1273b5b690
Model: unsloth/Llama-3.1-Nemotron-Nano-4B-v1.1-unsloth-bnb-4bit Source: Original Platform
59 lines
1.5 KiB
JSON
59 lines
1.5 KiB
JSON
{
|
|
"architectures": [
|
|
"LlamaForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 128000,
|
|
"eos_token_id": 128009,
|
|
"head_dim": 128,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 3072,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 9216,
|
|
"max_position_embeddings": 131072,
|
|
"mlp_bias": false,
|
|
"model_type": "llama",
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 32,
|
|
"num_key_value_heads": 8,
|
|
"pad_token_id": 128004,
|
|
"pretraining_tp": 1,
|
|
"quantization_config": {
|
|
"_load_in_4bit": true,
|
|
"_load_in_8bit": false,
|
|
"bnb_4bit_compute_dtype": "bfloat16",
|
|
"bnb_4bit_quant_storage": "uint8",
|
|
"bnb_4bit_quant_type": "nf4",
|
|
"bnb_4bit_use_double_quant": true,
|
|
"llm_int8_enable_fp32_cpu_offload": false,
|
|
"llm_int8_has_fp16_weight": false,
|
|
"llm_int8_skip_modules": [
|
|
"lm_head",
|
|
"multi_modal_projector",
|
|
"merger",
|
|
"modality_projection",
|
|
"model.layers.1.self_attn"
|
|
],
|
|
"llm_int8_threshold": 6.0,
|
|
"load_in_4bit": true,
|
|
"load_in_8bit": false,
|
|
"quant_method": "bitsandbytes"
|
|
},
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_scaling": {
|
|
"factor": 4.0,
|
|
"high_freq_factor": 4.0,
|
|
"low_freq_factor": 1.0,
|
|
"original_max_position_embeddings": 8192,
|
|
"rope_type": "llama3"
|
|
},
|
|
"rope_theta": 3565775107.2609234,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.52.3",
|
|
"unsloth_fixed": true,
|
|
"use_cache": true,
|
|
"vocab_size": 128256
|
|
}
|