Upload model
Browse files- config.json +55 -0
- generation_config.json +6 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Writer/InstructPalmyra-20b",
|
3 |
+
"activation_function": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.008165,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_embd": 6144,
|
15 |
+
"n_head": 48,
|
16 |
+
"n_inner": 24576,
|
17 |
+
"n_layer": 44,
|
18 |
+
"n_positions": 2048,
|
19 |
+
"quantization_config": {
|
20 |
+
"batch_size": 1,
|
21 |
+
"bits": 2,
|
22 |
+
"block_name_to_quantize": "transformer.h",
|
23 |
+
"damp_percent": 0.1,
|
24 |
+
"dataset": "c4-new",
|
25 |
+
"desc_act": false,
|
26 |
+
"disable_exllama": true,
|
27 |
+
"group_size": 128,
|
28 |
+
"max_input_length": 2048,
|
29 |
+
"model_seqlen": 2048,
|
30 |
+
"module_name_preceding_first_block": [
|
31 |
+
"transformer.wte",
|
32 |
+
"transformer.wpe",
|
33 |
+
"transformer.drop"
|
34 |
+
],
|
35 |
+
"pad_token_id": null,
|
36 |
+
"quant_method": "gptq",
|
37 |
+
"sym": true,
|
38 |
+
"tokenizer": null,
|
39 |
+
"true_sequential": true,
|
40 |
+
"use_cuda_fp16": true
|
41 |
+
},
|
42 |
+
"reorder_and_upcast_attn": false,
|
43 |
+
"resid_pdrop": 0.1,
|
44 |
+
"scale_attn_by_inverse_layer_idx": false,
|
45 |
+
"scale_attn_weights": true,
|
46 |
+
"summary_activation": null,
|
47 |
+
"summary_first_dropout": 0.1,
|
48 |
+
"summary_proj_to_labels": true,
|
49 |
+
"summary_type": "cls_index",
|
50 |
+
"summary_use_proj": true,
|
51 |
+
"torch_dtype": "float16",
|
52 |
+
"transformers_version": "4.35.0.dev0",
|
53 |
+
"use_cache": true,
|
54 |
+
"vocab_size": 50258
|
55 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.35.0.dev0"
|
6 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:466aa684b0a9d7ba41265e8d223a76525901c2a04c00d55fcd60595c5853d06c
|
3 |
+
size 5990886538
|