Upload GPTNeoXForCausalLM
Browse files- config.json +32 -0
- generation_config.json +6 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "zh-tw-llm-dv/zh-tw-llm-ta01-pythia-6.9b-ta8000-v1-a_1_embeddings-h100-t01-c5daa1",
|
3 |
+
"architectures": [
|
4 |
+
"GPTNeoXForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"classifier_dropout": 0.1,
|
8 |
+
"eos_token_id": 0,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 16384,
|
13 |
+
"layer_norm_eps": 1e-05,
|
14 |
+
"max_position_embeddings": 2048,
|
15 |
+
"model_type": "gpt_neox",
|
16 |
+
"num_attention_heads": 32,
|
17 |
+
"num_hidden_layers": 32,
|
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 |
+
"rotary_emb_base": 10000,
|
25 |
+
"rotary_pct": 0.25,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"torch_dtype": "float16",
|
28 |
+
"transformers_version": "4.29.2",
|
29 |
+
"use_cache": true,
|
30 |
+
"use_parallel_residual": true,
|
31 |
+
"vocab_size": 58113
|
32 |
+
}
|
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 sha256:8e122cb11c35118908ac9187868c71c5f667c147c1fa8c62fedee6b5633ca70f
|
3 |
+
size 7537144713
|