Hugging Face's logo

jikaixuan
/
zephyr-ds

Text Generation
Transformers
TensorBoard
Safetensors
mistral
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
jikaixuan commited on
Commit
679f184
•
1 Parent(s): 51fdfae

Training in progress, epoch 0

Browse files
Files changed (10) hide show
  1. adapter_config.json +29 -0
  2. adapter_model.safetensors +3 -0
  3. runs/Jan09_19-45-26_uclaml03.cs.ucla.edu/events.out.tfevents.1704858597.uclaml03.cs.ucla.edu.996780.0 +3 -0
  4. runs/Jan09_20-01-31_uclaml03.cs.ucla.edu/events.out.tfevents.1704859563.uclaml03.cs.ucla.edu.999912.0 +3 -0
  5. runs/Jan10_17-41-41_uclaml03.cs.ucla.edu/events.out.tfevents.1704937615.uclaml03.cs.ucla.edu.1952084.0 +3 -0
  6. runs/Jan10_17-48-24_uclaml03.cs.ucla.edu/events.out.tfevents.1704938019.uclaml03.cs.ucla.edu.1956277.0 +3 -0
  7. special_tokens_map.json +30 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +41 -0
  10. training_args.bin +3 -0
adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.1,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 64,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "q_proj",
23
+ "k_proj",
24
+ "o_proj",
25
+ "v_proj"
26
+ ],
27
+ "task_type": "CAUSAL_LM",
28
+ "use_rslora": false
29
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:447886fe6fad21a81ab28995ca80f14ad58365802ff23a558700892ee76e225c
3
+ size 109086672
runs/Jan09_19-45-26_uclaml03.cs.ucla.edu/events.out.tfevents.1704858597.uclaml03.cs.ucla.edu.996780.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d878e79ae12505ed4012114439cdd6955ad310d985123b547e4789998acdb39
3
+ size 4346
runs/Jan09_20-01-31_uclaml03.cs.ucla.edu/events.out.tfevents.1704859563.uclaml03.cs.ucla.edu.999912.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c82161e92cbf4ee9e082b850524fd79a0de5a198dfc900fd5604b8f0b56fea7c
3
+ size 4969
runs/Jan10_17-41-41_uclaml03.cs.ucla.edu/events.out.tfevents.1704937615.uclaml03.cs.ucla.edu.1952084.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7ecd110b8b81b144e078428556dd9de05a51a7c96737afad4c0a71bcf8cfbed
3
+ size 4959
runs/Jan10_17-48-24_uclaml03.cs.ucla.edu/events.out.tfevents.1704938019.uclaml03.cs.ucla.edu.1956277.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea7ea90829a0226bd88e84e8d6f6798044043d3765c463684f5452470137332e
3
+ size 66151
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [],
29
+ "bos_token": "<s>",
30
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": true,
34
+ "model_max_length": 2048,
35
+ "pad_token": "</s>",
36
+ "sp_model_kwargs": {},
37
+ "spaces_between_special_tokens": false,
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "unk_token": "<unk>",
40
+ "use_default_system_prompt": false
41
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69f7e7755c1fc3eccdf174f6c86da3e64b925c4d29ff5a11237a8e9d9db91720
3
+ size 4728