Hugging Face's logo

idoru
/
qwen3-0.6b-onnx-interp

Text Generation
Transformers.js
ONNX
qwen3
webgpu
interpretability
conversational
Model card Files
xet
 Community
idoru commited on
Commit
c14fd33
·
verified ·
1 Parent(s): 414a65b

Add ONNX export with attentions/hidden states

Browse files
Files changed (3) hide show
  1. config.json +1 -1
  2. onnx/model_fp16.onnx +3 -0
  3. onnx/model_q4f16.onnx +2 -2
config.json CHANGED
@@ -5,7 +5,7 @@
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 151643,
8
- "dtype": "float32",
9
  "eos_token_id": 151645,
10
  "head_dim": 128,
11
  "hidden_act": "silu",
 
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 151643,
8
+ "dtype": "float16",
9
  "eos_token_id": 151645,
10
  "head_dim": 128,
11
  "hidden_act": "silu",
onnx/model_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0277eb51bda1de92e54f7998af66873a4f9ce573f30a14bcd1fc73be23a6d9c4
3
+ size 1504634868
onnx/model_q4f16.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3349b9055dd9c27dd0f361febe6f1b8d1bf694dd848d0d6f997bfa8b7dd59709
3
- size 1780575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0277eb51bda1de92e54f7998af66873a4f9ce573f30a14bcd1fc73be23a6d9c4
3
+ size 1504634868