Opt-AI commited on
Commit
0cd7cf6
·
verified ·
1 Parent(s): a6f1811

Add files using upload-large-folder tool

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2560,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 9728,
14
+ "max_position_embeddings": 40960,
15
+ "max_window_layers": 36,
16
+ "model_type": "qwen3",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 36,
19
+ "num_key_value_heads": 8,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": true,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.51.0",
27
+ "use_cache": true,
28
+ "use_sliding_window": false,
29
+ "vocab_size": 151936
30
+ }
genie_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dialog": {
3
+ "version": 1,
4
+ "type": "basic",
5
+ "context": {
6
+ "version": 1,
7
+ "size": 4096,
8
+ "n-vocab": 151936,
9
+ "bos-token": 151643,
10
+ "eos-token": 151645
11
+ },
12
+ "sampler": {
13
+ "version": 1,
14
+ "seed": 42,
15
+ "temp": 0.8,
16
+ "top-k": 40,
17
+ "top-p": 0.95
18
+ },
19
+ "tokenizer": {
20
+ "version": 1,
21
+ "path": "tokenizer.json"
22
+ },
23
+ "engine": {
24
+ "version": 1,
25
+ "n-threads": 3,
26
+ "backend": {
27
+ "version": 1,
28
+ "type": "QnnHtp",
29
+ "QnnHtp": {
30
+ "version": 1,
31
+ "use-mmap": true,
32
+ "spill-fill-bufsize": 0,
33
+ "mmap-budget": 0,
34
+ "poll": true,
35
+ "cpu-mask": "0xe0",
36
+ "kv-dim": 128,
37
+ "pos-id-dim": 64,
38
+ "allow-async-init": false,
39
+ "rope-theta": 1000000
40
+ },
41
+ "extensions": "htp_backend_ext_config.json"
42
+ },
43
+ "model": {
44
+ "version": 1,
45
+ "type": "binary",
46
+ "binary": {
47
+ "version": 1,
48
+ "ctx-bins": [
49
+ "qwen3_4b_part_1_of_4.bin",
50
+ "qwen3_4b_part_2_of_4.bin",
51
+ "qwen3_4b_part_3_of_4.bin",
52
+ "qwen3_4b_part_4_of_4.bin"
53
+ ]
54
+ }
55
+ }
56
+ }
57
+ }
58
+ }
htp_backend_ext_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"devices": [{"soc_model": 87, "dsp_arch": "v81", "cores": [{"core_id": 0, "perf_profile": "burst", "rpc_control_latency": 100}]}], "memory": {"mem_type": "shared_buffer"}, "context": {"weight_sharing_enabled": true}}
metadata.yaml ADDED
@@ -0,0 +1,3223 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ components:
2
+ ar128_cl4096_1_of_4:
3
+ inputs:
4
+ input_ids:
5
+ shape:
6
+ - 1
7
+ - 128
8
+ dtype: int32
9
+ outputs:
10
+ /model/model/embed_tokens/Gather_output_0:
11
+ shape:
12
+ - 1
13
+ - 128
14
+ - 2560
15
+ dtype: uint16
16
+ quantization_parameters:
17
+ scale: 7.197370679789425e-06
18
+ offset: -30800
19
+ ar128_cl4096_2_of_4:
20
+ inputs:
21
+ /model/model/embed_tokens/Gather_output_0:
22
+ shape:
23
+ - 1
24
+ - 128
25
+ - 2560
26
+ dtype: uint16
27
+ quantization_parameters:
28
+ scale: 7.197370679789425e-06
29
+ offset: -30800
30
+ attention_mask:
31
+ shape:
32
+ - 1
33
+ - 1
34
+ - 128
35
+ - 4096
36
+ dtype: uint16
37
+ quantization_parameters:
38
+ scale: 0.0015259021896696422
39
+ offset: -65535
40
+ position_ids_cos:
41
+ shape:
42
+ - 1
43
+ - 1
44
+ - 128
45
+ - 64
46
+ dtype: uint16
47
+ quantization_parameters:
48
+ scale: 3.0518043793392844e-05
49
+ offset: -32768
50
+ position_ids_sin:
51
+ shape:
52
+ - 1
53
+ - 1
54
+ - 128
55
+ - 64
56
+ dtype: uint16
57
+ quantization_parameters:
58
+ scale: 3.0518043793392844e-05
59
+ offset: -32768
60
+ past_key_0_in:
61
+ shape:
62
+ - 8
63
+ - 1
64
+ - 128
65
+ - 3968
66
+ dtype: uint8
67
+ quantization_parameters:
68
+ scale: 2.345790112112451
69
+ offset: -128
70
+ past_value_0_in:
71
+ shape:
72
+ - 8
73
+ - 1
74
+ - 3968
75
+ - 128
76
+ dtype: uint8
77
+ quantization_parameters:
78
+ scale: 0.004396342855738843
79
+ offset: -128
80
+ past_key_1_in:
81
+ shape:
82
+ - 8
83
+ - 1
84
+ - 128
85
+ - 3968
86
+ dtype: uint8
87
+ quantization_parameters:
88
+ scale: 0.4745758537232406
89
+ offset: -128
90
+ past_value_1_in:
91
+ shape:
92
+ - 8
93
+ - 1
94
+ - 3968
95
+ - 128
96
+ dtype: uint8
97
+ quantization_parameters:
98
+ scale: 0.005273671820759773
99
+ offset: -128
100
+ past_key_2_in:
101
+ shape:
102
+ - 8
103
+ - 1
104
+ - 128
105
+ - 3968
106
+ dtype: uint8
107
+ quantization_parameters:
108
+ scale: 0.20883603394031525
109
+ offset: -128
110
+ past_value_2_in:
111
+ shape:
112
+ - 8
113
+ - 1
114
+ - 3968
115
+ - 128
116
+ dtype: uint8
117
+ quantization_parameters:
118
+ scale: 0.0066236164420843124
119
+ offset: -128
120
+ past_key_3_in:
121
+ shape:
122
+ - 8
123
+ - 1
124
+ - 128
125
+ - 3968
126
+ dtype: uint8
127
+ quantization_parameters:
128
+ scale: 0.20998451113700867
129
+ offset: -128
130
+ past_value_3_in:
131
+ shape:
132
+ - 8
133
+ - 1
134
+ - 3968
135
+ - 128
136
+ dtype: uint8
137
+ quantization_parameters:
138
+ scale: 0.009058302268385887
139
+ offset: -128
140
+ past_key_4_in:
141
+ shape:
142
+ - 8
143
+ - 1
144
+ - 128
145
+ - 3968
146
+ dtype: uint8
147
+ quantization_parameters:
148
+ scale: 0.5082661185677596
149
+ offset: -128
150
+ past_value_4_in:
151
+ shape:
152
+ - 8
153
+ - 1
154
+ - 3968
155
+ - 128
156
+ dtype: uint8
157
+ quantization_parameters:
158
+ scale: 0.010039279237389565
159
+ offset: -128
160
+ past_key_5_in:
161
+ shape:
162
+ - 8
163
+ - 1
164
+ - 128
165
+ - 3968
166
+ dtype: uint8
167
+ quantization_parameters:
168
+ scale: 0.8604878703440269
169
+ offset: -128
170
+ past_value_5_in:
171
+ shape:
172
+ - 8
173
+ - 1
174
+ - 3968
175
+ - 128
176
+ dtype: uint8
177
+ quantization_parameters:
178
+ scale: 0.011779437772929668
179
+ offset: -128
180
+ past_key_6_in:
181
+ shape:
182
+ - 8
183
+ - 1
184
+ - 128
185
+ - 3968
186
+ dtype: uint8
187
+ quantization_parameters:
188
+ scale: 0.32763143224040353
189
+ offset: -128
190
+ past_value_6_in:
191
+ shape:
192
+ - 8
193
+ - 1
194
+ - 3968
195
+ - 128
196
+ dtype: uint8
197
+ quantization_parameters:
198
+ scale: 0.015452229417860508
199
+ offset: -128
200
+ past_key_7_in:
201
+ shape:
202
+ - 8
203
+ - 1
204
+ - 128
205
+ - 3968
206
+ dtype: uint8
207
+ quantization_parameters:
208
+ scale: 0.2633135938268947
209
+ offset: -128
210
+ past_value_7_in:
211
+ shape:
212
+ - 8
213
+ - 1
214
+ - 3968
215
+ - 128
216
+ dtype: uint8
217
+ quantization_parameters:
218
+ scale: 0.023205885663628578
219
+ offset: -128
220
+ past_key_8_in:
221
+ shape:
222
+ - 8
223
+ - 1
224
+ - 128
225
+ - 3968
226
+ dtype: uint8
227
+ quantization_parameters:
228
+ scale: 0.4432932138442993
229
+ offset: -128
230
+ past_value_8_in:
231
+ shape:
232
+ - 8
233
+ - 1
234
+ - 3968
235
+ - 128
236
+ dtype: uint8
237
+ quantization_parameters:
238
+ scale: 0.025590643286705017
239
+ offset: -128
240
+ past_key_9_in:
241
+ shape:
242
+ - 8
243
+ - 1
244
+ - 128
245
+ - 3968
246
+ dtype: uint8
247
+ quantization_parameters:
248
+ scale: 0.198994809248316
249
+ offset: -128
250
+ past_value_9_in:
251
+ shape:
252
+ - 8
253
+ - 1
254
+ - 3968
255
+ - 128
256
+ dtype: uint8
257
+ quantization_parameters:
258
+ scale: 0.02567124180495739
259
+ offset: -128
260
+ past_key_10_in:
261
+ shape:
262
+ - 8
263
+ - 1
264
+ - 128
265
+ - 3968
266
+ dtype: uint8
267
+ quantization_parameters:
268
+ scale: 0.3400344252586365
269
+ offset: -128
270
+ past_value_10_in:
271
+ shape:
272
+ - 8
273
+ - 1
274
+ - 3968
275
+ - 128
276
+ dtype: uint8
277
+ quantization_parameters:
278
+ scale: 0.047514863312244415
279
+ offset: -128
280
+ past_key_11_in:
281
+ shape:
282
+ - 8
283
+ - 1
284
+ - 128
285
+ - 3968
286
+ dtype: uint8
287
+ quantization_parameters:
288
+ scale: 0.30140187421182946
289
+ offset: -128
290
+ past_value_11_in:
291
+ shape:
292
+ - 8
293
+ - 1
294
+ - 3968
295
+ - 128
296
+ dtype: uint8
297
+ quantization_parameters:
298
+ scale: 0.029060301818246915
299
+ offset: -128
300
+ outputs:
301
+ /model/model/layers.11/Add_1_output_0:
302
+ shape:
303
+ - 1
304
+ - 128
305
+ - 2560
306
+ dtype: uint16
307
+ quantization_parameters:
308
+ scale: 0.2177089144874876
309
+ offset: -14531
310
+ past_key_0_out:
311
+ shape:
312
+ - 8
313
+ - 1
314
+ - 128
315
+ - 128
316
+ dtype: uint8
317
+ quantization_parameters:
318
+ scale: 2.345790112112451
319
+ offset: -128
320
+ past_value_0_out:
321
+ shape:
322
+ - 8
323
+ - 1
324
+ - 128
325
+ - 128
326
+ dtype: uint8
327
+ quantization_parameters:
