masani/SFT_DeepScaleR_Llama-3.2-3B_epoch_1_global_step_26
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: masani/SFT_DeepScaleR_Llama-3.2-3B_epoch_1_global_step_26
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-13 12:24:16 +08:00
commit 15a1109a82
11 changed files with 2648 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
config.json Normal file
View File

@@ -0,0 +1,36 @@
{
"_name_or_path": "/mnt/dlabscratch1/amani/LLM-RL/logs/SFT_for_rl/DeepScaleR_Llama-3.2-3B/2026-01-25_16-42-51/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": 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,
"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
}