Training in progress, epoch 1
Browse files- config.json +5 -44
- model.safetensors +3 -0
- training_args.bin +2 -2
config.json
CHANGED
|
@@ -5,56 +5,17 @@
|
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 151643,
|
| 8 |
-
"dtype": "bfloat16",
|
| 9 |
"eos_token_id": 151645,
|
| 10 |
"head_dim": 128,
|
| 11 |
"hidden_act": "silu",
|
| 12 |
-
"hidden_size":
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
-
"intermediate_size":
|
| 15 |
-
"layer_types": [
|
| 16 |
-
"full_attention",
|
| 17 |
-
"full_attention",
|
| 18 |
-
"full_attention",
|
| 19 |
-
"full_attention",
|
| 20 |
-
"full_attention",
|
| 21 |
-
"full_attention",
|
| 22 |
-
"full_attention",
|
| 23 |
-
"full_attention",
|
| 24 |
-
"full_attention",
|
| 25 |
-
"full_attention",
|
| 26 |
-
"full_attention",
|
| 27 |
-
"full_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"full_attention",
|
| 30 |
-
"full_attention",
|
| 31 |
-
"full_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"full_attention",
|
| 34 |
-
"full_attention",
|
| 35 |
-
"full_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"full_attention",
|
| 38 |
-
"full_attention",
|
| 39 |
-
"full_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"full_attention",
|
| 42 |
-
"full_attention",
|
| 43 |
-
"full_attention",
|
| 44 |
-
"full_attention",
|
| 45 |
-
"full_attention",
|
| 46 |
-
"full_attention",
|
| 47 |
-
"full_attention",
|
| 48 |
-
"full_attention",
|
| 49 |
-
"full_attention",
|
| 50 |
-
"full_attention",
|
| 51 |
-
"full_attention"
|
| 52 |
-
],
|
| 53 |
"max_position_embeddings": 40960,
|
| 54 |
-
"max_window_layers":
|
| 55 |
"model_type": "qwen3",
|
| 56 |
-
"num_attention_heads":
|
| 57 |
-
"num_hidden_layers":
|
| 58 |
"num_key_value_heads": 8,
|
| 59 |
"rms_norm_eps": 1e-06,
|
| 60 |
"rope_scaling": null,
|
|
|
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 151643,
|
|
|
|
| 8 |
"eos_token_id": 151645,
|
| 9 |
"head_dim": 128,
|
| 10 |
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 6144,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
"max_position_embeddings": 40960,
|
| 15 |
+
"max_window_layers": 28,
|
| 16 |
"model_type": "qwen3",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 28,
|
| 19 |
"num_key_value_heads": 8,
|
| 20 |
"rms_norm_eps": 1e-06,
|
| 21 |
"rope_scaling": null,
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1af67257148835753fef993c9d1b99be754bdee903e8f31300b4108d62b1b5d2
|
| 3 |
+
size 3441185608
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee8bf454043cd72f251bdfaecc37db90b9c206be8fb9bccf64f2f6c6652fe3a3
|
| 3 |
+
size 8017
|