328
+ scale: 0.004396342855738843
329
+ offset: -128
330
+ past_key_1_out:
331
+ shape:
332
+ - 8
333
+ - 1
334
+ - 128
335
+ - 128
336
+ dtype: uint8
337
+ quantization_parameters:
338
+ scale: 0.4745758537232406
339
+ offset: -128
340
+ past_value_1_out:
341
+ shape:
342
+ - 8
343
+ - 1
344
+ - 128
345
+ - 128
346
+ dtype: uint8
347
+ quantization_parameters:
348
+ scale: 0.005273671820759773
349
+ offset: -128
350
+ past_key_2_out:
351
+ shape:
352
+ - 8
353
+ - 1
354
+ - 128
355
+ - 128
356
+ dtype: uint8
357
+ quantization_parameters:
358
+ scale: 0.20883603394031525
359
+ offset: -128
360
+ past_value_2_out:
361
+ shape:
362
+ - 8
363
+ - 1
364
+ - 128
365
+ - 128
366
+ dtype: uint8
367
+ quantization_parameters:
368
+ scale: 0.0066236164420843124
369
+ offset: -128
370
+ past_key_3_out:
371
+ shape:
372
+ - 8
373
+ - 1
374
+ - 128
375
+ - 128
376
+ dtype: uint8
377
+ quantization_parameters:
378
+ scale: 0.20998451113700867
379
+ offset: -128
380
+ past_value_3_out:
381
+ shape:
382
+ - 8
383
+ - 1
384
+ - 128
385
+ - 128
386
+ dtype: uint8
387
+ quantization_parameters:
388
+ scale: 0.009058302268385887
389
+ offset: -128
390
+ past_key_4_out:
391
+ shape:
392
+ - 8
393
+ - 1
394
+ - 128
395
+ - 128
396
+ dtype: uint8
397
+ quantization_parameters:
398
+ scale: 0.5082661185677596
399
+ offset: -128
400
+ past_value_4_out:
401
+ shape:
402
+ - 8
403
+ - 1
404
+ - 128
405
+ - 128
406
+ dtype: uint8
407
+ quantization_parameters:
408
+ scale: 0.010039279237389565
409
+ offset: -128
410
+ past_key_5_out:
411
+ shape:
412
+ - 8
413
+ - 1
414
+ - 128
415
+ - 128
416
+ dtype: uint8
417
+ quantization_parameters:
418
+ scale: 0.8604878703440269
419
+ offset: -128
420
+ past_value_5_out:
421
+ shape:
422
+ - 8
423
+ - 1
424
+ - 128
425
+ - 128
426
+ dtype: uint8
427
+ quantization_parameters:
428
+ scale: 0.011779437772929668
429
+ offset: -128
430
+ past_key_6_out:
431
+ shape:
432
+ - 8
433
+ - 1
434
+ - 128
435
+ - 128
436
+ dtype: uint8
437
+ quantization_parameters:
438
+ scale: 0.32763143224040353
439
+ offset: -128
440
+ past_value_6_out:
441
+ shape:
442
+ - 8
443
+ - 1
444
+ - 128
445
+ - 128
446
+ dtype: uint8
447
+ quantization_parameters:
448
+ scale: 0.015452229417860508
449
+ offset: -128
450
+ past_key_7_out:
451
+ shape:
452
+ - 8
453
+ - 1
454
+ - 128
455
+ - 128
456
+ dtype: uint8
457
+ quantization_parameters:
458
+ scale: 0.2633135938268947
459
+ offset: -128
460
+ past_value_7_out:
461
+ shape:
462
+ - 8
463
+ - 1
464
+ - 128
465
+ - 128
466
+ dtype: uint8
467
+ quantization_parameters:
468
+ scale: 0.023205885663628578
469
+ offset: -128
470
+ past_key_8_out:
471
+ shape:
472
+ - 8
473
+ - 1
474
+ - 128
475
+ - 128
476
+ dtype: uint8
477
+ quantization_parameters:
478
+ scale: 0.4432932138442993
479
+ offset: -128
480
+ past_value_8_out:
481
+ shape:
482
+ - 8
483
+ - 1
484
+ - 128
485
+ - 128
486
+ dtype: uint8
487
+ quantization_parameters:
488
+ scale: 0.025590643286705017
489
+ offset: -128
490
+ past_key_9_out:
491
+ shape:
492
+ - 8
493
+ - 1
494
+ - 128
495
+ - 128
496
+ dtype: uint8
497
+ quantization_parameters:
498
+ scale: 0.198994809248316
499
+ offset: -128
500
+ past_value_9_out:
501
+ shape:
502
+ - 8
503
+ - 1
504
+ - 128
505
+ - 128
506
+ dtype: uint8
507
+ quantization_parameters:
508
+ scale: 0.02567124180495739
509
+ offset: -128
510
+ past_key_10_out:
511
+ shape:
512
+ - 8
513
+ - 1
514
+ - 128
515
+ - 128
516
+ dtype: uint8
517
+ quantization_parameters:
518
+ scale: 0.3400344252586365
519
+ offset: -128
520
+ past_value_10_out:
521
+ shape:
522
+ - 8
523
+ - 1
524
+ - 128
525
+ - 128
526
+ dtype: uint8
527
+ quantization_parameters:
528
+ scale: 0.047514863312244415
529
+ offset: -128
530
+ past_key_11_out:
531
+ shape:
532
+ - 8
533
+ - 1
534
+ - 128
535
+ - 128
536
+ dtype: uint8
537
+ quantization_parameters:
538
+ scale: 0.30140187421182946
539
+ offset: -128
540
+ past_value_11_out:
541
+ shape:
542
+ - 8
543
+ - 1
544
+ - 128
545
+ - 128
546
+ dtype: uint8
547
+ quantization_parameters:
548
+ scale: 0.029060301818246915
549
+ offset: -128
550
+ ar128_cl4096_3_of_4:
551
+ inputs:
552
+ /model/model/layers.11/Add_1_output_0:
553
+ shape:
554
+ - 1
555
+ - 128
556
+ - 2560
557
+ dtype: uint16
558
+ quantization_parameters:
559
+ scale: 0.2177089144874876
560
+ offset: -14531
561
+ attention_mask:
562
+ shape:
563
+ - 1
564
+ - 1
565
+ - 128
566
+ - 4096
567
+ dtype: uint16
568
+ quantization_parameters:
569
+ scale: 0.0015259021896696422
570
+ offset: -65535
571
+ position_ids_cos:
572
+ shape:
573
+ - 1
574
+ - 1
575
+ - 128
576
+ - 64
577
+ dtype: uint16
578
+ quantization_parameters:
579
+ scale: 3.0518043793392844e-05
580
+ offset: -32768
581
+ position_ids_sin:
582
+ shape:
583
+ - 1
584
+ - 1
585
+ - 128
586
+ - 64
587
+ dtype: uint16
588
+ quantization_parameters:
589
+ scale: 3.0518043793392844e-05
590
+ offset: -32768
591
+ past_key_12_in:
592
+ shape:
593
+ - 8
594
+ - 1
595
+ - 128
596
+ - 3968
597
+ dtype: uint8
598
+ quantization_parameters:
599
+ scale: 0.2443227916955948
600
+ offset: -128
601
+ past_value_12_in:
602
+ shape:
603
+ - 8
604
+ - 1
605
+ - 3968
606
+ - 128
607
+ dtype: uint8
608
+ quantization_parameters:
609
+ scale: 0.028940375395647183
610
+ offset: -128
611
+ past_key_13_in:
612
+ shape:
613
+ - 8
614
+ - 1
615
+ - 128
616
+ - 3968
617
+ dtype: uint8
618
+ quantization_parameters:
619
+ scale: 0.2185003776249923
620
+ offset: -128
621
+ past_value_13_in:
622
+ shape:
623
+ - 8
624
+ - 1
625
+ - 3968
626
+ - 128
627
+ dtype: uint8
628
+ quantization_parameters:
629
+ scale: 0.17545437812805176
630
+ offset: -128
631
+ past_key_14_in:
632
+ shape:
633
+ - 8
634
+ - 1
635
+ - 128
636
+ - 3968
637
+ dtype: uint8
638
+ quantization_parameters:
639
+ scale: 0.2587217390537262
640
+ offset: -128
641
+ past_value_14_in:
642
+ shape:
643
+ - 8
644
+ - 1
645
+ - 3968
646
+ - 128
647
+ dtype: uint8
648
+ quantization_parameters:
649
+ scale: 0.09416288137435913
650
+ offset: -128
651
+ past_key_15_in:
652
+ shape:
653
+ - 8
654
+ - 1
655
+ - 128
656
+ - 3968
657
+ dtype: uint8
658
+ quantization_parameters:
659
+ scale: 0.18699947867806502
660
+ offset: -128
661
+ past_value_15_in:
662
+ shape:
663
+ - 8
664
+ - 1
665
+ - 3968
666
+ - 128
667
+ dtype: uint8
668
+ quantization_parameters:
669
+ scale: 0.2346538033072404
670
+ offset: -128
671
+ past_key_16_in:
672
+ shape:
673
+ - 8
674
+ - 1
675
+ - 128
676
+ - 3968
677
+ dtype: uint8
678
+ quantization_parameters:
679
+ scale: 0.2061757892370224
680
+ offset: -128
681
+ past_value_16_in:
682
+ shape:
683
+ - 8
684
+ - 1
685
+ - 3968
686
+ - 128
687
+ dtype: uint8
688
+ quantization_parameters:
689
+ scale: 0.19758310092715767
690
+ offset: -128
691
+ past_key_17_in:
692
+ shape:
693
+ - 8
694
+ - 1
695
+ - 128
696
+ - 3968
697
+ dtype: uint8
698
+ quantization_parameters:
699
+ scale: 0.17539973521795799
700
+ offset: -128
701
+ past_value_17_in:
702
+ shape:
703
+ - 8
704
+ - 1
705
+ - 3968
706
+ - 128
707
+ dtype: uint8
708
+ quantization_parameters:
709
+ scale: 0.32720860838890076
710
+ offset: -128
711
+ past_key_18_in:
712
+ shape:
713
+ - 8
714
+ - 1
715
+ - 128
716
+ - 3968
717
+ dtype: uint8
718
+ quantization_parameters:
719
+ scale: 0.19263408690925657
720
+ offset: -128
721
+ past_value_18_in:
722
+ shape:
723
+ - 8
724
+ - 1
725
+ - 3968
726
+ - 128
727
+ dtype: uint8
728
+ quantization_parameters:
729
+ scale: 0.16426491925096887
730
+ offset: -128
731
+ past_key_19_in:
732
+ shape:
733
+ - 8
734
+ - 1
735
+ - 128
736
+ - 3968
737
+ dtype: uint8
738
+ quantization_parameters:
739
+ scale: 0.21870377659797668
740
+ offset: -128
741
+ past_value_19_in:
742
+ shape:
743
+ - 8
744
+ - 1
745
+ - 3968
746
+ - 128
747
+ dtype: uint8
748
+ quantization_parameters:
749
+ scale: 0.06083845153568298
750
+ offset: -128
751
+ past_key_20_in:
752
+ shape:
753
+ - 8
754
+ - 1
755
+ - 128
756
+ - 3968
757
+ dtype: uint8
758
+ quantization_parameters:
759
+ scale: 0.1891358345746994
760
+ offset: -128
761
+ past_value_20_in:
762
+ shape:
763
+ - 8
764
+ - 1
765
+ - 3968
766
+ - 128
767
+ dtype: uint8
768
