Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- config.json +53 -0
- model-orig.onnx +3 -0
- model.data +3 -0
- model.onnx +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
model.data filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/nfs/scistore14/alistgrp/ekurtic/mpt_7b_gsm8k_final/TeacherFixed_frozenEmbedsNO_loss1.0CE_1.0KDlayerwise_oneshot_sparsegpt_sp80_4ep_lr1e-4_bs32_noGradClip_warmup20ba/training",
|
3 |
+
"architectures": [
|
4 |
+
"MPTForCausalLM"
|
5 |
+
],
|
6 |
+
"attn_config": {
|
7 |
+
"alibi": true,
|
8 |
+
"alibi_bias_max": 8,
|
9 |
+
"attn_impl": "torch",
|
10 |
+
"attn_pdrop": 0,
|
11 |
+
"attn_type": "multihead_attention",
|
12 |
+
"attn_uses_sequence_id": false,
|
13 |
+
"clip_qkv": null,
|
14 |
+
"prefix_lm": false,
|
15 |
+
"qk_ln": false,
|
16 |
+
"softmax_scale": null
|
17 |
+
},
|
18 |
+
"auto_map": {
|
19 |
+
"AutoConfig": "configuration_mpt.MPTConfig",
|
20 |
+
"AutoModelForCausalLM": "modeling_mpt.MPTForCausalLM"
|
21 |
+
},
|
22 |
+
"d_model": 4096,
|
23 |
+
"emb_pdrop": 0,
|
24 |
+
"embedding_fraction": 1.0,
|
25 |
+
"expansion_ratio": 4,
|
26 |
+
"init_config": {
|
27 |
+
"emb_init_std": null,
|
28 |
+
"emb_init_uniform_lim": null,
|
29 |
+
"fan_mode": "fan_in",
|
30 |
+
"init_div_is_residual": true,
|
31 |
+
"init_gain": 0,
|
32 |
+
"init_nonlinearity": "relu",
|
33 |
+
"init_std": 0.02,
|
34 |
+
"name": "kaiming_normal_",
|
35 |
+
"verbose": 0
|
36 |
+
},
|
37 |
+
"init_device": "cpu",
|
38 |
+
"learned_pos_emb": true,
|
39 |
+
"logit_scale": null,
|
40 |
+
"max_seq_len": 2048,
|
41 |
+
"model_type": "mpt",
|
42 |
+
"n_heads": 32,
|
43 |
+
"n_layers": 32,
|
44 |
+
"no_bias": true,
|
45 |
+
"norm_type": "low_precision_layernorm",
|
46 |
+
"resid_pdrop": 0,
|
47 |
+
"tokenizer_name": "EleutherAI/gpt-neox-20b",
|
48 |
+
"torch_dtype": "float32",
|
49 |
+
"transformers_version": "4.32.0.dev0",
|
50 |
+
"use_cache": false,
|
51 |
+
"verbose": 0,
|
52 |
+
"vocab_size": 50432
|
53 |
+
}
|
model-orig.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:439eb2abd46c86f163b0f44611650864371ef78751765a62b801edc4eef6c3c1
|
3 |
+
size 1479834
|
model.data
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a031e4ff26b13245d7c70b3a93a67cf1b828536f7c58fd61c409870491a46a1
|
3 |
+
size 6856916992
|
model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2dfc44fd545fee667c30ce83fb17a753dbd87662d86b93d8d8e1cc6a3bc4f946
|
3 |
+
size 1317861
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"eos_token": "<|endoftext|>",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|