Upload fine-tuned model
Browse files- README.md +45 -3
- config.json +26 -0
- mergekit_config.yml +16 -0
- model.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- vocab.txt +0 -0
README.md
CHANGED
@@ -1,3 +1,45 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- meta-llama/Meta-Llama-3-70B
|
4 |
+
library_name: transformers
|
5 |
+
tags:
|
6 |
+
- mergekit
|
7 |
+
- merge
|
8 |
+
|
9 |
+
---
|
10 |
+
# merged
|
11 |
+
|
12 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
13 |
+
|
14 |
+
## Merge Details
|
15 |
+
### Merge Method
|
16 |
+
|
17 |
+
This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
|
18 |
+
|
19 |
+
### Models Merged
|
20 |
+
|
21 |
+
The following models were included in the merge:
|
22 |
+
* [meta-llama/Meta-Llama-3-70B](https://huggingface.co/meta-llama/Meta-Llama-3-70B)
|
23 |
+
|
24 |
+
### Configuration
|
25 |
+
|
26 |
+
The following YAML configuration was used to produce this model:
|
27 |
+
|
28 |
+
```yaml
|
29 |
+
dtype: float16
|
30 |
+
merge_method: linear
|
31 |
+
slices:
|
32 |
+
- sources:
|
33 |
+
- layer_range: [0, 80]
|
34 |
+
model: meta-llama/Meta-Llama-3-70B
|
35 |
+
parameters:
|
36 |
+
weight: 1.0
|
37 |
+
- layer_range: [0, 80]
|
38 |
+
model: meta-llama/Meta-Llama-3-70B
|
39 |
+
parameters:
|
40 |
+
weight: 0.3
|
41 |
+
- layer_range: [0, 80]
|
42 |
+
model: meta-llama/Meta-Llama-3-70B
|
43 |
+
parameters:
|
44 |
+
weight: 0.5
|
45 |
+
```
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.41.2",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
dtype: float16
|
2 |
+
merge_method: linear
|
3 |
+
slices:
|
4 |
+
- sources:
|
5 |
+
- layer_range: [0, 80]
|
6 |
+
model: meta-llama/Meta-Llama-3-70B
|
7 |
+
parameters:
|
8 |
+
weight: 1.0
|
9 |
+
- layer_range: [0, 80]
|
10 |
+
model: meta-llama/Meta-Llama-3-70B
|
11 |
+
parameters:
|
12 |
+
weight: 0.3
|
13 |
+
- layer_range: [0, 80]
|
14 |
+
model: meta-llama/Meta-Llama-3-70B
|
15 |
+
parameters:
|
16 |
+
weight: 0.5
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b9f72943ca7b211f8eb12f184e4f3dd2755eb3623415b9c65d9eee6c3a07950
|
3 |
+
size 437958648
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 141107412992}, "weight_map": {"lm_head.weight": "model-00001-of-00030.safetensors", "model.embed_tokens.weight": "model-00001-of-00030.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00030.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00030.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00030.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00030.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00030.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00030.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00030.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00030.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00030.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00030.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00030.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00030.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00030.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00030.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00030.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00030.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00030.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00030.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00030.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00030.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00030.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00030.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00030.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00030.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00030.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00030.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00030.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00030.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00030.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00030.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00030.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00030.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00030.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00030.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00030.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00030.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00030.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00030.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00030.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00030.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00030.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00030.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00030.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00030.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00030.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00030.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00030.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00030.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00030.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00030.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00030.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00030.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00030.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00030.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00030.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00030.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00030.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00030.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00030.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00030.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00030.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00030.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00030.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00030.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00030.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00030.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00030.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00030.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00030.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00030.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00030.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00030.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00030.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00030.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00030.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00030.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00030.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00030.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00030.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00030.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00030.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00030.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00030.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00030.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00030.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00030.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00030.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00030.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00030.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00030.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00030.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00030.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00030.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00030.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00030.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00030.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00030.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00030.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00030.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00030.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00030.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00030.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00030.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00030.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00030.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00030.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00030.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00030.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00030.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00030.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00030.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00030.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00030.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00030.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00030.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00030.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00030.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00030.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00030.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00030.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00030.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00030.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00030.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00030.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00030.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00030.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00030.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00030.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00030.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00030.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00030.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00030.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00030.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00030.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00030.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00030.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00030.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00030.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00007-of-00030.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00030.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00030.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00030.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00030.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00030.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00030.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00030.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00030.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00007-of-00030.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00030.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00030.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00030.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00030.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00030.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00030.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00030.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00030.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00030.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00030.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00030.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00030.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00030.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00030.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00030.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00008-of-00030.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00030.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00008-of-00030.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00030.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00030.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00030.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00030.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00030.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00030.