Hugging Face's logo

meridianal
/
FinAI

Text Generation
Transformers
Safetensors
English
finance
mixture-of-experts
continual-learning
financial-nlp
custom-architecture
Model card Files
xet
 Community
meridianal commited on
Commit
c01a1f8
·
verified ·
1 Parent(s): 98369eb

Hourly training update [skip ci]

Browse files
Files changed (4) hide show
  1. checkpoint/config.json +58 -30
  2. checkpoint/generation_config.json +6 -6
  3. checkpoint/model.safetensors +3 -0
  4. checkpoint/trainer_state.pt +3 -0
checkpoint/config.json CHANGED
@@ -1,30 +1,58 @@
1
- {
2
- "_name_or_path": "Qwen/Qwen2.5-0.5B",
3
- "architectures": [
4
- "Qwen2ForCausalLM"
5
- ],
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 151643,
8
- "eos_token_id": 151643,
9
- "hidden_act": "silu",
10
- "hidden_size": 896,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 4864,
13
- "max_position_embeddings": 32768,
14
- "max_window_layers": 24,
15
- "model_type": "qwen2",
16
- "num_attention_heads": 14,
17
- "num_hidden_layers": 24,
18
- "num_key_value_heads": 2,
19
- "rms_norm_eps": 1e-06,
20
- "rope_scaling": null,
21
- "rope_theta": 1000000.0,
22
- "sliding_window": null,
23
- "tie_word_embeddings": true,
24
- "torch_dtype": "bfloat16",
25
- "transformers_version": "4.47.0",
26
- "use_cache": true,
27
- "use_mrope": false,
28
- "use_sliding_window": false,
29
- "vocab_size": 151936
30
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 896,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4864,
13
+ "layer_types": [
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
+ ],
39
+ "max_position_embeddings": 32768,
40
+ "max_window_layers": 24,
41
+ "model_type": "qwen2",
42
+ "num_attention_heads": 14,
43
+ "num_hidden_layers": 24,
44
+ "num_key_value_heads": 2,
45
+ "pad_token_id": null,
46
+ "rms_norm_eps": 1e-06,
47
+ "rope_parameters": {
48
+ "rope_theta": 1000000.0,
49
+ "rope_type": "default"
50
+ },
51
+ "sliding_window": null,
52
+ "tie_word_embeddings": true,
53
+ "transformers_version": "5.5.0",
54
+ "use_cache": false,
55
+ "use_mrope": false,
56
+ "use_sliding_window": false,
57
+ "vocab_size": 151936
58
+ }
checkpoint/generation_config.json CHANGED
@@ -1,6 +1,6 @@
1
- {
2
- "bos_token_id": 151643,
3
- "eos_token_id": 151643,
4
- "max_new_tokens": 2048,
5
- "transformers_version": "4.47.0"
6
- }
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "5.5.0"
6
+ }
checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cd8a7df80e42dbbe8b16bd7e74a99997113bc48567081876b9ce28fdeef3325
3
+ size 988097824
checkpoint/trainer_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea2edf2c6f0bf1605cf16c75f87d6052c1947aaf2afdce7573725d5298efe900
3
+ size 1361