pooja-ganesh commited on
Commit
4f97f06
·
verified ·
1 Parent(s): 38a7a9d

Upload 9 files

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
+ chatglm3_v4_npu_jit.onnx.data filter=lfs diff=lfs merge=lfs -text
chatglm3_v4_npu_jit.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b6ade9e5d439d69699ed562d7cbde3d418a0b31ff766fa44ebace63d7efb38c
3
+ size 3256166400
chatglm3_v4_npu_jit.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09ee3d60f9298b8400b487785dbdab678a3fcc70d1580fd1a0bdd168cc0dc795
3
+ size 265157
chatglm3_v4_npu_jit.onnx.data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db1d34ef3817200cce82c3bf2031e35a06afc1f6779f65b74eca801c47831944
3
+ size 3639685120
chatglm3_v4_npu_jit.pb.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98cae8bfaaf13751bdbeba6b3852d78a6f19f167904a78bb0bafb4b6f3ee6a0b
3
+ size 6751
genai_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": {
3
+ "bos_token_id": 1,
4
+ "context_length": 8192,
5
+ "decoder": {
6
+ "session_options": {
7
+ "log_id": "onnxruntime-genai",
8
+ "custom_ops_library": "//path//to//onnx_custom_ops.dll",
9
+ "external_data_file": "chatglm3_v4_npu_jit.pb.bin",
10
+ "custom_allocator": "shared_d3d_xrt",
11
+ "provider_options": []
12
+ },
13
+ "filename": "chatglm3_v4_npu_jit.onnx",
14
+ "head_size": 128,
15
+ "hidden_size": 4096,
16
+ "inputs": {
17
+ "input_ids": "input_ids",
18
+ "attention_mask": "attention_mask",
19
+ "past_key_names": "past_key_values.%d.key",
20
+ "past_value_names": "past_key_values.%d.value"
21
+ },
22
+ "outputs": {
23
+ "logits": "logits",
24
+ "present_key_names": "present.%d.key",
25
+ "present_value_names": "present.%d.value"
26
+ },
27
+ "num_attention_heads": 32,
28
+ "num_hidden_layers": 28,
29
+ "num_key_value_heads": 2
30
+ },
31
+ "eos_token_id": 2,
32
+ "pad_token_id": 0,
33
+ "type": "chatglm",
34
+ "vocab_size": 65024
35
+ },
36
+ "search": {
37
+ "diversity_penalty": 0.0,
38
+ "do_sample": false,
39
+ "early_stopping": true,
40
+ "length_penalty": 1.0,
41
+ "max_length": 8192,
42
+ "min_length": 0,
43
+ "no_repeat_ngram_size": 0,
44
+ "num_beams": 1,
45
+ "num_return_sequences": 1,
46
+ "past_present_share_buffer": true,
47
+ "repetition_penalty": 1.0,
48
+ "temperature": 1.0,
49
+ "top_k": 1,
50
+ "top_p": 1.0
51
+ }
52
+ }
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7dc4c393423b76e4373e5157ddc34803a0189ba96b21ddbb40269d31468a6f2
3
+ size 1018370
tokenizer_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "64790": {
4
+ "content": "[gMASK]",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "64792": {
12
+ "content": "sop",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "64795": {
20
+ "content": "<|user|>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "64796": {
28
+ "content": "<|assistant|>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ }
35
+ },
36
+ "auto_map": {
37
+ "AutoTokenizer": [
38
+ "tokenization_chatglm.ChatGLMTokenizer",
39
+ null
40
+ ]
41
+ },
42
+ "chat_template": "{% for message in messages %}{% if loop.first %}[gMASK]sop<|{{ message['role'] }}|>\n {{ message['content'] }}{% else %}<|{{ message['role'] }}|>\n {{ message['content'] }}{% endif %}{% endfor %}{% if add_generation_prompt %}<|assistant|>{% endif %}",
43
+ "clean_up_tokenization_spaces": false,
44
+ "do_lower_case": false,
45
+ "eos_token": "</s>",
46
+ "model_max_length": 1000000000000000019884624838656,
47
+ "pad_token": "<unk>",
48
+ "padding_side": "left",
49
+ "remove_space": false,
50
+ "tokenizer_class": "ChatGLMTokenizer",
51
+ "unk_token": "<unk>"
52
+ }