GardeniaM commited on
Commit
b79d62f
1 Parent(s): f12fd9e

Upload 6 files

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ llm-jp-3-1-8b.nemo filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "None",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 7168,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 24,
18
+ "num_key_value_heads": 16,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.40.0",
26
+ "use_cache": true,
27
+ "vocab_size": 99584
28
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.40.0"
6
+ }
llm-jp-3-1-8b.nemo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7a8b2ddeec3a13f072652e2baf3712af551808eabecc494789f76b486e686a4
3
+ size 5145006080
special_tokens_map.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<CLS|LLM-jp>",
4
+ "eod_token": "</s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": "<MASK|LLM-jp>",
7
+ "pad_token": "<PAD|LLM-jp>",
8
+ "sep_token": "<SEP|LLM-jp>",
9
+ "unk_token": "<unk>"
10
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "unk_token": "<unk>",
5
+ "bos_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "pad_token": "<PAD|LLM-jp>",
8
+ "cls_token": "<CLS|LLM-jp>",
9
+ "sep_token": "<SEP|LLM-jp>",
10
+ "eod_token": "</s>",
11
+ "mask_token": "<MASK|LLM-jp>",
12
+ "extra_ids": 0,
13
+ "sp_model_kwargs": {},
14
+ "model_max_length": 1000000000000000019884624838656,
15
+ "clean_up_tokenization_spaces": false,
16
+ "special_tokens_map_file": null,
17
+ "tokenizer_class": "PreTrainedTokenizerFast"
18
+ }