Hugging Face's logo

kaizen9
/
qspi30_7.1

Safetensors
qwen3_moe
Model card Files Community
kaizen9 commited on
Commit
277b252
·
verified ·
1 Parent(s): 0a27e42

Upload folder using huggingface_hub

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
+ "eos_token_id": 151643,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 6144,
15
+ "max_position_embeddings": 32768,
16
+ "max_window_layers": 48,
17
+ "mlp_only_layers": [],
18
+ "model_type": "qwen3_moe",
19
+ "moe_intermediate_size": 768,
20
+ "norm_topk_prob": true,
21
+ "num_attention_heads": 32,
22
+ "num_experts": 128,
23
+ "num_experts_per_tok": 8,
24
+ "num_hidden_layers": 48,
25
+ "num_key_value_heads": 4,
26
+ "output_router_logits": false,
27
+ "rms_norm_eps": 1e-06,
28
+ "rope_scaling": null,
29
+ "rope_theta": 1000000.0,
30
+ "router_aux_loss_coef": 0.001,
31
+ "sliding_window": null,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.51.3",
35
+ "use_cache": true,
36
+ "use_sliding_window": false,
37
+ "vocab_size": 151936
38
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.51.3"
6
+ }
model-00001-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2418be72164e3e014f3d0d4f6ea5eb96f17af702d1731fe7be3139127a5b7cc
3
+ size 4997184968
model-00002-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8202d2d50dcf6c39b11cab1227f3cfb496a75e5efcdc45946fd9af71f14e20bf
3
+ size 4997741608
model-00003-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a83142e6746018d8275418bc9c7336234f848a37ca811bc5ae72e0a270fbdb44
3
+ size 4997742208
model-00004-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90f7febc9d0cb0d28bb8bebc4f29e99a964d182313db19953d9ecbd1db68f8c9
3
+ size 4997743184
model-00005-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0013ccf6b831a4f757828de4736ccee5e6ffa913278ed683977dc60dff88eff5
3
+ size 4997743184
model-00006-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a74d6c0f1ce2a583b064b7620db214bc4752de2468d9c19f2bae288f4e9e68c9
3
+ size 4997743184
model-00007-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e206fde452fa906be4784f1d27dff3d001b7d648649b8f997f2e15d42869add4
3
+ size 4997743184
model-00008-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4fae419dc8437737ae46e3a55ec440c1bf44c798e03634fe10ff6a6c008c8be
3
+ size 4997743184
model-00009-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78bf78e507c6dd1ef5d6b40020fb8afd0a11f64ea75acbb4f4ddad88653aeb11
3
+ size 4997743184
model-00010-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a7ca7a40300f0d5c9978eac2ddaefc299a1306c3ac889b2b2c67c428f58a94b
3
+ size 4997743184
model-00011-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:059f42b180b09752a43f6ee1ef7b734b041a99221ac60da97c071efcaf302b42
3
+ size 4997743184
model-00012-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa54bb852ed90227625e9eeafd640ceaa0fb257588b376afa50b3d17414d02cb
3
+ size 4997743184
model-00013-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:075fb112c24a24002f4971e4f66e2a9ff77a335de0faef921135cbd4bd92bc4e
3
+ size 1094220288
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff