Upload paper checkpoint l8k365m_dense_seed45 checkpoint-44000
Browse files- checkpoints/primary_365m/l8k365m_dense_seed45/checkpoint-44000/config.json +36 -0
- checkpoints/primary_365m/l8k365m_dense_seed45/checkpoint-44000/loader_gen_state_rank0.pt +3 -0
- checkpoints/primary_365m/l8k365m_dense_seed45/checkpoint-44000/model.pt +3 -0
- checkpoints/primary_365m/l8k365m_dense_seed45/checkpoint-44000/rng_state_rank0.pt +3 -0
- checkpoints/primary_365m/l8k365m_dense_seed45/checkpoint-44000/training_state.pt +3 -0
checkpoints/primary_365m/l8k365m_dense_seed45/checkpoint-44000/config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"vocab_size": 151936,
|
| 3 |
+
"hidden_size": 768,
|
| 4 |
+
"intermediate_size": 3072,
|
| 5 |
+
"num_hidden_layers": 28,
|
| 6 |
+
"num_attention_heads": 6,
|
| 7 |
+
"num_key_value_heads": 2,
|
| 8 |
+
"head_dim": 128,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"max_position_embeddings": 32768,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"rms_norm_eps": 1e-06,
|
| 13 |
+
"use_cache": true,
|
| 14 |
+
"tie_word_embeddings": true,
|
| 15 |
+
"rope_theta": 1000000,
|
| 16 |
+
"rope_scaling": null,
|
| 17 |
+
"attention_bias": false,
|
| 18 |
+
"attention_dropout": 0.0,
|
| 19 |
+
"bos_token_id": 151643,
|
| 20 |
+
"eos_token_id": 151643,
|
| 21 |
+
"checkpoint_activations": false,
|
| 22 |
+
"attention_type": "sparse_stochastic",
|
| 23 |
+
"sparse_block_size": 128,
|
| 24 |
+
"sparse_num_random_blocks": 31,
|
| 25 |
+
"sparse_mask_pool_size": 1,
|
| 26 |
+
"sparse_max_seq_length": 8192,
|
| 27 |
+
"sparse_layer_indices": null,
|
| 28 |
+
"sparse_mask_cache_dir": null,
|
| 29 |
+
"sparse_mask_seed": 0,
|
| 30 |
+
"sparse_mixed_nrb_set": null,
|
| 31 |
+
"moba_block_size": 128,
|
| 32 |
+
"moba_top_k": 32,
|
| 33 |
+
"asentmax_alpha": 1.5,
|
| 34 |
+
"asentmax_learn_temp": true,
|
| 35 |
+
"asentmax_init_temp": 1.0
|
| 36 |
+
}
|
checkpoints/primary_365m/l8k365m_dense_seed45/checkpoint-44000/loader_gen_state_rank0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cee528d05ac8a47cd808ee86eda62863babc34c9a08696cc713c484f3f4bcdeb
|
| 3 |
+
size 6802
|
checkpoints/primary_365m/l8k365m_dense_seed45/checkpoint-44000/model.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efd8a32f0fd9d062d370abbf80810075222ea4b31abb2fdf279cdc8dd06cbc7f
|
| 3 |
+
size 718031899
|
checkpoints/primary_365m/l8k365m_dense_seed45/checkpoint-44000/rng_state_rank0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2f7a02fd17618b0a8d4d860aa2778ace47bb4e82285fa571ffcccd317c823e4
|
| 3 |
+
size 14821
|
checkpoints/primary_365m/l8k365m_dense_seed45/checkpoint-44000/training_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:886dbcca810948ad5e4091ef3b8c618c6417064b1e0eea02960598f7aa22cb95
|
| 3 |
+
size 1436105235
|