 38, | |
| 39, | |
| 40, | |
| 41, | |
| 42, | |
| 43, | |
| 44, | |
| 45, | |
| 46, | |
| 47 | |
| ], | |
| "no_rope_layer_interval": 4, | |
| "no_rope_layers": [ | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0 | |
| ], | |
| "num_attention_heads": 40, | |
| "num_experts_per_tok": 1, | |
| "num_hidden_layers": 48, | |
| "num_key_value_heads": 8, | |
| "num_local_experts": 16, | |
| "output_router_logits": false, | |
| "pad_token_id": 200018, | |
| "quantization_config": { | |
| "_load_in_4bit": true, | |
| "_load_in_8bit": false, | |
| "bnb_4bit_compute_dtype": "bfloat16", | |
| "bnb_4bit_quant_storage": "bfloat16", | |
| "bnb_4bit_quant_type": "nf4", | |
| "bnb_4bit_use_double_quant": false, | |
| "llm_int8_enable_fp32_cpu_offload": false, | |
| "llm_int8_has_fp16_weight": false, | |
| "llm_int8_skip_modules": null, | |
| "llm_int8_threshold": 6.0, | |
| "load_in_4bit": true, | |
| "load_in_8bit": false, | |
| "quant_method": "bitsandbytes" | |
| }, | |
| "rms_norm_eps": 1e-05, | |
| "rope_parameters": { | |
| "factor": 16.0, | |
| "high_freq_factor": 1.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_theta": 500000.0, | |
| "rope_type": "llama3" | |
| }, | |
| "router_aux_loss_coef": 0.001, | |
| "router_jitter_noise": 0.0, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.10.1", | |
| "use_cache": false, | |
| "use_qk_norm": true, | |
| "vocab_size": 202048, | |
| "torch_dtype": "bfloat16" | |
| } | |