Upload folder using huggingface_hub
Browse files
stage_2/checkpoint-500M/config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_sliding_window_pattern": 6,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Gemma3ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"attn_logit_softcapping": null,
|
| 9 |
+
"bos_token_id": 2,
|
| 10 |
+
"dtype": "bfloat16",
|
| 11 |
+
"eos_token_id": 1,
|
| 12 |
+
"final_logit_softcapping": null,
|
| 13 |
+
"head_dim": 256,
|
| 14 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 15 |
+
"hidden_size": 640,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 2048,
|
| 18 |
+
"layer_types": [
|
| 19 |
+
"sliding_attention",
|
| 20 |
+
"sliding_attention",
|
| 21 |
+
"sliding_attention",
|
| 22 |
+
"sliding_attention",
|
| 23 |
+
"sliding_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"sliding_attention",
|
| 26 |
+
"sliding_attention",
|
| 27 |
+
"sliding_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"sliding_attention",
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"full_attention"
|
| 37 |
+
],
|
| 38 |
+
"max_position_embeddings": 32768,
|
| 39 |
+
"model_type": "gemma3_text",
|
| 40 |
+
"num_attention_heads": 4,
|
| 41 |
+
"num_hidden_layers": 18,
|
| 42 |
+
"num_key_value_heads": 1,
|
| 43 |
+
"pad_token_id": 0,
|
| 44 |
+
"query_pre_attn_scalar": 256,
|
| 45 |
+
"rms_norm_eps": 1e-06,
|
| 46 |
+
"rope_parameters": {
|
| 47 |
+
"full_attention": {
|
| 48 |
+
"rope_theta": 1000000.0,
|
| 49 |
+
"rope_type": "default"
|
| 50 |
+
},
|
| 51 |
+
"sliding_attention": {
|
| 52 |
+
"rope_theta": 10000.0,
|
| 53 |
+
"rope_type": "default"
|
| 54 |
+
}
|
| 55 |
+
},
|
| 56 |
+
"sliding_window": 512,
|
| 57 |
+
"tie_word_embeddings": true,
|
| 58 |
+
"transformers_version": "5.3.0",
|
| 59 |
+
"use_bidirectional_attention": false,
|
| 60 |
+
"use_cache": true,
|
| 61 |
+
"vocab_size": 262144
|
| 62 |
+
}
|
stage_2/checkpoint-500M/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33959ba9cd853aaca95ea7c825efc63c0a39b64d4fd79d7de934689efe6bf286
|
| 3 |
+
size 465508967
|
stage_2/checkpoint-500M/state.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"stage": 2,
|
| 3 |
+
"global_step": 61036,
|
| 4 |
+
"total_tokens_seen": 500004864,
|
| 5 |
+
"shard_index": 1,
|
| 6 |
+
"shard_name": "stage_2/shard_2_0001.bin",
|
| 7 |
+
"position_in_shard": 231563264,
|
| 8 |
+
"checkpoint_name": "checkpoint-500M",
|
| 9 |
+
"checkpoint_hf_path": "stage_2/checkpoint-500M",
|
| 10 |
+
"timestamp": "2026-03-10T00:21:20.782890"
|
| 11 |
+
}
|