+ quantization_parameters:
769
+ scale: 0.05266200378537178
770
+ offset: -128
771
+ past_key_21_in:
772
+ shape:
773
+ - 8
774
+ - 1
775
+ - 128
776
+ - 3968
777
+ dtype: uint8
778
+ quantization_parameters:
779
+ scale: 0.19000622606652928
780
+ offset: -128
781
+ past_value_21_in:
782
+ shape:
783
+ - 8
784
+ - 1
785
+ - 3968
786
+ - 128
787
+ dtype: uint8
788
+ quantization_parameters:
789
+ scale: 0.06354268141618864
790
+ offset: -128
791
+ past_key_22_in:
792
+ shape:
793
+ - 8
794
+ - 1
795
+ - 128
796
+ - 3968
797
+ dtype: uint8
798
+ quantization_parameters:
799
+ scale: 0.22853676974773407
800
+ offset: -128
801
+ past_value_22_in:
802
+ shape:
803
+ - 8
804
+ - 1
805
+ - 3968
806
+ - 128
807
+ dtype: uint8
808
+ quantization_parameters:
809
+ scale: 0.19043058156967163
810
+ offset: -128
811
+ past_key_23_in:
812
+ shape:
813
+ - 8
814
+ - 1
815
+ - 128
816
+ - 3968
817
+ dtype: uint8
818
+ quantization_parameters:
819
+ scale: 0.2349507489542323
820
+ offset: -128
821
+ past_value_23_in:
822
+ shape:
823
+ - 8
824
+ - 1
825
+ - 3968
826
+ - 128
827
+ dtype: uint8
828
+ quantization_parameters:
829
+ scale: 0.06769621090626153
830
+ offset: -128
831
+ outputs:
832
+ /model/model/layers.23/Add_1_output_0:
833
+ shape:
834
+ - 1
835
+ - 128
836
+ - 2560
837
+ dtype: uint16
838
+ quantization_parameters:
839
+ scale: 0.22199481461480505
840
+ offset: -14218
841
+ past_key_12_out:
842
+ shape:
843
+ - 8
844
+ - 1
845
+ - 128
846
+ - 128
847
+ dtype: uint8
848
+ quantization_parameters:
849
+ scale: 0.2443227916955948
850
+ offset: -128
851
+ past_value_12_out:
852
+ shape:
853
+ - 8
854
+ - 1
855
+ - 128
856
+ - 128
857
+ dtype: uint8
858
+ quantization_parameters:
859
+ scale: 0.028940375395647183
860
+ offset: -128
861
+ past_key_13_out:
862
+ shape:
863
+ - 8
864
+ - 1
865
+ - 128
866
+ - 128
867
+ dtype: uint8
868
+ quantization_parameters:
869
+ scale: 0.2185003776249923
870
+ offset: -128
871
+ past_value_13_out:
872
+ shape:
873
+ - 8
874
+ - 1
875
+ - 128
876
+ - 128
877
+ dtype: uint8
878
+ quantization_parameters:
879
+ scale: 0.17545437812805176
880
+ offset: -128
881
+ past_key_14_out:
882
+ shape:
883
+ - 8
884
+ - 1
885
+ - 128
886
+ - 128
887
+ dtype: uint8
888
+ quantization_parameters:
889
+ scale: 0.2587217390537262
890
+ offset: -128
891
+ past_value_14_out:
892
+ shape:
893
+ - 8
894
+ - 1
895
+ - 128
896
+ - 128
897
+ dtype: uint8
898
+ quantization_parameters:
899
+ scale: 0.09416288137435913
900
+ offset: -128
901
+ past_key_15_out:
902
+ shape:
903
+ - 8
904
+ - 1
905
+ - 128
906
+ - 128
907
+ dtype: uint8
908
+ quantization_parameters:
909
+ scale: 0.18699947867806502
910
+ offset: -128
911
+ past_value_15_out:
912
+ shape:
913
+ - 8
914
+ - 1
915
+ - 128
916
+ - 128
917
+ dtype: uint8
918
+ quantization_parameters:
919
+ scale: 0.2346538033072404
920
+ offset: -128
921
+ past_key_16_out:
922
+ shape:
923
+ - 8
924
+ - 1
925
+ - 128
926
+ - 128
927
+ dtype: uint8
928
+ quantization_parameters:
929
+ scale: 0.2061757892370224
930
+ offset: -128
931
+ past_value_16_out:
932
+ shape:
933
+ - 8
934
+ - 1
935
+ - 128
936
+ - 128
937
+ dtype: uint8
938
+ quantization_parameters:
939
+ scale: 0.19758310092715767
940
+ offset: -128
941
+ past_key_17_out:
942
+ shape:
943
+ - 8
944
+ - 1
945
+ - 128
946
+ - 128
947
+ dtype: uint8
948
+ quantization_parameters:
949
+ scale: 0.17539973521795799
950
+ offset: -128
951
+ past_value_17_out:
952
+ shape:
953
+ - 8
954
+ - 1
955
+ - 128
956
+ - 128
957
+ dtype: uint8
958
+ quantization_parameters:
959
+ scale: 0.32720860838890076
960
+ offset: -128
961
+ past_key_18_out:
962
+ shape:
963
+ - 8
964
+ - 1
965
+ - 128
966
+ - 128
967
+ dtype: uint8
968
+ quantization_parameters:
969
+ scale: 0.19263408690925657
970
+ offset: -128
971
+ past_value_18_out:
972
+ shape:
973
+ - 8
974
+ - 1
975
+ - 128
976
+ - 128
977
+ dtype: uint8
978
+ quantization_parameters:
979
+ scale: 0.16426491925096887
980
+ offset: -128
981
+ past_key_19_out:
982
+ shape:
983
+ - 8
984
+ - 1
985
+ - 128
986
+ - 128
987
+ dtype: uint8
988
+ quantization_parameters:
989
+ scale: 0.21870377659797668
990
+ offset: -128
991
+ past_value_19_out:
992
+ shape:
993
+ - 8
994
+ - 1
995
+ - 128
996
+ - 128
997
+ dtype: uint8
998
+ quantization_parameters:
999
+ scale: 0.06083845153568298
1000
+ offset: -128
1001
+ past_key_20_out:
1002
+ shape:
1003
+ - 8
1004
+ - 1
1005
+ - 128
1006
+ - 128
1007
+ dtype: uint8
1008
+ quantization_parameters:
1009
+ scale: 0.1891358345746994
1010
+ offset: -128
1011
+ past_value_20_out:
1012
+ shape:
1013
+ - 8
1014
+ - 1
1015
+ - 128
1016
+ - 128
1017
+ dtype: uint8
1018
+ quantization_parameters:
1019
+ scale: 0.05266200378537178
1020
+ offset: -128
1021
+ past_key_21_out:
1022
+ shape:
1023
+ - 8
1024
+ - 1
1025
+ - 128
1026
+ - 128
1027
+ dtype: uint8
1028
+ quantization_parameters:
1029
+ scale: 0.19000622606652928
1030
+ offset: -128
1031
+ past_value_21_out:
1032
+ shape:
1033
+ - 8
1034
+ - 1
1035
+ - 128
1036
+ - 128
1037
+ dtype: uint8
1038
+ quantization_parameters:
1039
+ scale: 0.06354268141618864
1040
+ offset: -128
1041
+ past_key_22_out:
1042
+ shape:
1043
+ - 8
1044
+ - 1
1045
+ - 128
1046
+ - 128
1047
+ dtype: uint8
1048
+ quantization_parameters:
1049
+ scale: 0.22853676974773407
1050
+ offset: -128
1051
+ past_value_22_out:
1052
+ shape:
1053
+ - 8
1054
+ - 1
1055
+ - 128
1056
+ - 128
1057
+ dtype: uint8
1058
+ quantization_parameters:
1059
+ scale: 0.19043058156967163
1060
+ offset: -128
1061
+ past_key_23_out:
1062
+ shape:
1063
+ - 8
1064
+ - 1
1065
+ - 128
1066
+ - 128
1067
+ dtype: uint8
1068
+ quantization_parameters:
1069
+ scale: 0.2349507489542323
1070
+ offset: -128
1071
+ past_value_23_out:
1072
+ shape:
1073
+ - 8
1074
+ - 1
1075
+ - 128
1076
+ - 128
1077
+ dtype: uint8
1078
+ quantization_parameters:
1079
+ scale: 0.06769621090626153
1080
+ offset: -128
1081
+ ar128_cl4096_4_of_4:
1082
+ inputs:
1083
+ /model/model/layers.23/Add_1_output_0:
1084
+ shape:
1085
+ - 1
1086
+ - 128
1087
+ - 2560
1088
+ dtype: uint16
1089
+ quantization_parameters:
1090
+ scale: 0.22199481461480505
1091
+ offset: -14218
1092
+ attention_mask:
1093
+ shape:
1094
+ - 1
1095
+ - 1
1096
+ - 128
1097
+ - 4096
1098
+ dtype: uint16
1099
+ quantization_parameters:
1100
+ scale: 0.0015259021896696422
1101
+ offset: -65535
1102
+ position_ids_cos:
1103
+ shape:
1104
+ - 1
1105
+ - 1
1106
+ - 128
1107
+ - 64
1108
+ dtype: uint16
1109
+ quantization_parameters:
1110
+ scale: 3.0518043793392844e-05
1111
+ offset: -32768
1112
+ position_ids_sin:
1113
+ shape:
1114
+ - 1
1115
+ - 1
1116
+ - 128
1117
+ - 64
1118
+ dtype: uint16
1119
+ quantization_parameters:
1120
+ scale: 3.0518043793392844e-05
1121
+ offset: -32768
1122
+ past_key_24_in:
1123
+ shape:
1124
+ - 8
1125
+ - 1
1126
+ - 128
1127
+ - 3968
1128
+ dtype: uint8
1129
+ quantization_parameters:
1130
+ scale: 0.2168474873219888
1131
+ offset: -128
1132
+ past_value_24_in:
1133
+ shape:
1134
+ - 8
1135
+ - 1
1136
+ - 3968
1137
+ - 128
1138
+ dtype: uint8
1139
+ quantization_parameters:
1140
+ scale: 0.0993499606847763
1141
+ offset: -128
1142
+ past_key_25_in:
1143
+ shape:
1144
+ - 8
1145
+ - 1
1146
+ - 128
1147
+ - 3968
1148
+ dtype: uint8
1149
+ quantization_parameters:
1150
+ scale: 0.16338758170604706
1151
+ offset: -128
1152
+ past_value_25_in:
1153
+ shape:
1154
+ - 8
1155
+ - 1
1156
+ - 3968
1157
+ - 128
1158
+ dtype: uint8
1159
+ quantization_parameters:
1160
+ scale: 0.08785130083560944
1161
+ offset: -128
1162
+ past_key_26_in:
1163
+ shape:
1164
+ - 8
1165
+ - 1
1166
+ - 128
1167
+ - 3968
1168
+ dtype: uint8
1169
+ quantization_parameters:
1170
+ scale: 0.17082346975803375
1171
+ offset: -128
1172
+ past_value_26_in:
1173
+ shape:
1174
+ - 8
1175
+ - 1
1176
+ - 3968
1177
+ - 128
1178
+ dtype: uint8
1179
+ quantization_parameters:
1180
+ scale: 0.09179645448219119
1181
+ offset: -128
1182
+ past_key_27_in:
1183
+ shape:
1184
+ - 8
1185
+ - 1
1186
+ - 128
1187
+ - 3968
1188
+ dtype: uint8
1189
+ quantization_parameters:
1190
+ scale: 0.15799155831336975
1191
+ offset: -128
1192
+ past_value_27_in:
1193
+ shape:
1194
+ - 8
1195
+ - 1
