File size: 1,568 Bytes
c79c520 |
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 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 |
{
"_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"eos_token_id": [
128001,
128008,
128009
],
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 3072,
"initializer_range": 0.02,
"intermediate_size": 8192,
"max_position_embeddings": 131072,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 24,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"quantization_config": {
"amp": false,
"autoround_version": "0.4.0.dev",
"backend": "auto_round:exllamav2",
"bits": 4,
"data_type": "int",
"dataset": "NeelNanda/pile-10k",
"enable_minmax_tuning": true,
"enable_norm_bias_tuning": false,
"enable_quanted_input": true,
"gradient_accumulate_steps": 1,
"group_size": 128,
"iters": 200,
"low_gpu_mem_usage": false,
"lr": 0.005,
"minmax_lr": 0.005,
"nsamples": 128,
"quant_block_list": null,
"quant_method": "intel/auto-round",
"scale_dtype": "torch.float16",
"seqlen": 512,
"sym": false,
"train_bs": 4
},
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 32.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"rope_theta": 500000.0,
"tie_word_embeddings": true,
"torch_dtype": "float32",
"transformers_version": "4.45.2",
"use_cache": true,
"vocab_size": 128256
}
|