Hugging Face's logo

NOSIBLE
/
forward-looking-v1.1-base

Text Generation
Transformers
Safetensors
English
qwen3
finance
nlp
conversational
text-generation-inference
Model card Files
xet
Community
matthewdicks98 commited on
Commit
ab35f97
·
verified ·
1 Parent(s): 767ab5b

Left padding, no thinking, EOS

Browse files
Files changed (3) hide show
  1. config.json +60 -60
  2. generation_config.json +13 -13
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,60 +1,60 @@
1
- {
2
- "architectures": [
3
- "Qwen3ForCausalLM"
4
- ],
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": 1024,
13
- "initializer_range": 0.02,
14
- "intermediate_size": 3072,
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
- ],
45
- "max_position_embeddings": 40960,
46
- "max_window_layers": 28,
47
- "model_type": "qwen3",
48
- "num_attention_heads": 16,
49
- "num_hidden_layers": 28,
50
- "num_key_value_heads": 8,
51
- "rms_norm_eps": 1e-06,
52
- "rope_scaling": null,
53
- "rope_theta": 1000000,
54
- "sliding_window": null,
55
- "tie_word_embeddings": true,
56
- "transformers_version": "4.57.3",
57
- "use_cache": true,
58
- "use_sliding_window": false,
59
- "vocab_size": 151936
60
- }
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
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": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
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
+ ],
45
+ "max_position_embeddings": 40960,
46
+ "max_window_layers": 28,
47
+ "model_type": "qwen3",
48
+ "num_attention_heads": 16,
49
+ "num_hidden_layers": 28,
50
+ "num_key_value_heads": 8,
51
+ "rms_norm_eps": 1e-06,
52
+ "rope_scaling": null,
53
+ "rope_theta": 1000000,
54
+ "sliding_window": null,
55
+ "tie_word_embeddings": true,
56
+ "transformers_version": "4.57.3",
57
+ "use_cache": true,
58
+ "use_sliding_window": false,
59
+ "vocab_size": 151936
60
+ }
generation_config.json CHANGED
@@ -1,13 +1,13 @@
1
- {
2
- "bos_token_id": 151643,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 151645,
6
- 151643
7
- ],
8
- "pad_token_id": 151643,
9
- "temperature": 0.6,
10
- "top_k": 20,
11
- "top_p": 0.95,
12
- "transformers_version": "4.57.3"
13
- }
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.57.3"
13
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:587d492d72dee07a3cfb48b5722140915edfa235045f3425917564dccd8956af
3
  size 1192135096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7bd43064930d24aee377097f56cedea8e67851741dd9b1d82d144d1262cb6f7
3
  size 1192135096