Hugging Face's logo

DISCOStudy
/
PhenoGemini

Safetensors
English
qwen3_moe
medical
Model card Files
xet
 Community
Peter0707 commited on
Commit
952cd6f
·
verified ·
1 Parent(s): e898d8a

Upload Qwen3MoeForCausalLM

Browse files
Files changed (16) hide show
  1. config.json +38 -0
  2. generation_config.json +6 -0
  3. model-00001-of-00013.safetensors +3 -0
  4. model-00002-of-00013.safetensors +3 -0
  5. model-00003-of-00013.safetensors +3 -0
  6. model-00004-of-00013.safetensors +3 -0
  7. model-00005-of-00013.safetensors +3 -0
  8. model-00006-of-00013.safetensors +3 -0
  9. model-00007-of-00013.safetensors +3 -0
  10. model-00008-of-00013.safetensors +3 -0
  11. model-00009-of-00013.safetensors +3 -0
  12. model-00010-of-00013.safetensors +3 -0
  13. model-00011-of-00013.safetensors +3 -0
  14. model-00012-of-00013.safetensors +3 -0
  15. model-00013-of-00013.safetensors +3 -0
  16. model.safetensors.index.json +0 -0
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3MoeForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "decoder_sparse_step": 1,
9
+ "dtype": "bfloat16",
10
+ "eos_token_id": 151645,
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 2048,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 6144,
16
+ "max_position_embeddings": 262144,
17
+ "max_window_layers": 48,
18
+ "mlp_only_layers": [],
19
+ "model_type": "qwen3_moe",
20
+ "moe_intermediate_size": 768,
21
+ "norm_topk_prob": true,
22
+ "num_attention_heads": 32,
23
+ "num_experts": 136,
24
+ "num_experts_per_tok": 8,
25
+ "num_hidden_layers": 48,
26
+ "num_key_value_heads": 4,
27
+ "output_router_logits": false,
28
+ "rms_norm_eps": 1e-06,
29
+ "rope_scaling": null,
30
+ "rope_theta": 10000000,
31
+ "router_aux_loss_coef": 0.001,
32
+ "sliding_window": null,
33
+ "tie_word_embeddings": false,
34
+ "transformers_version": "4.56.2",
35
+ "use_cache": true,
36
+ "use_sliding_window": false,
37
+ "vocab_size": 156408
38
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.56.2"
6
+ }
model-00001-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7d49ce2998ac87038b81da6ce5193e2dd47ea943fbf17a2054d678a235c6b4f
3
+ size 4999904184
model-00002-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb5c474915b68211233e2cd69c0356671b1f63adc499faaf960b85ec56c8dc2f
3
+ size 4997872784
model-00003-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c54e3a419d338d8aec3e928d86b840b11f3c3726e3bab31c29eee75f9698ea0b
3
+ size 4997307800
model-00004-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e71d8f4db460412dd65b70d42eddf57ca04e8a02479029ebfb2c47942999240
3
+ size 4997874296
model-00005-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:646c132a32a9cd2c0652f39fef2ec2188d46f9b61287fb8a68b9f668bf039b90
3
+ size 4997874352
model-00006-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ac3c1295c0245e874494aabf86e33f06dc8dc410e4f51217d25b606fbeee405
3
+ size 4997874352
model-00007-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b378a364f223a983f3a68885c8647f9c8684784b83e810e223ca8040fa1741b2
3
+ size 4997309072
model-00008-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4eed157dfc30847f981b2de60ce060e3d51e99ecbc9ea35e068bc81930b505e
3
+ size 4997874256
model-00009-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91d12323332d765297828936a0428a09a96bdd84883f660d6330ba5e0fb10208
3
+ size 4997874344
model-00010-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d48d2f93012158c0128f4eda62cacf98aa6d029ee7e8573fa0038ca0fe1127a
3
+ size 4997874352
model-00011-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:526df14faaca753a08ccd60a09595703cc981cf1a9a4e5530316e17afb16eccd
3
+ size 4997874352
model-00012-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f7790217f3982bea546e360a0e7ed9c02daefc4664f69071c5d24648ad070f9
3
+ size 4997309032
model-00013-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c0d23050eee027135897f959b721e9d88e743f90c7c1716e5dd487d6b68a897
3
+ size 4753984864
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff