pretrained_checkpoint_converted

out/pretrain/pretrained_checkpoint_converted/config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94e73e086a5ed14149cee99a1aa3e2563ec7ab536c1653ff332999afa3520694
+size 546

out/pretrain/pretrained_checkpoint_converted/lit_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f96fbbdfdea652bc37108ef1b7ac63fb93ce017b8edca1d20de972b6d072d0fa
+size 133116026

out/pretrain/pretrained_checkpoint_converted/model_config.yaml

@@ -0,0 +1,33 @@
+attention_logit_softcapping: null
+attention_scores_scalar: null
+bias: false
+block_size: 32768
+final_logit_softcapping: null
+gelu_approximate: none
+head_size: 26
+hf_config: {}
+intermediate_size: 1092
+lm_head_bias: false
+mlp_class_name: LLaMAMLP
+n_embd: 312
+n_expert: 0
+n_expert_per_token: 0
+n_head: 12
+n_layer: 10
+n_query_groups: 4
+name: ''
+norm_class_name: RMSNorm
+norm_eps: 1.0e-05
+padded_vocab_size: 32768
+padding_multiple: 512
+parallel_residual: false
+post_attention_norm: false
+post_mlp_norm: false
+rope_base: 500000
+rope_condense_ratio: 1
+rotary_percentage: 1.0
+scale_embeddings: false
+shared_attention_norm: false
+sliding_window_layer_placing: null
+sliding_window_size: null
+vocab_size: 32768

out/pretrain/pretrained_checkpoint_converted/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b496a30dc268bcb8adfd551f693e68e9eadd06b81cab385c088a61e7663649c
+size 1368561

out/pretrain/pretrained_checkpoint_converted/tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6333d68c3280be6081b795cc160fd5872707562021f9889b2e2bd3ae508fa62
+size 23043