Upload folder using huggingface_hub
Browse files- README.md +28 -0
- config.json +30 -0
- mergekit_config.yml +12 -0
- model-00001-of-00001.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +207 -0
README.md
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- merge
|
4 |
+
- mergekit
|
5 |
+
- lazymergekit
|
6 |
+
- btherien/JOB-3150994_410M_it-132366_tr-pile-train_scratch
|
7 |
+
License: apache-2.0
|
8 |
+
---
|
9 |
+
|
10 |
+
# 405M_TIES-merge_pile_300B_into_slimp_300B_from_pile_replay5_density-0.75
|
11 |
+
|
12 |
+
405M_TIES-merge_pile_300B_into_slimp_300B_from_pile_replay5_density-0.75 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|
13 |
+
* [btherien/JOB-3150994_410M_it-132366_tr-pile-train_scratch](https://huggingface.co/btherien/JOB-3150994_410M_it-132366_tr-pile-train_scratch)
|
14 |
+
|
15 |
+
## 🧩 Configuration
|
16 |
+
|
17 |
+
\```yamlmodels:
|
18 |
+
- model: btherien/Model_-410M_It_-132366_Tr_-slim-pajama-300B-replay5_finetune
|
19 |
+
# no parameters necessary for base model
|
20 |
+
- model: btherien/JOB-3150994_410M_it-132366_tr-pile-train_scratch
|
21 |
+
parameters:
|
22 |
+
density: 0.75
|
23 |
+
weight: 1.0
|
24 |
+
merge_method: ties
|
25 |
+
base_model: btherien/Model_-410M_It_-132366_Tr_-slim-pajama-300B-replay5_finetune
|
26 |
+
parameters:
|
27 |
+
normalize: true
|
28 |
+
dtype: float16\```
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "btherien/Model_-410M_It_-132366_Tr_-slim-pajama-300B-replay5_finetune",
|
3 |
+
"architectures": [
|
4 |
+
"GPTNeoXForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": true,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": 0.1,
|
10 |
+
"eos_token_id": 0,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout": 0.0,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 4096,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"max_position_embeddings": 2048,
|
18 |
+
"model_type": "gpt_neox",
|
19 |
+
"num_attention_heads": 16,
|
20 |
+
"num_hidden_layers": 24,
|
21 |
+
"rope_scaling": null,
|
22 |
+
"rotary_emb_base": 10000,
|
23 |
+
"rotary_pct": 0.25,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "float16",
|
26 |
+
"transformers_version": "4.38.2",
|
27 |
+
"use_cache": true,
|
28 |
+
"use_parallel_residual": true,
|
29 |
+
"vocab_size": 50304
|
30 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
models:
|
2 |
+
- model: btherien/Model_-410M_It_-132366_Tr_-slim-pajama-300B-replay5_finetune
|
3 |
+
# no parameters necessary for base model
|
4 |
+
- model: btherien/JOB-3150994_410M_it-132366_tr-pile-train_scratch
|
5 |
+
parameters:
|
6 |
+
density: 0.75
|
7 |
+
weight: 1.0
|
8 |
+
merge_method: ties
|
9 |
+
base_model: btherien/Model_-410M_It_-132366_Tr_-slim-pajama-300B-replay5_finetune
|
10 |
+
parameters:
|
11 |
+
normalize: true
|
12 |
+
dtype: float16
|
model-00001-of-00001.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:673cf3e624560b00186f1b86668d799528094d17b8717ef9839bf4bbd258c32c
|
3 |
+
size 810701896
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"embed_out.weight": "model-00001-of-00001.safetensors", "gpt_neox.final_layer_norm.weight": "model-00001-of-00001.safetensors", "gpt_neox.final_layer_norm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.23.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.23.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.23.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.23.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.23.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.23.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.22.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.22.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.22.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.22.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.22.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.22.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.21.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.21.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.21.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.21.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.21.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.21.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.20.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.20.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.20.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.20.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.20.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.20.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.19.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.19.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.19.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.19.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.19.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.19.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.18.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.18.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.18.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.18.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.18.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.18.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.17.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.17.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.17.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.17.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.17.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.17.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.16.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.16.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.16.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.16.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.16.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.16.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.15.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.15.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.15.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.15.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.15.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.15.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.14.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.14.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.14.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.14.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.14.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.14.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.13.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.13.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.13.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.13.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.13.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.13.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.12.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.12.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.12.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.12.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.12.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.12.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.11.