Hugging Face's logo

SmallDoge
/
Doge-320M-Instruct-SFT

Question Answering
Transformers
Safetensors
English
doge
text-generation
trl
sft
custom_code
Model card Files
xet
Community
JingzeShi commited on
Commit
8e69278
路
verified 路
1 Parent(s): 1e853ed

Upload DogeForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +47 -42
  2. generation_config.json +7 -7
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,42 +1,47 @@
1
- {
2
- "_name_or_path": "/root/autodl-tmp/small-doge/data/Doge-320M-Instruct-SFT",
3
- "architectures": [
4
- "DogeForCausalLM"
5
- ],
6
- "attention_dropout": 0.0,
7
- "auto_map": {
8
- "AutoConfig": "configuration_doge.DogeConfig",
9
- "AutoModelForCausalLM": "modeling_doge.DogeForCausalLM"
10
- },
11
- "bos_token_id": 0,
12
- "dynamic_mask_ratio": 0.0,
13
- "eos_token_id": 1,
14
- "hidden_act": "silu",
15
- "hidden_bias": false,
16
- "hidden_dropout": 0.0,
17
- "hidden_size": 1024,
18
- "initializer_range": 0.02,
19
- "intermediate_size": 2048,
20
- "is_moe": false,
21
- "keep_window_size": 2048,
22
- "max_position_embeddings": 2048,
23
- "model_type": "doge",
24
- "num_attention_heads": 8,
25
- "num_experts": 2048,
26
- "num_experts_per_tok": 8,
27
- "num_hidden_layers": 32,
28
- "num_key_value_heads": 4,
29
- "pad_token_id": 2,
30
- "rms_norm_eps": 1e-06,
31
- "rope_scaling": {
32
- "factor": 4.0,
33
- "original_max_position_embeddings": 2048,
34
- "rope_type": "dynamic"
35
- },
36
- "rope_theta": 10000.0,
37
- "tie_word_embeddings": true,
38
- "torch_dtype": "float32",
39
- "transformers_version": "4.49.0",
40
- "use_cache": true,
41
- "vocab_size": 32768
42
- }
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DogeForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_doge.DogeConfig",
9
+ "AutoModelForCausalLM": "modeling_doge.DogeForCausalLM"
10
+ },
11
+ "bos_token_id": 0,
12
+ "dynamic_mask_ratio": 0.0,
13
+ "eos_token_id": 1,
14
+ "hidden_act": "silu",
15
+ "hidden_bias": false,
16
+ "hidden_dropout": 0.0,
17
+ "hidden_size": 1024,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 2048,
20
+ "is_moe": false,
21
+ "keep_window_size": 2048,
22
+ "max_position_embeddings": 2048,
23
+ "mlp_bias": false,
24
+ "model_type": "doge",
25
+ "norm_topk_prob": false,
26
+ "num_attention_heads": 8,
27
+ "num_experts": 2048,
28
+ "num_experts_per_tok": 8,
29
+ "num_hidden_layers": 32,
30
+ "num_key_value_heads": 4,
31
+ "output_router_logits": false,
32
+ "pad_token_id": 2,
33
+ "rms_norm_eps": 1e-06,
34
+ "rope_scaling": {
35
+ "factor": 4.0,
36
+ "original_max_position_embeddings": 2048,
37
+ "rope_type": "dynamic"
38
+ },
39
+ "rope_theta": 10000.0,
40
+ "router_aux_loss_coef": 0.001,
41
+ "sliding_window": null,
42
+ "tie_word_embeddings": true,
43
+ "torch_dtype": "bfloat16",
44
+ "transformers_version": "4.55.0",
45
+ "use_cache": true,
46
+ "vocab_size": 32768
47
+ }
generation_config.json CHANGED
@@ -1,7 +1,7 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 0,
4
- "eos_token_id": 1,
5
- "pad_token_id": 2,
6
- "transformers_version": "4.49.0"
7
- }
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.55.0"
7
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c2e840c4e30ba871871ac7442ebfd8684b15509a1f81824bab2cc8a020353e1
3
- size 1343277696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cf8442bf90ed2df4b819494a56aabe750130e7614f75e36a31733477513f3c1
3
+ size 671661936