Training in progress, epoch 1
Browse files- config.json +2 -32
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
- model.safetensors.index.json +0 -1
- training_args.bin +2 -2
config.json
CHANGED
|
@@ -9,36 +9,6 @@
|
|
| 9 |
"hidden_size": 3584,
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
"intermediate_size": 18944,
|
| 12 |
-
"layer_types": [
|
| 13 |
-
"full_attention",
|
| 14 |
-
"full_attention",
|
| 15 |
-
"full_attention",
|
| 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 |
-
],
|
| 42 |
"max_position_embeddings": 32768,
|
| 43 |
"max_window_layers": 28,
|
| 44 |
"model_type": "qwen2",
|
|
@@ -48,10 +18,10 @@
|
|
| 48 |
"rms_norm_eps": 1e-06,
|
| 49 |
"rope_scaling": null,
|
| 50 |
"rope_theta": 1000000.0,
|
| 51 |
-
"sliding_window":
|
| 52 |
"tie_word_embeddings": false,
|
| 53 |
"torch_dtype": "bfloat16",
|
| 54 |
-
"transformers_version": "4.
|
| 55 |
"use_cache": false,
|
| 56 |
"use_sliding_window": false,
|
| 57 |
"vocab_size": 152064
|
|
|
|
| 9 |
"hidden_size": 3584,
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
"intermediate_size": 18944,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
"max_position_embeddings": 32768,
|
| 13 |
"max_window_layers": 28,
|
| 14 |
"model_type": "qwen2",
|
|
|
|
| 18 |
"rms_norm_eps": 1e-06,
|
| 19 |
"rope_scaling": null,
|
| 20 |
"rope_theta": 1000000.0,
|
| 21 |
+
"sliding_window": 131072,
|
| 22 |
"tie_word_embeddings": false,
|
| 23 |
"torch_dtype": "bfloat16",
|
| 24 |
+
"transformers_version": "4.52.3",
|
| 25 |
"use_cache": false,
|
| 26 |
"use_sliding_window": false,
|
| 27 |
"vocab_size": 152064
|
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4877660776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58c527756029ac3feeaff3d08775069fd2cc3d5f73930d141574a97b40b401db
|
| 3 |
size 4877660776
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4932751008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:197fbdbcf74853af7ce7b19ff320cdbd65bc7dd333e15fb07f5f2126f04c3fa0
|
| 3 |
size 4932751008
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4330865200
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff561d88f43cb7211b86bab21522d22949ff46af01241d78a6e908ef14d27974
|
| 3 |
size 4330865200
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1089994880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:348573f05f1646816ce5231f0bfbceba5d0a96c3d99b4e9d36f16858c4e6051d
|
| 3 |
size 1089994880
|
model.safetensors.index.json
CHANGED
|
@@ -1,6 +1,5 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_parameters": 333312,
|
| 4 |
"total_size": 15231233024
|
| 5 |
},
|
| 6 |
"weight_map": {
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
|
|
|
| 3 |
"total_size": 15231233024
|
| 4 |
},
|
| 5 |
"weight_map": {
|
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 sha256:0ea8872e02997207dd334542b47e6bd1d4831e96e6bff90e5741a10a4cc1447a
|
| 3 |
+
size 8017
|