1196
+ - 3968
1197
+ - 128
1198
+ dtype: uint8
1199
+ quantization_parameters:
1200
+ scale: 0.11564768105745316
1201
+ offset: -128
1202
+ past_key_28_in:
1203
+ shape:
1204
+ - 8
1205
+ - 1
1206
+ - 128
1207
+ - 3968
1208
+ dtype: uint8
1209
+ quantization_parameters:
1210
+ scale: 0.16321668850155327
1211
+ offset: -128
1212
+ past_value_28_in:
1213
+ shape:
1214
+ - 8
1215
+ - 1
1216
+ - 3968
1217
+ - 128
1218
+ dtype: uint8
1219
+ quantization_parameters:
1220
+ scale: 0.12118262193334384
1221
+ offset: -128
1222
+ past_key_29_in:
1223
+ shape:
1224
+ - 8
1225
+ - 1
1226
+ - 128
1227
+ - 3968
1228
+ dtype: uint8
1229
+ quantization_parameters:
1230
+ scale: 0.181901752948761
1231
+ offset: -128
1232
+ past_value_29_in:
1233
+ shape:
1234
+ - 8
1235
+ - 1
1236
+ - 3968
1237
+ - 128
1238
+ dtype: uint8
1239
+ quantization_parameters:
1240
+ scale: 0.35103084534171997
1241
+ offset: -128
1242
+ past_key_30_in:
1243
+ shape:
1244
+ - 8
1245
+ - 1
1246
+ - 128
1247
+ - 3968
1248
+ dtype: uint8
1249
+ quantization_parameters:
1250
+ scale: 0.18615905940532684
1251
+ offset: -128
1252
+ past_value_30_in:
1253
+ shape:
1254
+ - 8
1255
+ - 1
1256
+ - 3968
1257
+ - 128
1258
+ dtype: uint8
1259
+ quantization_parameters:
1260
+ scale: 0.29017698764801025
1261
+ offset: -128
1262
+ past_key_31_in:
1263
+ shape:
1264
+ - 8
1265
+ - 1
1266
+ - 128
1267
+ - 3968
1268
+ dtype: uint8
1269
+ quantization_parameters:
1270
+ scale: 0.19037732481956482
1271
+ offset: -128
1272
+ past_value_31_in:
1273
+ shape:
1274
+ - 8
1275
+ - 1
1276
+ - 3968
1277
+ - 128
1278
+ dtype: uint8
1279
+ quantization_parameters:
1280
+ scale: 0.3625663096510519
1281
+ offset: -128
1282
+ past_key_32_in:
1283
+ shape:
1284
+ - 8
1285
+ - 1
1286
+ - 128
1287
+ - 3968
1288
+ dtype: uint8
1289
+ quantization_parameters:
1290
+ scale: 0.15537120789054812
1291
+ offset: -128
1292
+ past_value_32_in:
1293
+ shape:
1294
+ - 8
1295
+ - 1
1296
+ - 3968
1297
+ - 128
1298
+ dtype: uint8
1299
+ quantization_parameters:
1300
+ scale: 0.45803920115072894
1301
+ offset: -128
1302
+ past_key_33_in:
1303
+ shape:
1304
+ - 8
1305
+ - 1
1306
+ - 128
1307
+ - 3968
1308
+ dtype: uint8
1309
+ quantization_parameters:
1310
+ scale: 0.17338245121512827
1311
+ offset: -128
1312
+ past_value_33_in:
1313
+ shape:
1314
+ - 8
1315
+ - 1
1316
+ - 3968
1317
+ - 128
1318
+ dtype: uint8
1319
+ quantization_parameters:
1320
+ scale: 0.9015522754098487
1321
+ offset: -128
1322
+ past_key_34_in:
1323
+ shape:
1324
+ - 8
1325
+ - 1
1326
+ - 128
1327
+ - 3968
1328
+ dtype: uint8
1329
+ quantization_parameters:
1330
+ scale: 0.17443639039993286
1331
+ offset: -128
1332
+ past_value_34_in:
1333
+ shape:
1334
+ - 8
1335
+ - 1
1336
+ - 3968
1337
+ - 128
1338
+ dtype: uint8
1339
+ quantization_parameters:
1340
+ scale: 0.8790855407714844
1341
+ offset: -128
1342
+ past_key_35_in:
1343
+ shape:
1344
+ - 8
1345
+ - 1
1346
+ - 128
1347
+ - 3968
1348
+ dtype: uint8
1349
+ quantization_parameters:
1350
+ scale: 0.35408836603164673
1351
+ offset: -128
1352
+ past_value_35_in:
1353
+ shape:
1354
+ - 8
1355
+ - 1
1356
+ - 3968
1357
+ - 128
1358
+ dtype: uint8
1359
+ quantization_parameters:
1360
+ scale: 0.470033198595047
1361
+ offset: -128
1362
+ outputs:
1363
+ logits:
1364
+ shape:
1365
+ - 1
1366
+ - 128
1367
+ - 151936
1368
+ dtype: uint16
1369
+ quantization_parameters:
1370
+ scale: 0.0013899723052105387
1371
+ offset: -26872
1372
+ past_key_24_out:
1373
+ shape:
1374
+ - 8
1375
+ - 1
1376
+ - 128
1377
+ - 128
1378
+ dtype: uint8
1379
+ quantization_parameters:
1380
+ scale: 0.2168474873219888
1381
+ offset: -128
1382
+ past_value_24_out:
1383
+ shape:
1384
+ - 8
1385
+ - 1
1386
+ - 128
1387
+ - 128
1388
+ dtype: uint8
1389
+ quantization_parameters:
1390
+ scale: 0.0993499606847763
1391
+ offset: -128
1392
+ past_key_25_out:
1393
+ shape:
1394
+ - 8
1395
+ - 1
1396
+ - 128
1397
+ - 128
1398
+ dtype: uint8
1399
+ quantization_parameters:
1400
+ scale: 0.16338758170604706
1401
+ offset: -128
1402
+ past_value_25_out:
1403
+ shape:
1404
+ - 8
1405
+ - 1
1406
+ - 128
1407
+ - 128
1408
+ dtype: uint8
1409
+ quantization_parameters:
1410
+ scale: 0.08785130083560944
1411
+ offset: -128
1412
+ past_key_26_out:
1413
+ shape:
1414
+ - 8
1415
+ - 1
1416
+ - 128
1417
+ - 128
1418
+ dtype: uint8
1419
+ quantization_parameters:
1420
+ scale: 0.17082346975803375
1421
+ offset: -128
1422
+ past_value_26_out:
1423
+ shape:
1424
+ - 8
1425
+ - 1
1426
+ - 128
1427
+ - 128
1428
+ dtype: uint8
1429
+ quantization_parameters:
1430
+ scale: 0.09179645448219119
1431
+ offset: -128
1432
+ past_key_27_out:
1433
+ shape:
1434
+ - 8
1435
+ - 1
1436
+ - 128
1437
+ - 128
1438
+ dtype: uint8
1439
+ quantization_parameters:
1440
+ scale: 0.15799155831336975
1441
+ offset: -128
1442
+ past_value_27_out:
1443
+ shape:
1444
+ - 8
1445
+ - 1
1446
+ - 128
1447
+ - 128
1448
+ dtype: uint8
1449
+ quantization_parameters:
1450
+ scale: 0.11564768105745316
1451
+ offset: -128
1452
+ past_key_28_out:
1453
+ shape:
1454
+ - 8
1455
+ - 1
1456
+ - 128
1457
+ - 128
1458
+ dtype: uint8
1459
+ quantization_parameters:
1460
+ scale: 0.16321668850155327
1461
+ offset: -128
1462
+ past_value_28_out:
1463
+ shape:
1464
+ - 8
1465
+ - 1
1466
+ - 128
1467
+ - 128
1468
+ dtype: uint8
1469
+ quantization_parameters:
1470
+ scale: 0.12118262193334384
1471
+ offset: -128
1472
+ past_key_29_out:
1473
+ shape:
1474
+ - 8
1475
+ - 1
1476
+ - 128
1477
+ - 128
1478
+ dtype: uint8
1479
+ quantization_parameters:
1480
+ scale: 0.181901752948761
1481
+ offset: -128
1482
+ past_value_29_out:
1483
+ shape:
1484
+ - 8
1485
+ - 1
1486
+ - 128
1487
+ - 128
1488
+ dtype: uint8
1489
+ quantization_parameters:
1490
+ scale: 0.35103084534171997
1491
+ offset: -128
1492
+ past_key_30_out:
1493
+ shape:
1494
+ - 8
1495
+ - 1
1496
+ - 128
1497
+ - 128
1498
+ dtype: uint8
1499
+ quantization_parameters:
1500
+ scale: 0.18615905940532684
1501
+ offset: -128
1502
+ past_value_30_out:
1503
+ shape:
1504
+ - 8
1505
+ - 1
1506
+ - 128
1507
+ - 128
1508
+ dtype: uint8
1509
+ quantization_parameters:
1510
+ scale: 0.29017698764801025
1511
+ offset: -128
1512
+ past_key_31_out:
1513
+ shape:
1514
+ - 8
1515
+ - 1
1516
+ - 128
1517
+ - 128
1518
+ dtype: uint8
1519
+ quantization_parameters:
1520
+ scale: 0.19037732481956482
1521
+ offset: -128
1522
+ past_value_31_out:
1523
+ shape:
1524
+ - 8
1525
+ - 1
1526
+ - 128
1527
+ - 128
1528
+ dtype: uint8
1529
+ quantization_parameters:
1530
+ scale: 0.3625663096510519
1531
+ offset: -128
1532
+ past_key_32_out:
1533
+ shape:
1534
+ - 8
1535
+ - 1
1536
+ - 128
1537
+ - 128
1538
+ dtype: uint8
1539
+ quantization_parameters:
1540
+ scale: 0.15537120789054812
1541
+ offset: -128
1542
+ past_value_32_out:
1543
+ shape:
1544
+ - 8
1545
+ - 1
1546
+ - 128
1547
+ - 128
1548
+ dtype: uint8
1549
+ quantization_parameters:
1550
+ scale: 0.45803920115072894
1551
+ offset: -128
1552
+ past_key_33_out:
1553
+ shape:
1554
+ - 8
1555
+ - 1
1556
+ - 128
1557
+ - 128
1558
+ dtype: uint8
1559
+ quantization_parameters:
1560
+ scale: 0.17338245121512827
1561
+ offset: -128
1562
+ past_value_33_out:
1563
+ shape:
1564
+ - 8
1565
+ - 1
1566
+ - 128
1567
+ - 128
1568
+ dtype: uint8
1569
+ quantization_parameters:
1570
+ scale: 0.9015522754098487
1571
+ offset: -128
1572
+ past_key_34_out:
1573
+ shape:
1574
+ - 8
1575
+ - 1
1576
+ - 128
1577
+ - 128
1578
+ dtype: uint8
1579
+ quantization_parameters:
1580
+ scale: 0.17443639039993286
1581
+ offset: -128
1582
+ past_value_34_out:
1583
+ shape:
1584
+ - 8
1585
+ - 1
1586
+ - 128
1587
+ - 128
1588
+ dtype: uint8
1589
+ quantization_parameters:
1590
+ scale: 0.8790855407714844
1591
+ offset: -128
1592
+ past_key_35_out:
1593
+ shape:
1594
+ - 8
1595
+ - 1
1596
+ - 128
1597
+ - 128
1598
+ dtype: uint8
1599
+ quantization_parameters:
1600
+ scale: 0.35408836603164673
1601
+ offset: -128
1602
+ past_value_35_out:
1603
+ shape:
1604
+ - 8
1605
+ - 1
1606
+ - 128
1607
+ - 128
1608
+ dtype: uint8
1609
+ quantization_parameters:
1610
+ scale: 0.470033198595047
1611
+ offset: -128
1612
+ ar1_cl4096_1_of_4:
1613
+ inputs:
1614
+ input_ids:
1615