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.11.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.11.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.11.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.11.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.11.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.10.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.10.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.10.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.10.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.10.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.10.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.9.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.9.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.9.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.9.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.9.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.9.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.8.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.8.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.8.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.8.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.8.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.8.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.7.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.7.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.7.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.7.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.7.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.7.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.6.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.6.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.6.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.6.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.6.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.6.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.5.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.5.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.5.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.5.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.5.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.5.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.4.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.4.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.4.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.4.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.4.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.4.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00001.safetensors", "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00001.safetensors", "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00001.safetensors", "gpt_neox.embed_in.weight": "model-00001-of-00001.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<|endoftext|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<|padding|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"50254": {
|
20 |
+
"content": " ",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": true,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": false
|
26 |
+
},
|
27 |
+
"50255": {
|
28 |
+
"content": " ",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": false
|
34 |
+
},
|
35 |
+
"50256": {
|
36 |
+
"content": " ",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": true,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": false
|
42 |
+
},
|
43 |
+
"50257": {
|
44 |
+
"content": " ",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": true,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": false
|
50 |
+
},
|
51 |
+
"50258": {
|
52 |
+
"content": " ",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": true,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": false
|
58 |
+
},
|
59 |
+
"50259": {
|
60 |
+
"content": " ",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": true,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": false
|
66 |
+
},
|
67 |
+
"50260": {
|
68 |
+
"content": " ",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": true,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": false
|
74 |
+
},
|
75 |
+
"50261": {
|
76 |
+
"content": " ",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": true,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": false
|
82 |
+
},
|
83 |
+
"50262": {
|
84 |
+
"content": " ",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": true,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": false
|
90 |
+
},
|
91 |
+
"50263": {
|
92 |
+
"content": " ",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": true,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": false
|
98 |
+
},
|
99 |
+
"50264": {
|
100 |
+
"content": " ",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": true,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": false
|
106 |
+
},
|
107 |
+
"50265": {
|
108 |
+
"content": " ",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": true,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": false
|
114 |
+
},
|
115 |
+
"50266": {
|
116 |
+
"content": " ",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": true,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": false
|
122 |
+
},
|
123 |
+
"50267": {
|
124 |
+
"content": " ",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": true,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": false
|
130 |
+
},
|
131 |
+
"50268": {
|
132 |
+
"content": " ",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": true,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": false
|
138 |
+
},
|
139 |
+
"50269": {
|
140 |
+
"content": " ",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": true,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": false
|
146 |
+
},
|
147 |
+
"50270": {
|
148 |
+
"content": " ",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": true,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": false
|
154 |
+
},
|
155 |
+
"50271": {
|
156 |
+
"content": " ",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": true,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": false
|
162 |
+
},
|
163 |
+
"50272": {
|
164 |
+
"content": " ",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": true,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": false
|
170 |
+
},
|
171 |
+
"50273": {
|
172 |
+
"content": " ",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": true,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": false
|
178 |
+
},
|
179 |
+
"50274": {
|
180 |
+
"content": " ",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": true,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": false
|
186 |
+
},
|
187 |
+
"50275": {
|
188 |
+
"content": " ",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": true,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": false
|
194 |
+
},
|
195 |
+
"50276": {
|
196 |
+
"content": " ",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": true,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": false
|
202 |
+
}
|
203 |
+
},
|
204 |
+
"clean_up_tokenization_spaces": true,
|
205 |
+
"model_max_length": 1000000000000000019884624838656,
|
206 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
207 |
+
}
|