Text Generation
Transformers
Safetensors
English
German
llama
goliath
deutsch
llama2
discoresearch
Inference Endpoints
text-generation-inference
LoneStriker commited on
Commit
2ba9dbb
1 Parent(s): f8d9bd3

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -4,8 +4,8 @@
4
  "LlamaForCausalLM"
5
  ],
6
  "attention_bias": false,
7
- "bos_token_id": 1,
8
- "eos_token_id": 2,
9
  "hidden_act": "silu",
10
  "hidden_size": 8192,
11
  "initializer_range": 0.02,
 
4
  "LlamaForCausalLM"
5
  ],
6
  "attention_bias": false,
7
+ "bos_token_id": 32001,
8
+ "eos_token_id": 32000,
9
  "hidden_act": "silu",
10
  "hidden_size": 8192,
11
  "initializer_range": 0.02,
config.json-orig ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bjoernp/leo-big",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 8192,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 28672,
13
+ "max_position_embeddings": 8192,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 64,
16
+ "num_hidden_layers": 80,
17
+ "num_key_value_heads": 8,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": {
21
+ "factor": 2.0,
22
+ "type": "linear"
23
+ },
24
+ "rope_theta": 10000.0,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float16",
27
+ "transformers_version": "4.35.2",
28
+ "use_cache": true,
29
+ "vocab_size": 32032
30
+ }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "add_bos_token": true,
3
- "add_eos_token": false,
4
  "added_tokens_decoder": {
5
  "0": {
6
  "content": "<unk>",
 
1
  {
2
  "add_bos_token": true,
3
+ "add_eos_token": true,
4
  "added_tokens_decoder": {
5
  "0": {
6
  "content": "<unk>",
tokenizer_config.json-orig ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "32000": {
30
+ "content": "<|im_end|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|im_start|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ }
45
+ },
46
+ "bos_token": "<s>",
47
+ "clean_up_tokenization_spaces": false,
48
+ "eos_token": "<|im_end|>",
49
+ "legacy": false,
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "</s>",
52
+ "padding_side": "right",
53
+ "sp_model_kwargs": {},
54
+ "spaces_between_special_tokens": false,
55
+ "tokenizer_class": "LlamaTokenizer",
56
+ "trust_remote_code": true,
57
+ "unk_token": "<unk>",
58
+ "use_default_system_prompt": true,
59
+ "use_fast": false
60
+ }