Upload GPTNeoXForSequenceClassification
Browse files- config.json +6 -17
- pytorch_model.bin +2 -2
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"GPTNeoXForSequenceClassification"
|
5 |
],
|
@@ -9,31 +9,20 @@
|
|
9 |
"eos_token_id": 0,
|
10 |
"hidden_act": "gelu",
|
11 |
"hidden_dropout": 0.0,
|
12 |
-
"hidden_size":
|
13 |
"initializer_range": 0.02,
|
14 |
-
"intermediate_size":
|
15 |
"layer_norm_eps": 1e-05,
|
16 |
"max_position_embeddings": 2048,
|
17 |
"model_type": "gpt_neox",
|
18 |
-
"num_attention_heads":
|
19 |
-
"num_hidden_layers":
|
20 |
"pad_token_id": 0,
|
21 |
-
"quantization_config": {
|
22 |
-
"bnb_4bit_compute_dtype": "float32",
|
23 |
-
"bnb_4bit_quant_type": "fp4",
|
24 |
-
"bnb_4bit_use_double_quant": false,
|
25 |
-
"llm_int8_enable_fp32_cpu_offload": false,
|
26 |
-
"llm_int8_has_fp16_weight": false,
|
27 |
-
"llm_int8_skip_modules": null,
|
28 |
-
"llm_int8_threshold": 6.0,
|
29 |
-
"load_in_4bit": false,
|
30 |
-
"load_in_8bit": true
|
31 |
-
},
|
32 |
"rope_scaling": null,
|
33 |
"rotary_emb_base": 10000,
|
34 |
"rotary_pct": 1.0,
|
35 |
"tie_word_embeddings": false,
|
36 |
-
"torch_dtype": "
|
37 |
"transformers_version": "4.32.0.dev0",
|
38 |
"use_cache": true,
|
39 |
"use_parallel_residual": false,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "output/checkpoint-30/",
|
3 |
"architectures": [
|
4 |
"GPTNeoXForSequenceClassification"
|
5 |
],
|
|
|
9 |
"eos_token_id": 0,
|
10 |
"hidden_act": "gelu",
|
11 |
"hidden_dropout": 0.0,
|
12 |
+
"hidden_size": 768,
|
13 |
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
"layer_norm_eps": 1e-05,
|
16 |
"max_position_embeddings": 2048,
|
17 |
"model_type": "gpt_neox",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
"pad_token_id": 0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
"rope_scaling": null,
|
22 |
"rotary_emb_base": 10000,
|
23 |
"rotary_pct": 1.0,
|
24 |
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "float32",
|
26 |
"transformers_version": "4.32.0.dev0",
|
27 |
"use_cache": true,
|
28 |
"use_parallel_residual": false,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a18d098aa70f569ae5dbc95fc715f412a3e8c0175a0cb1c9650df2cd36b4dc7
|
3 |
+
size 500322189
|