Hugging Face's logo

Wonder-Griffin
/
TraXLMistralForCausalLM

Text Generation
Transformers
Safetensors
English
TraXLMistral
text-generation-inference
causal-LM
question-answering
conversational
Inference Endpoints
Model card Files Community
Wonder-Griffin commited on
Commit
04d93df
•
1 Parent(s): 2455e93

Upload 22 files

Browse files
Files changed (16) hide show
  1. checkpoint-200245/config.json +36 -0
  2. checkpoint-200245/generation_config.json +4 -0
  3. checkpoint-200245/merges.txt +0 -0
  4. checkpoint-200245/model.safetensors +3 -0
  5. checkpoint-200245/optimizer.pt +3 -0
  6. checkpoint-200245/rng_state.pth +3 -0
  7. checkpoint-200245/scheduler.pt +3 -0
  8. checkpoint-200245/special_tokens_map.json +30 -0
  9. checkpoint-200245/tokenizer.json +0 -0
  10. checkpoint-200245/tokenizer_config.json +20 -0
  11. checkpoint-200245/trainer_state.json +0 -0
  12. checkpoint-200245/training_args.bin +3 -0
  13. checkpoint-200245/vocab.json +0 -0
  14. config.json +36 -36
  15. generation_config.json +4 -0
  16. model.safetensors +1 -1
checkpoint-200245/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "C:/Users/wonde/Wonder-Griffin/TraXLMistralForCausalLM",
3
+ "architectures": [
4
+ "TraXLMistralForCausalLM"
5
+ ],
6
+ "dropout": 0.1,
7
+ "dynamic_routing": true,
8
+ "ff_expansion_factor": 4,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3",
15
+ "4": "LABEL_4"
16
+ },
17
+ "is_decoder": true,
18
+ "label2id": {
19
+ "LABEL_0": 0,
20
+ "LABEL_1": 1,
21
+ "LABEL_2": 2,
22
+ "LABEL_3": 3,
23
+ "LABEL_4": 4
24
+ },
25
+ "max_computation_steps": 5,
26
+ "max_len": 256,
27
+ "memory_size": 256,
28
+ "model_type": "TraXLMistral",
29
+ "n_head": 4,
30
+ "n_layer": 4,
31
+ "rnn_units": 128,
32
+ "sparse_attention": true,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.44.2",
35
+ "vocab_size": 50257
36
+ }
checkpoint-200245/generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.44.2"
4
+ }
checkpoint-200245/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-200245/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:848430740948bba9e1491496335370ff0016f910988a5cdde88d532113bd7d68
3
+ size 194528200
checkpoint-200245/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60ee5ba024c1c2479a867380e80bef0812a27e47ec0afb893683552f17f5411
3
+ size 369911930
checkpoint-200245/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cf49b1b239d490a0c183491b71a3538316d80907202cf6560e34a71b3f6178c
3
+ size 14244
checkpoint-200245/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c41ad118f60452e23871f03611c2c5e64083674e07e5e05a92a01032634abcf5
3
+ size 1064
checkpoint-200245/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
checkpoint-200245/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-200245/tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1024,
17
+ "pad_token": "<|endoftext|>",
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
20
+ }
checkpoint-200245/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-200245/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9abdc3f98a81525a3c63ea16eb57647d7c229d181018be84fa7d31fad3f12696
3
+ size 5176
checkpoint-200245/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json CHANGED
@@ -1,36 +1,36 @@
1
- {
2
- "_name_or_path": "C:/Users/wonde/Wonder-Griffin/TraXLMistralForCausalLM",
3
- "architectures": [
4
- "TraXLMistralForCausalLM"
5
- ],
6
- "dropout": 0.1,
7
- "dynamic_routing": true,
8
- "ff_expansion_factor": 4,
9
- "hidden_size": 768,
10
- "id2label": {
11
- "0": "LABEL_0",
12
- "1": "LABEL_1",
13
- "2": "LABEL_2",
14
- "3": "LABEL_3",
15
- "4": "LABEL_4"
16
- },
17
- "is_decoder": true,
18
- "label2id": {
19
- "LABEL_0": 0,
20
- "LABEL_1": 1,
21
- "LABEL_2": 2,
22
- "LABEL_3": 3,
23
- "LABEL_4": 4
24
- },
25
- "max_computation_steps": 5,
26
- "max_len": 256,
27
- "memory_size": 256,
28
- "model_type": "gpt2",
29
- "n_head": 4,
30
- "n_layer": 4,
31
- "rnn_units": 128,
32
- "sparse_attention": true,
33
- "torch_dtype": "float32",
34
- "transformers_version": "4.44.2",
35
- "vocab_size": 50257
36
- }
 
1
+ {
2
+ "_name_or_path": "C:/Users/wonde/Wonder-Griffin/TraXLMistralForCausalLM",
3
+ "architectures": [
4
+ "TraXLMistralForCausalLM"
5
+ ],
6
+ "dropout": 0.1,
7
+ "dynamic_routing": true,
8
+ "ff_expansion_factor": 4,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3",
15
+ "4": "LABEL_4"
16
+ },
17
+ "is_decoder": true,
18
+ "label2id": {
19
+ "LABEL_0": 0,
20
+ "LABEL_1": 1,
21
+ "LABEL_2": 2,
22
+ "LABEL_3": 3,
23
+ "LABEL_4": 4
24
+ },
25
+ "max_computation_steps": 5,
26
+ "max_len": 256,
27
+ "memory_size": 256,
28
+ "model_type": "TraXLMistral",
29
+ "n_head": 4,
30
+ "n_layer": 4,
31
+ "rnn_units": 128,
32
+ "sparse_attention": true,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.44.2",
35
+ "vocab_size": 50257
36
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.44.2"
4
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0bceb990b83c77292376f2a509df9fffdf04ccd9c395f19d8d148acfaa547d1
3
  size 194528200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:848430740948bba9e1491496335370ff0016f910988a5cdde88d532113bd7d68
3
  size 194528200