Hugging Face's logo

optimum-intel-internal-testing
/
tiny-random-chatglm

TensorBoard
Safetensors
chatglm
Generated from Trainer
custom_code
Model card Files
xet
 Metrics Community
1

Fix NaN outputs

#1
by helenai - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+94
-73
Files changed (5) hide show
  1. config.json +46 -47
  2. generation_config.json +6 -6
  3. model.safetensors +1 -1
  4. special_tokens_map.json +5 -1
  5. tokenizer_config.json +36 -18
config.json CHANGED
@@ -1,47 +1,46 @@
1
- {
2
- "_name_or_path": "katuni4ka/tiny-random-chatglm2",
3
- "add_bias_linear": false,
4
- "add_qkv_bias": true,
5
- "apply_query_key_layer_scaling": true,
6
- "apply_residual_connection_post_layernorm": false,
7
- "architectures": [
8
- "ChatGLMForConditionalGeneration"
9
- ],
10
- "attention_dropout": 0.0,
11
- "attention_softmax_in_fp32": true,
12
- "auto_map": {
13
- "AutoConfig": "katuni4ka/tiny-random-chatglm2--configuration_chatglm.ChatGLMConfig",
14
- "AutoModel": "katuni4ka/tiny-random-chatglm2--modeling_chatglm.ChatGLMForConditionalGeneration",
15
- "AutoModelForCausalLM": "katuni4ka/tiny-random-chatglm2--modeling_chatglm.ChatGLMForConditionalGeneration",
16
- "AutoModelForSeq2SeqLM": "katuni4ka/tiny-random-chatglm2--modeling_chatglm.ChatGLMForConditionalGeneration",
17
- "AutoModelForSequenceClassification": "katuni4ka/tiny-random-chatglm2--modeling_chatglm.ChatGLMForSequenceClassification"
18
- },
19
- "bias_dropout_fusion": true,
20
- "classifier_dropout": null,
21
- "eos_token_id": 2,
22
- "ffn_hidden_size": 3424,
23
- "fp32_residual_connection": false,
24
- "hidden_dropout": 0.0,
25
- "hidden_size": 128,
26
- "kv_channels": 32,
27
- "layernorm_epsilon": 1e-05,
28
- "model_type": "chatglm",
29
- "multi_query_attention": true,
30
- "multi_query_group_num": 1,
31
- "num_attention_heads": 2,
32
- "num_layers": 2,
33
- "original_rope": true,
34
- "pad_token_id": 0,
35
- "padded_vocab_size": 65024,
36
- "post_layer_norm": true,
37
- "pre_seq_len": null,
38
- "prefix_projection": false,
39
- "quantization_bit": 0,
40
- "rmsnorm": true,
41
- "seq_length": 32768,
42
- "tie_word_embeddings": false,
43
- "torch_dtype": "float32",
44
- "transformers_version": "4.38.1",
45
- "use_cache": true,
46
- "vocab_size": 65024
47
- }
 
1
+ {
2
+ "add_bias_linear": false,
3
+ "add_qkv_bias": true,
4
+ "apply_query_key_layer_scaling": true,
5
+ "apply_residual_connection_post_layernorm": false,
6
+ "architectures": [
7
+ "ChatGLMForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "attention_softmax_in_fp32": true,
11
+ "auto_map": {
12
+ "AutoConfig": "configuration_chatglm.ChatGLMConfig",
13
+ "AutoModel": "katuni4ka/tiny-random-chatglm2--modeling_chatglm.ChatGLMForConditionalGeneration",
14
+ "AutoModelForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
15
+ "AutoModelForSeq2SeqLM": "katuni4ka/tiny-random-chatglm2--modeling_chatglm.ChatGLMForConditionalGeneration",
16
+ "AutoModelForSequenceClassification": "katuni4ka/tiny-random-chatglm2--modeling_chatglm.ChatGLMForSequenceClassification"
17
+ },
18
+ "bias_dropout_fusion": true,
19
+ "classifier_dropout": null,
20
+ "eos_token_id": 2,
21
+ "ffn_hidden_size": 3424,
22
+ "fp32_residual_connection": false,
23
+ "hidden_dropout": 0.0,
24
+ "hidden_size": 128,
25
+ "kv_channels": 32,
26
+ "layernorm_epsilon": 1e-05,
27
+ "model_type": "chatglm",
28
+ "multi_query_attention": true,
29
+ "multi_query_group_num": 1,
30
+ "num_attention_heads": 2,
31
+ "num_layers": 2,
32
+ "original_rope": true,
33
+ "pad_token_id": 0,
34
+ "padded_vocab_size": 65024,
35
+ "post_layer_norm": true,
36
+ "pre_seq_len": null,
37
+ "prefix_projection": false,
38
+ "quantization_bit": 0,
39
+ "rmsnorm": true,
40
+ "seq_length": 32768,
41
+ "tie_word_embeddings": false,
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.55.4",
44
+ "use_cache": true,
45
+ "vocab_size": 65024
46
+ }
 
generation_config.json CHANGED
@@ -1,6 +1,6 @@
1
- {
2
- "_from_model_config": true,
3
- "eos_token_id": 2,
4
- "pad_token_id": 0,
5
- "transformers_version": "4.38.1"
6
- }
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 2,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.55.4"
6
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:feebf1e929365645e986ae056b8fc1ab8c56f96f44d837f4d2cdd002b4900a44
3
  size 77305592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a3c1036c7b5709aca072f14837752559bd4210989b814be2a314437c28a6517
3
  size 77305592
special_tokens_map.json CHANGED
@@ -1 +1,5 @@
1
- {}
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<unk>",
4
+ "unk_token": "<unk>"
5
+ }
tokenizer_config.json CHANGED
@@ -1,18 +1,36 @@
1
- {
2
- "added_tokens_decoder": {},
3
- "auto_map": {
4
- "AutoTokenizer": [
5
- "katuni4ka/tiny-random-chatglm2--tokenization_chatglm.ChatGLMTokenizer",
6
- null
7
- ]
8
- },
9
- "clean_up_tokenization_spaces": false,
10
- "do_lower_case": false,
11
- "eos_token": "</s>",
12
- "model_max_length": 1000000000000000019884624838656,
13
- "pad_token": "<unk>",
14
- "padding_side": "left",
15
- "remove_space": false,
16
- "tokenizer_class": "ChatGLMTokenizer",
17
- "unk_token": "<unk>"
18
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "64787": {
4
+ "content": "</s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "64788": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ }
19
+ },
20
+ "auto_map": {
21
+ "AutoTokenizer": [
22
+ "tokenization_chatglm.ChatGLMTokenizer",
23
+ null
24
+ ]
25
+ },
26
+ "clean_up_tokenization_spaces": false,
27
+ "do_lower_case": false,
28
+ "eos_token": "</s>",
29
+ "extra_special_tokens": {},
30
+ "model_max_length": 1000000000000000019884624838656,
31
+ "pad_token": "<unk>",
32
+ "padding_side": "left",
33
+ "remove_space": false,
34
+ "tokenizer_class": "ChatGLMTokenizer",
35
+ "unk_token": "<unk>"
36
+ }