yujiepan commited on
Commit
173d98d
1 Parent(s): c3887f4

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "keyfan/grok-1-hf",
3
+ "architectures": [
4
+ "GrokForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "attn_output_multiplier": 0.08838834764831845,
8
+ "auto_map": {
9
+ "AutoConfig": "keyfan/grok-1-hf--configuration_grok.GrokConfig",
10
+ "AutoModelForCausalLM": "keyfan/grok-1-hf--modeling_grok.GrokForCausalLM"
11
+ },
12
+ "bos_token_id": 1,
13
+ "embedding_multiplier_scale": 78.38367176906169,
14
+ "eos_token_id": 2,
15
+ "hidden_act": "gelu_new",
16
+ "hidden_size": 4,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8,
19
+ "max_position_embeddings": 8192,
20
+ "model_type": "grok",
21
+ "num_attention_heads": 4,
22
+ "num_experts_per_tok": 2,
23
+ "num_hidden_layers": 2,
24
+ "num_key_value_heads": 2,
25
+ "num_local_experts": 8,
26
+ "output_multiplier_scale": 0.5773502691896257,
27
+ "output_router_logits": false,
28
+ "pad_token_id": 0,
29
+ "rms_norm_eps": 1e-05,
30
+ "rope_theta": 10000.0,
31
+ "router_aux_loss_coef": 0.02,
32
+ "sliding_window": null,
33
+ "torch_dtype": "float16",
34
+ "transformers_version": "4.38.1",
35
+ "use_cache": true,
36
+ "vocab_size": 131072
37
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.38.1"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:446c87c0d9bbd043a587abcf8cc916d2f9c88af13c9e75382ef4e919624ec4e9
3
+ size 1059424
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
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 sha256:5c69d7cbad192fa2c9d14e2a77fbfdc11597c68907b043ddb0260e3d28eddd7f
3
+ size 2229219
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": null,
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
+ }