Hugging Face's logo

Boldt
/
Boldt-1B-IT-Preview

Text Generation
Transformers
Safetensors
German
llama
instruction-tuned
german
conversational
text-generation-inference
Model card Files
xet
 Community
aynetdia commited on
Commit
ecaf100
·
verified ·
1 Parent(s): c0f494a

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. added_tokens.json +5 -0
  2. chat_template.jinja +20 -0
  3. config.json +30 -0
  4. generation_config.json +9 -0
  5. merges.txt +0 -0
  6. model.safetensors +3 -0
  7. special_tokens_map.json +53 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +58 -0
  10. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 32002,
3
+ "<|system|>": 32000,
4
+ "<|user|>": 32001
5
+ }
chat_template.jinja ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if messages[0]['role'] != 'system' -%}
2
+ {%- set messages = [{'role': 'system', 'content': 'Du bist ein hilfreicher KI-Assistent.'}] + messages -%}
3
+ {%- endif -%}
4
+ {%- for message in messages -%}
5
+ {%- if message['role'] == 'user' -%}
6
+ {{ '<|user|>
7
+ ' + message['content'] + eos_token }}
8
+ {%- elif message['role'] == 'system' -%}
9
+ {{ '<|system|>
10
+ ' + message['content'] + eos_token }}
11
+ {%- elif message['role'] == 'assistant' -%}
12
+ {% generation %}{{ '<|assistant|>
13
+ ' + message['content'] + eos_token }}{% endgeneration %}
14
+ {%- endif -%}
15
+ {%- endfor -%}
16
+ {%- if add_generation_prompt -%}
17
+ {{ '<|assistant|>
18
+ ' }}
19
+ {%- endif -%}
20
+
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 0,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8192,
15
+ "max_position_embeddings": 4096,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 16,
20
+ "num_key_value_heads": 16,
21
+ "pad_token_id": 1,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "tie_word_embeddings": false,
27
+ "transformers_version": "4.57.3",
28
+ "use_cache": true,
29
+ "vocab_size": 32064
30
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": [
5
+ 0
6
+ ],
7
+ "pad_token_id": 1,
8
+ "transformers_version": "4.57.3"
9
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bcc7ed8bd9a5b2846ce09d7d654f946335b11ea19f7263d5c1136543dccc7a5
3
+ size 2410304008
special_tokens_map.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|system|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|user|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<|assistant|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ ],
25
+ "bos_token": {
26
+ "content": "<|endoftext|>",
27
+ "lstrip": false,
28
+ "normalized": true,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "eos_token": {
33
+ "content": "<|endoftext|>",
34
+ "lstrip": false,
35
+ "normalized": true,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
+ "pad_token": {
40
+ "content": "<|pad|>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "unk_token": {
47
+ "content": "<|endoftext|>",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ }
53
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|pad|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "32000": {
21
+ "content": "<|system|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "32001": {
29
+ "content": "<|user|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "32002": {
37
+ "content": "<|assistant|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "additional_special_tokens": [
46
+ "<|system|>",
47
+ "<|user|>",
48
+ "<|assistant|>"
49
+ ],
50
+ "bos_token": "<|endoftext|>",
51
+ "clean_up_tokenization_spaces": false,
52
+ "eos_token": "<|endoftext|>",
53
+ "extra_special_tokens": {},
54
+ "model_max_length": 4096,
55
+ "pad_token": "<|pad|>",
56
+ "tokenizer_class": "GPT2Tokenizer",
57
+ "unk_token": "<|endoftext|>"
58
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff