394c597642
Model: masani/SFT_DeepScaleR_Llama-3.2-1B_epoch_1_global_step_26 Source: Original Platform
37 lines
985 B
JSON
37 lines
985 B
JSON
{
|
|
"_name_or_path": "/mnt/dlabscratch1/amani/LLM-RL/logs/SFT_for_rl/DeepScaleR_Llama-3.2-1B/2026-01-25_16-35-29/checkpoints/epoch_1_global_step_26",
|
|
"architectures": [
|
|
"LlamaForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 128000,
|
|
"eos_token_id": 128001,
|
|
"head_dim": 64,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 2048,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 8192,
|
|
"max_position_embeddings": 131072,
|
|
"mlp_bias": false,
|
|
"model_type": "llama",
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 16,
|
|
"num_key_value_heads": 8,
|
|
"pretraining_tp": 1,
|
|
"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": "4.49.0",
|
|
"use_cache": true,
|
|
"vocab_size": 128257
|
|
}
|