Hugging Face's logo

Zayhe
/
PreThink_MemAgent

Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
trl
sft
conversational
text-generation-inference
Model card Files
xet
 Community
Zayhe commited on
Commit
c087b21
·
verified ·
1 Parent(s): c4abe13

Training in progress, epoch 1

Browse files
Files changed (4) hide show
  1. config.json +39 -0
  2. model-00001-of-00002.safetensors +1 -1
  3. model-00002-of-00002.safetensors +1 -1
  4. training_args.bin +1 -1
config.json CHANGED
@@ -5,12 +5,51 @@
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": 2560,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 9728,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  "max_position_embeddings": 40960,
15
  "max_window_layers": 36,
16
  "model_type": "qwen3",
 
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": 2560,
13
  "initializer_range": 0.02,
14
  "intermediate_size": 9728,
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": 36,
55
  "model_type": "qwen3",
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b0715a10392bdd5118d08de1f514a6a435eca90370c552da724ef7e9349a8b6
3
  size 4967215360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d859d7a0b2472bc60d1e3157e7755aef9aef1321bd536356d20366ae360dae11
3
  size 4967215360
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:609e7e7f829e72fc66dbc79f9934d26593cecf852bf2b8f4989f7f690654d1bd
3
  size 3077766632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbacb63aa2797beac1c00f79715f0c187de43c57bed9ac6c2ee20a3bf4b760fe
3
  size 3077766632
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1afc2500a68483c16264423e468022edf4976022d51c6ffbcedb08c51ab6d277
3
  size 7953
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8470d727e64d342a7188d92201c679231746a8d1ea411a46b4147ce9d144865b
3
  size 7953