RajuKandasamy commited on
Commit
7d277fb
1 Parent(s): 88f2d76

Upload GPTNeoXForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +40 -0
  2. generation_config.json +6 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./output",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": 0.1,
8
+ "custom_pipelines": {
9
+ "text-generation": {
10
+ "impl": "instruct_pipeline.InstructionTextGenerationPipeline",
11
+ "pt": "AutoModelForCausalLM",
12
+ "tf": "TFAutoModelForCausalLM"
13
+ }
14
+ },
15
+ "eos_token_id": 0,
16
+ "hidden_act": "gelu",
17
+ "hidden_size": 2560,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 10240,
20
+ "layer_norm_eps": 1e-05,
21
+ "max_position_embeddings": 2048,
22
+ "model_type": "gpt_neox",
23
+ "num_attention_heads": 32,
24
+ "num_hidden_layers": 32,
25
+ "pad_token_id": 0,
26
+ "quantization_config": {
27
+ "llm_int8_enable_fp32_cpu_offload": false,
28
+ "llm_int8_skip_modules": null,
29
+ "llm_int8_threshold": 6.0,
30
+ "load_in_8bit": true
31
+ },
32
+ "rotary_emb_base": 10000,
33
+ "rotary_pct": 0.25,
34
+ "tie_word_embeddings": false,
35
+ "torch_dtype": "float16",
36
+ "transformers_version": "4.29.2",
37
+ "use_cache": false,
38
+ "use_parallel_residual": true,
39
+ "vocab_size": 50285
40
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.29.2"
6
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba4297b568715b9fb297b35652c924396f2bcd3da1c330fe81f67dd32d8a11a8
3
+ size 3171014493