DanceLab commited on
Commit
0de9143
1 Parent(s): cbed1e3

Upload LlamaForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +30 -0
  2. generation_config.json +7 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data3/lk/llm/model/pretrain_rezhihu_large_v5_0_49999_ckpt_convert/",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 1,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_position_embeddings": 2048,
13
+ "max_sequence_length": 2048,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "pad_token_id": -1,
18
+ "quantization_config": {
19
+ "llm_int8_enable_fp32_cpu_offload": false,
20
+ "llm_int8_skip_modules": null,
21
+ "llm_int8_threshold": 6.0,
22
+ "load_in_8bit": true
23
+ },
24
+ "rms_norm_eps": 1e-06,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float16",
27
+ "transformers_version": "4.29.2",
28
+ "use_cache": true,
29
+ "vocab_size": 50000
30
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": -1,
6
+ "transformers_version": "4.29.2"
7
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4e5755a3b2203512f06901ddd9c93f4611cf59e7b9e19b9a298170d44ac7ab5
3
+ size 7295850179