Hugging Face's logo

DavidAU
/
Qwen2.5-3X7B-CoderInstruct-OlympicCoder-MS-Next-Coder-25B-v1-128k-ctx

Text Generation
Transformers
Safetensors
English
qwen2_moe
Merge
programming
code generation
code
codeqwen
Mixture of Experts
coding
coder
qwen2
chat
qwen
qwen-coder
mixture of experts
qwen2moe
3X7B Shared.
conversational
Model card Files Community
DavidAU commited on
Commit
0f6525f
·
verified ·
1 Parent(s): 02b7583

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +42 -38
config.json CHANGED
@@ -1,38 +1,42 @@
1
- {
2
- "architectures": [
3
- "Qwen2MoeForCausalLM"
4
- ],
5
- "attention_dropout": 0.0,
6
- "bos_token_id": 151643,
7
- "decoder_sparse_step": 1,
8
- "eos_token_id": 151645,
9
- "hidden_act": "silu",
10
- "hidden_size": 3584,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 18944,
13
- "max_position_embeddings": 32768,
14
- "max_window_layers": 28,
15
- "mlp_only_layers": [],
16
- "model_type": "qwen2_moe",
17
- "moe_intermediate_size": 18944,
18
- "norm_topk_prob": true,
19
- "num_attention_heads": 28,
20
- "num_experts": 3,
21
- "num_experts_per_tok": 2,
22
- "num_hidden_layers": 28,
23
- "num_key_value_heads": 4,
24
- "output_router_logits": false,
25
- "qkv_bias": true,
26
- "rms_norm_eps": 1e-06,
27
- "rope_scaling": null,
28
- "rope_theta": 1000000.0,
29
- "router_aux_loss_coef": 0.001,
30
- "shared_expert_intermediate_size": 18944,
31
- "sliding_window": null,
32
- "tie_word_embeddings": false,
33
- "torch_dtype": "bfloat16",
34
- "transformers_version": "4.52.0.dev0",
35
- "use_cache": true,
36
- "use_sliding_window": false,
37
- "vocab_size": 152064
38
- }
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2MoeForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "decoder_sparse_step": 1,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 131072,
14
+ "max_window_layers": 28,
15
+ "mlp_only_layers": [],
16
+ "model_type": "qwen2_moe",
17
+ "moe_intermediate_size": 18944,
18
+ "norm_topk_prob": true,
19
+ "num_attention_heads": 28,
20
+ "num_experts": 3,
21
+ "num_experts_per_tok": 2,
22
+ "num_hidden_layers": 28,
23
+ "num_key_value_heads": 4,
24
+ "output_router_logits": false,
25
+ "qkv_bias": true,
26
+ "rms_norm_eps": 1e-06,
27
+ "rope_scaling": {
28
+ "type": "yarn",
29
+ "factor": 4.0,
30
+ "original_max_position_embeddings": 32768
31
+ },
32
+ "rope_theta": 1000000.0,
33
+ "router_aux_loss_coef": 0.001,
34
+ "shared_expert_intermediate_size": 18944,
35
+ "sliding_window": null,
36
+ "tie_word_embeddings": false,
37
+ "torch_dtype": "bfloat16",
38
+ "transformers_version": "4.52.0.dev0",
39
+ "use_cache": true,
40
+ "use_sliding_window": false,
41
+ "vocab_size": 152064
42
+ }