+ shape:
1616
+ - 1
1617
+ - 1
1618
+ dtype: int32
1619
+ outputs:
1620
+ /model/model/embed_tokens/Gather_output_0:
1621
+ shape:
1622
+ - 1
1623
+ - 1
1624
+ - 2560
1625
+ dtype: uint16
1626
+ quantization_parameters:
1627
+ scale: 7.197370679789425e-06
1628
+ offset: -30800
1629
+ ar1_cl4096_2_of_4:
1630
+ inputs:
1631
+ /model/model/embed_tokens/Gather_output_0:
1632
+ shape:
1633
+ - 1
1634
+ - 1
1635
+ - 2560
1636
+ dtype: uint16
1637
+ quantization_parameters:
1638
+ scale: 7.197370679789425e-06
1639
+ offset: -30800
1640
+ attention_mask:
1641
+ shape:
1642
+ - 1
1643
+ - 1
1644
+ - 1
1645
+ - 4096
1646
+ dtype: uint16
1647
+ quantization_parameters:
1648
+ scale: 0.0015259021896696422
1649
+ offset: -65535
1650
+ position_ids_cos:
1651
+ shape:
1652
+ - 1
1653
+ - 1
1654
+ - 1
1655
+ - 64
1656
+ dtype: uint16
1657
+ quantization_parameters:
1658
+ scale: 3.0518043793392844e-05
1659
+ offset: -32768
1660
+ position_ids_sin:
1661
+ shape:
1662
+ - 1
1663
+ - 1
1664
+ - 1
1665
+ - 64
1666
+ dtype: uint16
1667
+ quantization_parameters:
1668
+ scale: 3.0518043793392844e-05
1669
+ offset: -32768
1670
+ past_key_0_in:
1671
+ shape:
1672
+ - 8
1673
+ - 1
1674
+ - 128
1675
+ - 4095
1676
+ dtype: uint8
1677
+ quantization_parameters:
1678
+ scale: 2.345790112112451
1679
+ offset: -128
1680
+ past_value_0_in:
1681
+ shape:
1682
+ - 8
1683
+ - 1
1684
+ - 4095
1685
+ - 128
1686
+ dtype: uint8
1687
+ quantization_parameters:
1688
+ scale: 0.004396342855738843
1689
+ offset: -128
1690
+ past_key_1_in:
1691
+ shape:
1692
+ - 8
1693
+ - 1
1694
+ - 128
1695
+ - 4095
1696
+ dtype: uint8
1697
+ quantization_parameters:
1698
+ scale: 0.4745758537232406
1699
+ offset: -128
1700
+ past_value_1_in:
1701
+ shape:
1702
+ - 8
1703
+ - 1
1704
+ - 4095
1705
+ - 128
1706
+ dtype: uint8
1707
+ quantization_parameters:
1708
+ scale: 0.005273671820759773
1709
+ offset: -128
1710
+ past_key_2_in:
1711
+ shape:
1712
+ - 8
1713
+ - 1
1714
+ - 128
1715
+ - 4095
1716
+ dtype: uint8
1717
+ quantization_parameters:
1718
+ scale: 0.20883603394031525
1719
+ offset: -128
1720
+ past_value_2_in:
1721
+ shape:
1722
+ - 8
1723
+ - 1
1724
+ - 4095
1725
+ - 128
1726
+ dtype: uint8
1727
+ quantization_parameters:
1728
+ scale: 0.0066236164420843124
1729
+ offset: -128
1730
+ past_key_3_in:
1731
+ shape:
1732
+ - 8
1733
+ - 1
1734
+ - 128
1735
+ - 4095
1736
+ dtype: uint8
1737
+ quantization_parameters:
1738
+ scale: 0.20998451113700867
1739
+ offset: -128
1740
+ past_value_3_in:
1741
+ shape:
1742
+ - 8
1743
+ - 1
1744
+ - 4095
1745
+ - 128
1746
+ dtype: uint8
1747
+ quantization_parameters:
1748
+ scale: 0.009058302268385887
1749
+ offset: -128
1750
+ past_key_4_in:
1751
+ shape:
1752
+ - 8
1753
+ - 1
1754
+ - 128
1755
+ - 4095
1756
+ dtype: uint8
1757
+ quantization_parameters:
1758
+ scale: 0.5082661185677596
1759
+ offset: -128
1760
+ past_value_4_in:
1761
+ shape:
1762
+ - 8
1763
+ - 1
1764
+ - 4095
1765
+ - 128
1766
+ dtype: uint8
1767
+ quantization_parameters:
1768
+ scale: 0.010039279237389565
1769
+ offset: -128
1770
+ past_key_5_in:
1771
+ shape:
1772
+ - 8
1773
+ - 1
1774
+ - 128
1775
+ - 4095
1776
+ dtype: uint8
1777
+ quantization_parameters:
1778
+ scale: 0.8604878703440269
1779
+ offset: -128
1780
+ past_value_5_in:
1781
+ shape:
1782
+ - 8
1783
+ - 1
1784
+ - 4095
1785
+ - 128
1786
+ dtype: uint8
1787
+ quantization_parameters:
1788
+ scale: 0.011779437772929668
1789
+ offset: -128
1790
+ past_key_6_in:
1791
+ shape:
1792
+ - 8
1793
+ - 1
1794
+ - 128
1795
+ - 4095
1796
+ dtype: uint8
1797
+ quantization_parameters:
1798
+ scale: 0.32763143224040353
1799
+ offset: -128
1800
+ past_value_6_in:
1801
+ shape:
1802
+ - 8
1803
+ - 1
1804
+ - 4095
1805
+ - 128
1806
+ dtype: uint8
1807
+ quantization_parameters:
1808
+ scale: 0.015452229417860508
1809
+ offset: -128
1810
+ past_key_7_in:
1811
+ shape:
1812
+ - 8
1813
+ - 1
1814
+ - 128
1815
+ - 4095
1816
+ dtype: uint8
1817
+ quantization_parameters:
1818
+ scale: 0.2633135938268947
1819
+ offset: -128
1820
+ past_value_7_in:
1821
+ shape:
1822
+ - 8
1823
+ - 1
1824
+ - 4095
1825
+ - 128
1826
+ dtype: uint8
1827
+ quantization_parameters:
1828
+ scale: 0.023205885663628578
1829
+ offset: -128
1830
+ past_key_8_in:
1831
+ shape:
1832
+ - 8
1833
+ - 1
1834
+ - 128
1835
+ - 4095
1836
+ dtype: uint8
1837
+ quantization_parameters:
1838
+ scale: 0.4432932138442993
1839
+ offset: -128
1840
+ past_value_8_in:
1841
+ shape:
1842
+ - 8
1843
+ - 1
1844
+ - 4095
1845
+ - 128
1846
+ dtype: uint8
1847
+ quantization_parameters:
1848
+ scale: 0.025590643286705017
1849
+ offset: -128
1850
+ past_key_9_in:
1851
+ shape:
1852
+ - 8
1853
+ - 1
1854
+ - 128
1855
+ - 4095
1856
+ dtype: uint8
1857
+ quantization_parameters:
1858
+ scale: 0.198994809248316
1859
+ offset: -128
1860
+ past_value_9_in:
1861
+ shape:
1862
+ - 8
1863
+ - 1
1864
+ - 4095
1865
+ - 128
1866
+ dtype: uint8
1867
+ quantization_parameters:
1868
+ scale: 0.02567124180495739
1869
+ offset: -128
1870
+ past_key_10_in:
1871
+ shape:
1872
+ - 8
1873
+ - 1
1874
+ - 128
1875
+ - 4095
1876
+ dtype: uint8
1877
+ quantization_parameters:
1878
+ scale: 0.3400344252586365
1879
+ offset: -128
1880
+ past_value_10_in:
1881
+ shape:
1882
+ - 8
1883
+ - 1
1884
+ - 4095
1885
+ - 128
1886
+ dtype: uint8
1887
+ quantization_parameters:
1888
+ scale: 0.047514863312244415
1889
+ offset: -128
1890
+ past_key_11_in:
1891
+ shape:
1892
+ - 8
1893
+ - 1
1894
+ - 128
1895
+ - 4095
1896
+ dtype: uint8
1897
+ quantization_parameters:
1898
+ scale: 0.30140187421182946
1899
+ offset: -128
1900
+ past_value_11_in:
1901
+ shape:
1902
+ - 8
1903
+ - 1
1904
+ - 4095
1905
+ - 128
1906
+ dtype: uint8
1907
+ quantization_parameters:
1908
+ scale: 0.029060301818246915
1909
+ offset: -128
1910
+ outputs:
1911
+ /model/model/layers.11/Add_1_output_0:
1912
+ shape:
1913
+ - 1
1914
+ - 1
1915
+ - 2560
1916
+ dtype: uint16
1917
+ quantization_parameters:
1918
+ scale: 0.2177089144874876
1919
+ offset: -14531
1920
+ past_key_0_out:
1921
+ shape:
1922
+ - 8
1923
+ - 1
1924
+ - 128
1925
+ - 1
1926
+ dtype: uint8
1927
+ quantization_parameters:
1928
+ scale: 2.345790112112451
1929
+ offset: -128
1930
+ past_value_0_out:
1931
+ shape:
1932
+ - 8
1933
+ - 1
1934
+ - 1
1935
+ - 128
1936
+ dtype: uint8
1937
+ quantization_parameters:
1938
+ scale: 0.004396342855738843
1939
+ offset: -128
1940
+ past_key_1_out:
1941
+ shape:
1942
+ - 8
1943
+ - 1
1944
+ - 128
1945
+ - 1
1946
+ dtype: uint8
1947
+ quantization_parameters:
1948
+ scale: 0.4745758537232406
1949
+ offset: -128
1950
+ past_value_1_out:
1951
+ shape:
1952
+ - 8
1953
+ - 1
1954
+ - 1
1955
+ - 128
1956
+ dtype: uint8
1957
+ quantization_parameters:
1958
+ scale: 0.005273671820759773
1959
+ offset: -128
1960
+ past_key_2_out:
1961
+ shape:
1962
+ - 8
1963
+ - 1
1964
+ - 128
1965
+ - 1
1966
+ dtype: uint8
1967
+ quantization_parameters:
1968
+ scale: 0.20883603394031525
1969
+ offset: -128
1970
+ past_value_2_out:
1971
+ shape:
1972
+ - 8
1973
+ - 1
1974
+ - 1
1975
+ - 128
1976
+ dtype: uint8
1977
+ quantization_parameters:
1978
+ scale: 0.0066236164420843124
1979
+ offset: -128
1980
+ past_key_3_out:
1981
+ shape:
1982
+ - 8
1983
+ - 1
1984
+ - 128
1985
+ - 1
1986
+ dtype: uint8
1987
+ quantization_parameters:
1988
+ scale: 0.20998451113700867
1989
+ offset: -128
1990
+ past_value_3_out:
1991
+ shape:
1992
+ - 8
1993
+ - 1
1994
+ - 1
1995
+ - 128
1996
+ dtype: uint8
1997
+ quantization_parameters:
1998
+ scale: 0.009058302268385887
1999
+ offset: -128
2000
+ past_key_4_out:
2001
+ shape:
2002
+ - 8
2003
+ - 1
2004
+ - 128
2005
+ - 1
2006
+ dtype: uint8
2007
+ quantization_parameters:
2008
+ scale: 0.5082661185677596
2009
+ offset: -128
2010
+ past_value_4_out:
2011
+ shape:
2012
+ - 8
2013
+ - 1
2014
+ - 1
2015
+ - 128
2016
+ dtype: uint8
2017
+ quantization_parameters:
2018
+ scale: 0.010039279237389565
2019
+ offset: -128
2020
+ past_key_5_out:
2021
+ shape:
2022
+ - 8
2023
+ - 1
2024
+ - 128
2025
+ - 1
2026
+ dtype: uint8
2027
+ quantization_parameters:
2028
+ scale: 0.8604878703440269
2029
+ offset: -128
2030
+ past_value_5_out:
2031
+ shape:
2032
+ - 8
2033
+ - 1
