osiria commited on
Commit
b88917a
1 Parent(s): 2730bd8

Upload 7 files

Browse files
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "gelu",
4
+ "attention_dropout": 0.1,
5
+ "attention_heads": 32,
6
+ "bos_token_id": 0,
7
+ "d_model": 4096,
8
+ "decoder_start_token_id": 2,
9
+ "dropout": 0.1,
10
+ "eos_token_id": 2,
11
+ "ffn_dim": 16384,
12
+ "init_std": 0.02,
13
+ "layerdrop": 0.0,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "xglm",
16
+ "num_layers": 32,
17
+ "pad_token_id": 1,
18
+ "quantization_config": {
19
+ "bnb_4bit_compute_dtype": "float32",
20
+ "bnb_4bit_quant_type": "fp4",
21
+ "bnb_4bit_use_double_quant": false,
22
+ "llm_int8_enable_fp32_cpu_offload": false,
23
+ "llm_int8_has_fp16_weight": false,
24
+ "llm_int8_skip_modules": null,
25
+ "llm_int8_threshold": 6.0,
26
+ "load_in_4bit": false,
27
+ "load_in_8bit": true
28
+ },
29
+ "scale_embedding": true,
30
+ "torch_dtype": "float16",
31
+ "transformers_version": "4.30.1",
32
+ "use_cache": true,
33
+ "vocab_size": 50335
34
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "eos_token_id": 2,
6
+ "pad_token_id": 1,
7
+ "transformers_version": "4.30.1"
8
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6b76613d53b7775c497100ccd3d8d8385eb7a8a4582ad496ce3c3b69ccca95f
3
+ size 6863170295
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "sp_model_kwargs": {}, "vocab_type": "spm"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff