Hugging Face's logo

Rijgersberg
/
Mistral-7B-v0.1-chat-nl

Text Generation
Transformers
TensorBoard
Safetensors
Dutch
mistral
Generated from Trainer
GEITje
conversational
Inference Endpoints
text-generation-inference
Model card Files Metrics Community
Rijgersberg commited on
Commit
7ae4e33
•
1 Parent(s): fcc9ca6

Training in progress, epoch 0

Browse files
Files changed (11) hide show
  1. config.json +27 -0
  2. runs/Dec12_06-26-18_cff6e0378b08/events.out.tfevents.1702362391.cff6e0378b08.3086.0 +3 -0
  3. runs/Dec12_06-29-01_cff6e0378b08/events.out.tfevents.1702362554.cff6e0378b08.3471.0 +3 -0
  4. runs/Dec12_06-37-54_cff6e0378b08/events.out.tfevents.1702363086.cff6e0378b08.3858.0 +3 -0
  5. runs/Dec12_06-59-31_cff6e0378b08/events.out.tfevents.1702364373.cff6e0378b08.4268.0 +3 -0
  6. runs/Dec12_07-07-51_cff6e0378b08/events.out.tfevents.1702364872.cff6e0378b08.4845.0 +3 -0
  7. special_tokens_map.json +24 -0
  8. tokenizer.json +0 -0
  9. tokenizer.model +3 -0
  10. tokenizer_config.json +44 -0
  11. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-7B-v0.1",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "pad_token_id": 0,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_theta": 10000.0,
21
+ "sliding_window": 4096,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.36.0.dev0",
25
+ "use_cache": true,
26
+ "vocab_size": 32000
27
+ }
runs/Dec12_06-26-18_cff6e0378b08/events.out.tfevents.1702362391.cff6e0378b08.3086.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bea0d30f23027302a7da01285dfc02fe1125e2b8b2bbaf3d6090e83dd18fb67
3
+ size 4423
runs/Dec12_06-29-01_cff6e0378b08/events.out.tfevents.1702362554.cff6e0378b08.3471.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d94253821244a03b63c92d7a1a2270a921da91ae0d38f5199ecbccaeb95bde02
3
+ size 4423
runs/Dec12_06-37-54_cff6e0378b08/events.out.tfevents.1702363086.cff6e0378b08.3858.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a6d21d0f690bf1b471023258ea979ed673a55a34ae22725efec9c500cc571ca
3
+ size 4424
runs/Dec12_06-59-31_cff6e0378b08/events.out.tfevents.1702364373.cff6e0378b08.4268.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43ec915c9f01eb1792330aee6e14b9e7c11fb0e93a8c147efca8b04ceddb808f
3
+ size 4423
runs/Dec12_07-07-51_cff6e0378b08/events.out.tfevents.1702364872.cff6e0378b08.4845.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cbe62de2e07c3786185fcaf45c65eb7224da41c9f19bd9205a9d6513eac81e5
3
+ size 190929
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "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 %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "<unk>",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false,
43
+ "use_fase": false
44
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be3c7955dd0af593be90e9a9c8b6d43ce857ab99a79a2ea28c668114dd46af44
3
+ size 4728