2034
+ - 1
2035
+ - 128
2036
+ dtype: uint8
2037
+ quantization_parameters:
2038
+ scale: 0.011779437772929668
2039
+ offset: -128
2040
+ past_key_6_out:
2041
+ shape:
2042
+ - 8
2043
+ - 1
2044
+ - 128
2045
+ - 1
2046
+ dtype: uint8
2047
+ quantization_parameters:
2048
+ scale: 0.32763143224040353
2049
+ offset: -128
2050
+ past_value_6_out:
2051
+ shape:
2052
+ - 8
2053
+ - 1
2054
+ - 1
2055
+ - 128
2056
+ dtype: uint8
2057
+ quantization_parameters:
2058
+ scale: 0.015452229417860508
2059
+ offset: -128
2060
+ past_key_7_out:
2061
+ shape:
2062
+ - 8
2063
+ - 1
2064
+ - 128
2065
+ - 1
2066
+ dtype: uint8
2067
+ quantization_parameters:
2068
+ scale: 0.2633135938268947
2069
+ offset: -128
2070
+ past_value_7_out:
2071
+ shape:
2072
+ - 8
2073
+ - 1
2074
+ - 1
2075
+ - 128
2076
+ dtype: uint8
2077
+ quantization_parameters:
2078
+ scale: 0.023205885663628578
2079
+ offset: -128
2080
+ past_key_8_out:
2081
+ shape:
2082
+ - 8
2083
+ - 1
2084
+ - 128
2085
+ - 1
2086
+ dtype: uint8
2087
+ quantization_parameters:
2088
+ scale: 0.4432932138442993
2089
+ offset: -128
2090
+ past_value_8_out:
2091
+ shape:
2092
+ - 8
2093
+ - 1
2094
+ - 1
2095
+ - 128
2096
+ dtype: uint8
2097
+ quantization_parameters:
2098
+ scale: 0.025590643286705017
2099
+ offset: -128
2100
+ past_key_9_out:
2101
+ shape:
2102
+ - 8
2103
+ - 1
2104
+ - 128
2105
+ - 1
2106
+ dtype: uint8
2107
+ quantization_parameters:
2108
+ scale: 0.198994809248316
2109
+ offset: -128
2110
+ past_value_9_out:
2111
+ shape:
2112
+ - 8
2113
+ - 1
2114
+ - 1
2115
+ - 128
2116
+ dtype: uint8
2117
+ quantization_parameters:
2118
+ scale: 0.02567124180495739
2119
+ offset: -128
2120
+ past_key_10_out:
2121
+ shape:
2122
+ - 8
2123
+ - 1
2124
+ - 128
2125
+ - 1
2126
+ dtype: uint8
2127
+ quantization_parameters:
2128
+ scale: 0.3400344252586365
2129
+ offset: -128
2130
+ past_value_10_out:
2131
+ shape:
2132
+ - 8
2133
+ - 1
2134
+ - 1
2135
+ - 128
2136
+ dtype: uint8
2137
+ quantization_parameters:
2138
+ scale: 0.047514863312244415
2139
+ offset: -128
2140
+ past_key_11_out:
2141
+ shape:
2142
+ - 8
2143
+ - 1
2144
+ - 128
2145
+ - 1
2146
+ dtype: uint8
2147
+ quantization_parameters:
2148
+ scale: 0.30140187421182946
2149
+ offset: -128
2150
+ past_value_11_out:
2151
+ shape:
2152
+ - 8
2153
+ - 1
2154
+ - 1
2155
+ - 128
2156
+ dtype: uint8
2157
+ quantization_parameters:
2158
+ scale: 0.029060301818246915
2159
+ offset: -128
2160
+ ar1_cl4096_3_of_4:
2161
+ inputs:
2162
+ /model/model/layers.11/Add_1_output_0:
2163
+ shape:
2164
+ - 1
2165
+ - 1
2166
+ - 2560
2167
+ dtype: uint16
2168
+ quantization_parameters:
2169
+ scale: 0.2177089144874876
2170
+ offset: -14531
2171
+ attention_mask:
2172
+ shape:
2173
+ - 1
2174
+ - 1
2175
+ - 1
2176
+ - 4096
2177
+ dtype: uint16
2178
+ quantization_parameters:
2179
+ scale: 0.0015259021896696422
2180
+ offset: -65535
2181
+ position_ids_cos:
2182
+ shape:
2183
+ - 1
2184
+ - 1
2185
+ - 1
2186
+ - 64
2187
+ dtype: uint16
2188
+ quantization_parameters:
2189
+ scale: 3.0518043793392844e-05
2190
+ offset: -32768
2191
+ position_ids_sin:
2192
+ shape:
2193
+ - 1
2194
+ - 1
2195
+ - 1
2196
+ - 64
2197
+ dtype: uint16
2198
+ quantization_parameters:
2199
+ scale: 3.0518043793392844e-05
2200
+ offset: -32768
2201
+ past_key_12_in:
2202
+ shape:
2203
+ - 8
2204
+ - 1
2205
+ - 128
2206
+ - 4095
2207
+ dtype: uint8
2208
+ quantization_parameters:
2209
+ scale: 0.2443227916955948
2210
+ offset: -128
2211
+ past_value_12_in:
2212
+ shape:
2213
+ - 8
2214
+ - 1
2215
+ - 4095
2216
+ - 128
2217
+ dtype: uint8
2218
+ quantization_parameters:
2219
+ scale: 0.028940375395647183
2220
+ offset: -128
2221
+ past_key_13_in:
2222
+ shape:
2223
+ - 8
2224
+ - 1
2225
+ - 128
2226
+ - 4095
2227
+ dtype: uint8
2228
+ quantization_parameters:
2229
+ scale: 0.2185003776249923
2230
+ offset: -128
2231
+ past_value_13_in:
2232
+ shape:
2233
+ - 8
2234
+ - 1
2235
+ - 4095
2236
+ - 128
2237
+ dtype: uint8
2238
+ quantization_parameters:
2239
+ scale: 0.17545437812805176
2240
+ offset: -128
2241
+ past_key_14_in:
2242
+ shape:
2243
+ - 8
2244
+ - 1
2245
+ - 128
2246
+ - 4095
2247
+ dtype: uint8
2248
+ quantization_parameters:
2249
+ scale: 0.2587217390537262
2250
+ offset: -128
2251
+ past_value_14_in:
2252
+ shape:
2253
+ - 8
2254
+ - 1
2255
+ - 4095
2256
+ - 128
2257
+ dtype: uint8
2258
+ quantization_parameters:
2259
+ scale: 0.09416288137435913
2260
+ offset: -128
2261
+ past_key_15_in:
2262
+ shape:
2263
+ - 8
2264
+ - 1
2265
+ - 128
2266
+ - 4095
2267
+ dtype: uint8
2268
+ quantization_parameters:
2269
+ scale: 0.18699947867806502
2270
+ offset: -128
2271
+ past_value_15_in:
2272
+ shape:
2273
+ - 8
2274
+ - 1
2275
+ - 4095
2276
+ - 128
2277
+ dtype: uint8
2278
+ quantization_parameters:
2279
+ scale: 0.2346538033072404
2280
+ offset: -128
2281
+ past_key_16_in:
2282
+ shape:
2283
+ - 8
2284
+ - 1
2285
+ - 128
2286
+ - 4095
2287
+ dtype: uint8
2288
+ quantization_parameters:
2289
+ scale: 0.2061757892370224
2290
+ offset: -128
2291
+ past_value_16_in:
2292
+ shape:
2293
+ - 8
2294
+ - 1
2295
+ - 4095
2296
+ - 128
2297
+ dtype: uint8
2298
+ quantization_parameters:
2299
+ scale: 0.19758310092715767
2300
+ offset: -128
2301
+ past_key_17_in:
2302
+ shape:
2303
+ - 8
2304
+ - 1
2305
+ - 128
2306
+ - 4095
2307
+ dtype: uint8
2308
+ quantization_parameters:
2309
+ scale: 0.17539973521795799
2310
+ offset: -128
2311
+ past_value_17_in:
2312
+ shape:
2313
+ - 8
2314
+ - 1
2315
+ - 4095
2316
+ - 128
2317
+ dtype: uint8
2318
+ quantization_parameters:
2319
+ scale: 0.32720860838890076
2320
+ offset: -128
2321
+ past_key_18_in:
2322
+ shape:
2323
+ - 8
2324
+ - 1
2325
+ - 128
2326
+ - 4095
2327
+ dtype: uint8
2328
+ quantization_parameters:
2329
+ scale: 0.19263408690925657
2330
+ offset: -128
2331
+ past_value_18_in:
2332
+ shape:
2333
+ - 8
2334
+ - 1
2335
+ - 4095
2336
+ - 128
2337
+ dtype: uint8
2338
+ quantization_parameters:
2339
+ scale: 0.16426491925096887
2340
+ offset: -128
2341
+ past_key_19_in:
2342
+ shape:
2343
+ - 8
2344
+ - 1
2345
+ - 128
2346
+ - 4095
2347
+ dtype: uint8
2348
+ quantization_parameters:
2349
+ scale: 0.21870377659797668
2350
+ offset: -128
2351
+ past_value_19_in:
2352
+ shape:
2353
+ - 8
2354
+ - 1
2355
+ - 4095
2356
+ - 128
2357
+ dtype: uint8
2358
+ quantization_parameters:
2359
+ scale: 0.06083845153568298
2360
+ offset: -128
2361
+ past_key_20_in:
2362
+ shape:
2363
+ - 8
2364
+ - 1
2365
+ - 128
2366
+ - 4095
2367
+ dtype: uint8
2368
+ quantization_parameters:
2369
+ scale: 0.1891358345746994
2370
+ offset: -128
2371
+ past_value_20_in:
2372
+ shape:
2373
+ - 8
2374
+ - 1
2375
+ - 4095
2376
+ - 128
2377
+ dtype: uint8
2378
+ quantization_parameters:
2379
+ scale: 0.05266200378537178
2380
+ offset: -128
2381
+ past_key_21_in:
2382
+ shape:
2383
+ - 8
2384
+ - 1
2385
+ - 128
2386
+ - 4095
2387
+ dtype: uint8
2388
+ quantization_parameters:
2389
+ scale: 0.19000622606652928
2390
+ offset: -128
2391
+ past_value_21_in:
2392
+ shape:
2393
+ - 8
2394
+ - 1
2395
+ - 4095
2396
+ - 128
2397
+ dtype: uint8
2398
+ quantization_parameters:
2399
+ scale: 0.06354268141618864
2400
+ offset: -128
2401
+ past_key_22_in:
2402
+ shape:
2403
+ - 8
2404
+ - 1
2405
+ - 128
2406
+ - 4095
2407
+ dtype: uint8
2408
+ quantization_parameters:
2409
+ scale: 0.22853676974773407
2410
+ offset: -128
2411
+ past_value_22_in:
2412
+ shape:
2413
+ - 8
2414
+ - 1
2415
+ - 4095
2416
+ - 128
2417
+ dtype: uint8
2418
+ quantization_parameters:
2419
+ scale: 0.19043058156967163
2420
+ offset: -128
2421
+ past_key_23_in:
2422
+ shape:
2423
+ - 8
2424
+ - 1
2425
+ - 128
2426
+ - 4095
2427
+ dtype: uint8
2428
+ quantization_parameters:
2429
+ scale: 0.2349507489542323
2430
+ offset: -128
2431
+ past_value_23_in:
2432
+ shape:
2433
+ - 8
2434
+ - 1
2435
+ - 4095
2436
+ - 128
2437
+ dtype: uint8
2438
+ quantization_parameters:
2439
+ scale: 0.06769621090626153
2440
+ offset: -128
2441
+ outputs:
2442
+ /model/model/layers.23/Add_1_output_0:
2443
+ shape:
2444
+ - 1
2445
+ - 1
2446
+ - 2560
2447
+ dtype: uint16
2448
+ quantization_parameters:
2449
+ scale: 0.22199481461480505
2450
+ offset: -14218
2451
+ past_key_12_out:
2452
+ shape:
2453
+ - 8
2454
+ - 1
2455
+ - 128
2456
+ - 1
2457
+ dtype: uint8
2458
+ quantization_parameters:
2459
+ scale: 0.2443227916955948
2460
+ offset: -128
2461
+ past_value_12_out:
2462
+ shape:
2463
+ - 8
2464
+ - 1
2465
+ - 1
2466
+ - 128
2467
+ dtype: uint8
2468
+ quantization_parameters:
2469
+ scale: 0.028940375395647183
2470
+ offset: -128
2471
+ past_key_13_out:
2472
+ shape:
2473
+ - 8
2474
+ - 1
2475
+ - 128
2476
+ - 1
2477
+ dtype: uint8
2478
+ quantization_parameters:
2479
+ scale: 0.2185003776249923
2480
+ offset: -128
2481
+ past_value_13_out:
2482
+ shape:
2483
+ - 8
2484
+ - 1
2485
+ - 1
2486
+ - 128
2487
+ dtype: uint8
2488
+ quantization_parameters:
2489
+ scale: 0.17545437812805176
2490
+ offset: -128
2491
+ past_key_14_out:
2492
+ shape:
2493
+ - 8
2494
+ - 1
2495
+ - 128
2496
+ - 1
2497
+ dtype: uint8
2498
+ quantization_parameters:
2499
+ scale: 0.2587217390537262
2500
+ offset: -128
2501
+ past_value_14_out:
2502
+ shape:
2503
+ - 8
2504
+ - 1
2505
+ - 1
2506
+ - 128
2507
+ dtype: uint8
2508
+ quantization_parameters:
2509
+ scale: 0.09416288137435913
2510
+ offset: -128
2511
+ past_key_15_out:
2512
+ shape:
2513
+ - 8
2514
+ - 1
2515
+ - 128
2516
+ - 1
2517
+ dtype: uint8
2518
+ quantization_parameters:
2519
+ scale: 0.18699947867806502
2520
+ offset: -128
2521
+ past_value_15_out:
2522
+ shape:
2523
+ - 8
2524
+ - 1
2525
+ - 1
2526
+ - 128
2527
+ dtype: uint8
2528
+ quantization_parameters:
2529
+ scale: 0.2346538033072404
2530
+ offset: -128
2531
+ past_key_16_out:
2532
+ shape:
2533
+ - 8
2534
+ - 1
2535
+ - 128
2536
+ - 1
2537
+ dtype: uint8
2538
+ quantization_parameters:
2539
+ scale: 0.2061757892370224
2540
+ offset: -128
2541
+ past_value_16_out:
2542
+ shape:
2543
+ - 8
2544
+ - 1
2545
+ - 1
2546
+ - 128
2547
+ dtype: uint8
2548
+ quantization_parameters:
2549
+ scale: 0.19758310092715767
2550
+ offset: -128
2551
+ past_key_17_out:
2552
+ shape:
2553
+ - 8
2554
+ - 1
2555
+ - 128
2556
+ - 1
2557
+ dtype: uint8
2558
+ quantization_parameters:
2559
+ scale: 0.17539973521795799
2560
+ offset: -128
2561
+ past_value_17_out:
2562
+ shape:
2563
+ - 8
2564
+ - 1
2565
+ - 1
2566
+ - 128
2567
+ dtype: uint8
2568
+ quantization_parameters:
2569
+ scale: 0.32720860838890076
2570
+ offset: -128
2571
+ past_key_18_out:
2572
+ shape:
2573
+ - 8
2574
+ - 1
2575
+ - 128
2576
+ - 1
2577
+ dtype: uint8
2578
+ quantization_parameters:
2579
+ scale: 0.19263408690925657
2580
+ offset: -128
2581
+ past_value_18_out:
2582
+ shape:
2583
+ - 8
2584
+ - 1
2585
+ - 1
2586
+ - 128
2587
+ dtype: uint8
2588
+ quantization_parameters:
2589
+ scale: 0.16426491925096887
2590
+ offset: -128
2591
+ past_key_19_out:
2592
+ shape:
2593
+ - 8
2594
+ - 1
2595
+ - 128
2596
+ - 1
2597
+ dtype: uint8
2598
+ quantization_parameters:
2599
+ scale: 0.21870377659797668
2600
+ offset: -128
2601
+ past_value_19_out:
2602
+ shape:
2603
+ - 8
2604
+ - 1
2605
+ - 1
2606
+ - 128
2607
+ dtype: uint8
2608
+ quantization_parameters:
2609
+ scale: 0.06083845153568298
2610
+ offset: -128
2611
+ past_key_20_out:
2612
+ shape:
2613
+ - 8
2614
+ - 1
2615
+ - 128
2616
+ - 1
2617
+ dtype: uint8
2618
+ quantization_parameters:
2619
+ scale: 0.1891358345746994
2620
+ offset: -128
2621
+ past_value_20_out:
2622
+ shape:
2623
+ - 8
2624
+ - 1
2625
+ - 1
2626
+ - 128
2627
+ dtype: uint8
2628
+ quantization_parameters:
2629
+ scale: 0.05266200378537178
2630
+ offset: -128
2631
+ past_key_21_out:
2632
+ shape:
2633
+ - 8
2634
+ - 1
2635
+ - 128
2636
+ - 1
2637
+ dtype: uint8
2638
+ quantization_parameters:
2639
+ scale: 0.19000622606652928
2640
+ offset: -128
2641
+ past_value_21_out:
2642
+ shape:
2643
+ - 8
2644
+ - 1
2645
+ - 1
2646
+ - 128
2647
+ dtype: uint8
2648
+ quantization_parameters:
2649
+ scale: 0.06354268141618864
2650
+ offset: -128
2651
+ past_key_22_out:
2652
+ shape:
2653
+ - 8
2654
+ - 1
2655
+ - 128
2656
+ - 1
2657
+ dtype: uint8
2658
+ quantization_parameters:
2659
+ scale: 0.22853676974773407
2660
+ offset: -128
2661
+ past_value_22_out:
2662
+ shape:
2663
+ - 8
2664
+ - 1
2665
+ - 1
2666
+ - 128
2667
+ dtype: uint8
2668
+ quantization_parameters:
2669
+ scale: 0.19043058156967163
2670
+ offset: -128
2671
+ past_key_23_out:
2672
+ shape:
2673
+ - 8
2674
+ - 1
2675
+ - 128
2676
+ - 1
2677
+ dtype: uint8
2678
+ quantization_parameters:
2679
+ scale: 0.2349507489542323
2680
+ offset: -128
2681
+ past_value_23_out:
2682
+ shape:
2683
+ - 8
2684
+ - 1
2685
+ - 1
2686
+ - 128
2687
+ dtype: uint8
2688
+ quantization_parameters:
2689
+ scale: 0.06769621090626153
2690
+ offset: -128
2691
+ ar1_cl4096_4_of_4:
2692
+ inputs:
2693
+ /model/model/layers.23/Add_1_output_0:
2694
+ shape:
2695
+ - 1
2696
+ - 1
2697
+ - 2560
2698
+ dtype: uint16
2699
+ quantization_parameters:
2700
+ scale: 0.22199481461480505
2701
+ offset: -14218
2702
+ attention_mask:
2703
+ shape:
2704
+ - 1
2705
+ - 1
2706
+ - 1
2707
+ - 4096
2708
+ dtype: uint16
2709
+ quantization_parameters:
2710
+ scale: 0.0015259021896696422
2711
+ offset: -65535
2712
+ position_ids_cos:
2713
+ shape:
2714
+ - 1
2715
+ - 1
2716
+ - 1
2717
+ - 64
2718
+ dtype: uint16
2719
+ quantization_parameters:
2720
+ scale: 3.0518043793392844e-05
2721
+ offset: -32768
2722
+ position_ids_sin:
2723
+ shape:
2724
+ - 1
2725
+ - 1
2726
+ - 1
2727
+ - 64
2728
+ dtype: uint16
2729
+ quantization_parameters:
2730
+ scale: 3.0518043793392844e-05
2731
+ offset: -32768
2732
+ past_key_24_in:
2733
+ shape:
2734
+ - 8
2735
+ - 1
2736
+ - 128
2737
+ - 4095
2738
+ dtype: uint8
2739
+ quantization_parameters:
2740
+ scale: 0.2168474873219888
2741
+ offset: -128
2742
+ past_value_24_in:
2743
+ shape:
2744
+ - 8
2745
+ - 1
2746
+ - 4095
2747
+ - 128
2748
+ dtype: uint8
2749
+ quantization_parameters:
2750
+ scale: 0.0993499606847763
2751
+ offset: -128
2752
+ past_key_25_in:
2753
+ shape:
2754
+ - 8
2755
+ - 1
2756
+ - 128
2757
+ - 4095
2758
+ dtype: uint8
2759
+ quantization_parameters:
2760
+ scale: 0.16338758170604706
2761
+ offset: -128
2762
+ past_value_25_in:
2763
+ shape:
2764
+ - 8
2765
+ - 1
2766
+ - 4095
2767
+ - 128
2768
+ dtype: uint8
2769
+ quantization_parameters:
2770
+ scale: 0.08785130083560944
2771
+ offset: -128
2772
+ past_key_26_in:
2773
+ shape:
2774
+ - 8
2775
+ - 1
2776
+ - 128
2777
+ - 4095
2778
+ dtype: uint8
2779
+ quantization_parameters:
2780
+ scale: 0.17082346975803375
2781
+ offset: -128
2782
+ past_value_26_in:
2783
+ shape:
2784
+ - 8
2785
+ - 1
2786
+ - 4095
2787
+ - 128
2788
+ dtype: uint8
2789
+ quantization_parameters:
2790
+ scale: 0.09179645448219119
2791
+ offset: -128
2792
+ past_key_27_in:
2793
+ shape:
2794
+ - 8
2795
+ - 1
2796
+ - 128
2797
+ - 4095
2798
+ dtype: uint8
2799
+ quantization_parameters:
2800
+ scale: 0.15799155831336975
2801
+ offset: -128
2802
+ past_value_27_in:
2803
+ shape:
2804
+ - 8
2805
+ - 1
2806
+ - 4095
2807
+ - 128
2808
+ dtype: uint8
2809
+ quantization_parameters:
2810
+ scale: 0.11564768105745316
2811
+ offset: -128
2812
+ past_key_28_in:
2813
+ shape:
2814
+ - 8
2815
+ - 1
2816
+ - 128
2817
+ - 4095
2818
+ dtype: uint8
2819
+ quantization_parameters:
2820
+ scale: 0.16321668850155327
2821
+ offset: -128
2822
+ past_value_28_in:
2823
+ shape:
2824
+ - 8
2825
+ - 1
2826
+ - 4095
2827
+ - 128
2828
+ dtype: uint8
2829
+ quantization_parameters:
2830
+ scale: 0.12118262193334384
2831
+ offset: -128
2832
+ past_key_29_in:
2833
+ shape:
2834
+ - 8
2835
+ - 1
2836
+ - 128
2837
+ - 4095
2838
+ dtype: uint8
2839
+ quantization_parameters:
2840
+ scale: 0.181901752948761
2841
+ offset: -128
2842
+ past_value_29_in:
2843
+ shape:
2844
+ - 8
2845
+ - 1
2846
+ - 4095
2847
+ - 128
2848
+ dtype: uint8
2849
+ quantization_parameters:
2850
+ scale: 0.35103084534171997
2851
+ offset: -128
2852
+ past_key_30_in:
2853
+ shape:
2854
+ - 8
2855
+ - 1
2856
+ - 128
2857
+ - 4095
2858
+ dtype: uint8
2859
+ quantization_parameters:
2860
+ scale: 0.18615905940532684
2861
+ offset: -128
2862
+ past_value_30_in:
2863
+ shape:
2864
+ - 8
2865
+ - 1
2866
+ - 4095
2867
+ - 128
2868
+ dtype: uint8
2869
+ quantization_parameters:
2870
+ scale: 0.29017698764801025
2871
+ offset: -128
2872
+ past_key_31_in:
2873
+ shape:
2874
+ - 8
2875
+ - 1
2876
+ - 128
2877
+ - 4095
2878
+ dtype: uint8
2879
+ quantization_parameters:
2880
+ scale: 0.19037732481956482
2881
+ offset: -128
2882
+ past_value_31_in:
2883
+ shape:
2884
+ - 8
2885
+ - 1
2886
+ - 4095
2887
+ - 128
2888
+ dtype: uint8
2889
+ quantization_parameters:
2890
+ scale: 0.3625663096510519
2891
+ offset: -128
2892
+ past_key_32_in:
2893
+ shape:
2894
+ - 8
2895
+ - 1
2896
+ - 128
2897
+ - 4095
2898
+ dtype: uint8
2899
+ quantization_parameters:
2900
+ scale: 0.15537120789054812
2901
+ offset: -128
2902
+ past_value_32_in:
2903
+ shape:
2904
+ - 8
2905
+ - 1
2906
+ - 4095
2907
+ - 128
2908
+ dtype: uint8
2909
+ quantization_parameters:
2910
+ scale: 0.45803920115072894
2911
+ offset: -128
2912
+ past_key_33_in:
2913
+ shape:
2914
+ - 8
2915
+ - 1
2916
+ - 128
2917
+ - 4095
2918
+ dtype: uint8
2919
+ quantization_parameters:
2920
+ scale: 0.17338245121512827
2921
+ offset: -128
2922
+ past_value_33_in:
2923
+ shape:
2924
+ - 8
2925
+ - 1
2926
+ - 4095
2927
+ - 128
2928
+ dtype: uint8
2929
+ quantization_parameters:
2930
+ scale: 0.9015522754098487
2931
+ offset: -128
2932
+ past_key_34_in:
2933
+ shape:
2934
+ - 8
2935
+ - 1
2936
+ - 128
2937
+ - 4095
2938
+ dtype: uint8
2939
+ quantization_parameters:
2940
+ scale: 0.17443639039993286
2941
+ offset: -128
2942
+ past_value_34_in:
2943
+ shape:
2944
+ - 8
2945
+ - 1
2946
+ - 4095
2947
+ - 128
2948
+ dtype: uint8
2949
+ quantization_parameters:
2950
+ scale: 0.8790855407714844
2951
+ offset: -128
2952
+ past_key_35_in:
2953
+ shape:
2954
+ - 8
2955
+ - 1
2956
+ - 128
2957
+ - 4095
2958
+ dtype: uint8
2959
+ quantization_parameters:
2960
+ scale: 0.35408836603164673
2961
+ offset: -128
2962
+ past_value_35_in:
2963
+ shape:
2964
+ - 8
2965
+ - 1
2966
+ - 4095
2967
+ - 128
2968
+ dtype: uint8
2969
+ quantization_parameters:
2970
+ scale: 0.470033198595047
2971
+ offset: -128
2972
+ outputs:
2973
+ logits:
2974
+ shape:
2975
+ - 1
2976
+ - 1
2977
+ - 151936
2978
+ dtype: uint16
2979
+ quantization_parameters:
2980
+ scale: 0.0013899723052105387
2981
+ offset: -26872
2982
+ past_key_24_out:
2983
+ shape:
2984
+ - 8
2985
+ - 1
2986
+ - 128
2987
+ - 1
2988
+ dtype: uint8
2989
+ quantization_parameters:
2990
+ scale: 0.2168474873219888
2991
+ offset: -128
2992
+ past_value_24_out:
2993
+ shape:
2994
+ - 8
2995
+ - 1
2996
+ - 1
2997
+ - 128
2998
+ dtype: uint8
2999
+ quantization_parameters:
3000
+ scale: 0.0993499606847763
3001
+ offset: -128
3002
+ past_key_25_out:
3003
+ shape:
3004
+ - 8
3005
+ - 1
3006
+ - 128
3007
+ - 1
3008
+ dtype: uint8
3009
+ quantization_parameters:
3010
+ scale: 0.16338758170604706
3011
+ offset: -128
3012
+ past_value_25_out:
3013
+ shape:
3014
+ - 8
3015
+ - 1
3016
+ - 1
3017
+ - 128
3018
+ dtype: uint8
3019
+ quantization_parameters:
3020
+ scale: 0.08785130083560944
3021
+ offset: -128
3022
+ past_key_26_out:
3023
+ shape:
3024
+ - 8
3025
+ - 1
3026
+ - 128
3027
+ - 1
3028
+ dtype: uint8
3029
+ quantization_parameters:
3030
+ scale: 0.17082346975803375
3031
+ offset: -128
3032
+ past_value_26_out:
3033
+ shape:
3034
+ - 8
3035
+ - 1
3036
+ - 1
3037
+ - 128
3038
+ dtype: uint8
3039
+ quantization_parameters:
3040
+ scale: 0.09179645448219119
3041
+ offset: -128
3042
+ past_key_27_out:
3043
+ shape:
3044
+ - 8
3045
+ - 1
3046
+ - 128
3047
+ - 1
3048
+ dtype: uint8
3049
+ quantization_parameters:
3050
+ scale: 0.15799155831336975
3051
+ offset: -128
3052
+ past_value_27_out:
3053
+ shape:
3054
+ - 8
3055
+ - 1
3056
+ - 1
3057
+ - 128
3058
+ dtype: uint8
3059
+ quantization_parameters:
3060
+ scale: 0.11564768105745316
3061
+ offset: -128
3062
+ past_key_28_out:
3063
+ shape:
3064
+ - 8
3065
+ - 1
3066
+ - 128
3067
+ - 1
3068
+ dtype: uint8
3069
+ quantization_parameters:
3070
+ scale: 0.16321668850155327
3071
+ offset: -128
3072
+ past_value_28_out:
3073
+ shape:
3074
+ - 8
3075
+ - 1
3076
+ - 1
3077
+ - 128
3078
+ dtype: uint8
3079
+ quantization_parameters:
3080
+ scale: 0.12118262193334384
3081
+ offset: -128
3082
+ past_key_29_out:
3083
+ shape:
3084
+ - 8
3085
+ - 1
3086
+ - 128
3087
+ - 1
3088
+ dtype: uint8
3089
+ quantization_parameters:
3090
+ scale: 0.181901752948761
3091
+ offset: -128
3092
+ past_value_29_out:
3093
+ shape:
3094
+ - 8
3095
+ - 1
3096
+ - 1
3097
+ - 128
3098
+ dtype: uint8
3099
+ quantization_parameters:
3100
+ scale: 0.35103084534171997
3101
+ offset: -128
3102
+ past_key_30_out:
3103
+ shape:
3104
+ - 8
3105
+ - 1
3106
+ - 128
3107
+ - 1
3108
+ dtype: uint8
3109
+ quantization_parameters:
3110
+ scale: 0.18615905940532684
3111
+ offset: -128
3112
+ past_value_30_out:
3113
+ shape:
3114
+ - 8
3115
+ - 1
3116
+ - 1
3117
+ - 128
3118
+ dtype: uint8
3119
+ quantization_parameters:
3120
+ scale: 0.29017698764801025
3121
+ offset: -128
3122
+ past_key_31_out:
3123
+ shape:
3124
+ - 8
3125
+ - 1
3126
+ - 128
3127
+ - 1
3128
+ dtype: uint8
3129
+ quantization_parameters:
3130
+ scale: 0.19037732481956482
3131
+ offset: -128
3132
+ past_value_31_out:
3133
+ shape:
3134
+ - 8
3135
+ - 1
3136
+ - 1
3137
+ - 128
3138
+ dtype: uint8
3139
+ quantization_parameters:
3140
+ scale: 0.3625663096510519
3141
+ offset: -128
3142
+ past_key_32_out:
3143
+ shape:
3144
+ - 8
3145
+ - 1
3146
+ - 128
3147
+ - 1
3148
+ dtype: uint8
3149
+ quantization_parameters:
3150
+ scale: 0.15537120789054812
3151
+ offset: -128
3152
+ past_value_32_out:
3153
+ shape:
3154
+ - 8
3155
+ - 1
3156
+ - 1
3157
+ - 128
3158
+ dtype: uint8
3159
+ quantization_parameters:
3160
+ scale: 0.45803920115072894
3161
+ offset: -128
3162
+ past_key_33_out:
3163
+ shape:
3164
+ - 8
3165
+ - 1
3166
+ - 128
3167
+ - 1
3168
+ dtype: uint8
3169
+ quantization_parameters:
3170
+ scale: 0.17338245121512827
3171
+ offset: -128
3172
+ past_value_33_out:
3173
+ shape:
3174
+ - 8
3175
+ - 1
3176
+ - 1
3177
+ - 128
3178
+ dtype: uint8
3179
+ quantization_parameters:
3180
+ scale: 0.9015522754098487
3181
+ offset: -128
3182
+ past_key_34_out:
3183
+ shape:
3184
+ - 8
3185
+ - 1
3186
+ - 128
3187
+ - 1
3188
+ dtype: uint8
3189
+ quantization_parameters:
3190
+ scale: 0.17443639039993286
3191
+ offset: -128
3192
+ past_value_34_out:
3193
+ shape:
3194
+ - 8
3195
+ - 1
3196
+ - 1
3197
+ - 128
3198
+ dtype: uint8
3199
+ quantization_parameters:
3200
+ scale: 0.8790855407714844
3201
+ offset: -128
3202
+ past_key_35_out:
3203
+ shape:
3204
+ - 8
3205
+ - 1
3206
+ - 128
3207
+ - 1
3208
+ dtype: uint8
3209
+ quantization_parameters:
3210
+ scale: 0.35408836603164673
3211
+ offset: -128
3212
+ past_value_35_out:
3213
+ shape:
3214
+ - 8
3215
+ - 1
3216
+ - 1
3217
+ - 128
3218
+ dtype: uint8
3219
+ quantization_parameters:
3220
+ scale: 0.470033198595047
3221
+ offset: -128
3222
+ precision: w4a16
3223
+ runtime: genie
qwen3_4b_part_1_of_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e639c72438fe0dd130b654edfc72286a2e4bd4342c10b4e4a9658160fc14633a
3
+ size 777973760
qwen3_4b_part_2_of_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ed132983eba72ef3d0da064d27a5e5df77c3aa93a3b4ea9c1e8e1d4cfd1a381
3
+ size 629985280
qwen3_4b_part_3_of_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4308eba2aef46493c4bc764e6f0a49330640756147b80632cec8392368c687e4
3
+ size 630013952
qwen3_4b_part_4_of_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98a924fe148e05a009d140759ec76ed52cca0616621f869b3e53607b9e79465c
3
+ size 1023483904
sample_prompt.txt ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ <|im_start|>system
2
+ You are a helpful AI assistant<|im_end|>
3
+ <|im_start|>user
4
+ What is gravity? Keep the answer under ten words.<|im_end|>
5
+ <|im_start|>assistant
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
231
+ "clean_up_tokenization_spaces": false,
232
+ "eos_token": "<|im_end|>",
233
+ "errors": "replace",
234
+ "extra_special_tokens": {},
235
+ "is_fast": true,
236
+ "model_max_length": 131072,
237
+ "pad_token": "<|im_end|>",
238
+ "split_special_tokens": false,
239
+ "tokenizer_class": "Qwen2Tokenizer",
240
+ "unk_token": null
241
+ }
tool-versions.yaml ADDED
@@ -0,0 +1 @@
 
 
1
+ qairt: 2.42.0.251225135753_193295