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00030.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00030.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00008-of-00030.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00030.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00030.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00030.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00030.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00030.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00030.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00030.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00030.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00030.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00030.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00030.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00030.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00030.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00030.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00030.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00009-of-00030.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00030.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00009-of-00030.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00030.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00030.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00030.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00030.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00030.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00030.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00009-of-00030.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00030.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00009-of-00030.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00030.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00030.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00030.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00030.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00030.safetensors", "model.layers.3.input_layernorm.weight": "model-00010-of-00030.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00010-of-00030.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00010-of-00030.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00010-of-00030.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00010-of-00030.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00030.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00010-of-00030.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00010-of-00030.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00010-of-00030.safetensors", "model.layers.30.input_layernorm.weight": "model-00010-of-00030.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00010-of-00030.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00030.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00010-of-00030.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00030.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00030.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00030.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00030.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00030.safetensors", "model.layers.31.input_layernorm.weight": "model-00010-of-00030.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00010-of-00030.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00010-of-00030.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00030.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00030.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00030.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00030.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00030.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00030.safetensors", "model.layers.32.input_layernorm.weight": "model-00011-of-00030.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00011-of-00030.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00030.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00011-of-00030.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00030.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00030.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00030.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00030.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00030.safetensors", "model.layers.33.input_layernorm.weight": "model-00011-of-00030.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00011-of-00030.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00011-of-00030.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00011-of-00030.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00011-of-00030.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00011-of-00030.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00011-of-00030.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00011-of-00030.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00011-of-00030.safetensors", "model.layers.34.input_layernorm.weight": "model-00011-of-00030.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00011-of-00030.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00030.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00012-of-00030.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00030.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00030.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00030.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00030.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00030.safetensors", "model.layers.35.input_layernorm.weight": "model-00012-of-00030.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00012-of-00030.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00030.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00012-of-00030.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00030.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00030.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00030.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00030.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00030.safetensors", "model.layers.36.input_layernorm.weight": "model-00012-of-00030.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00012-of-00030.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00012-of-00030.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00012-of-00030.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00012-of-00030.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00030.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00012-of-00030.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00030.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00030.safetensors", "model.layers.37.input_layernorm.weight": "model-00012-of-00030.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00013-of-00030.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00030.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00013-of-00030.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00013-of-00030.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00030.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00030.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00030.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00030.safetensors", "model.layers.38.input_layernorm.weight": "model-00013-of-00030.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00013-of-00030.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00030.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00013-of-00030.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00013-of-00030.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00030.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00030.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00030.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00030.safetensors", "model.layers.39.input_layernorm.weight": "model-00013-of-00030.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00013-of-00030.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00013-of-00030.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00013-of-00030.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00013-of-00030.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00013-of-00030.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00013-of-00030.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00014-of-00030.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00014-of-00030.safetensors", "model.layers.4.input_layernorm.weight": "model-00014-of-00030.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00014-of-00030.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00014-of-00030.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00014-of-00030.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00014-of-00030.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00014-of-00030.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00014-of-00030.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00014-of-00030.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00014-of-00030.safetensors", "model.layers.40.input_layernorm.weight": "model-00014-of-00030.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00014-of-00030.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00014-of-00030.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00014-of-00030.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00014-of-00030.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00014-of-00030.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00014-of-00030.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00014-of-00030.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00014-of-00030.safetensors", "model.layers.41.input_layernorm.weight": "model-00014-of-00030.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00014-of-00030.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00014-of-00030.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00014-of-00030.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00014-of-00030.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00014-of-00030.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00015-of-00030.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00015-of-00030.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00015-of-00030.safetensors", "model.layers.42.input_layernorm.weight": "model-00015-of-00030.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00015-of-00030.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00015-of-00030.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00015-of-00030.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00015-of-00030.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00015-of-00030.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00015-of-00030.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00015-of-00030.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00015-of-00030.safetensors", "model.layers.43.input_layernorm.weight": "model-00015-of-00030.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00015-of-00030.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00015-of-00030.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00015-of-00030.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00015-of-00030.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00015-of-00030.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00015-of-00030.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00015-of-00030.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00015-of-00030.safetensors", "model.layers.44.input_layernorm.weight": "model-00015-of-00030.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00015-of-00030.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00015-of-00030.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00016-of-00030.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00016-of-00030.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00016-of-00030.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00016-of-00030.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00016-of-00030.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00016-of-00030.safetensors", "model.layers.45.input_layernorm.weight": "model-00016-of-00030.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00016-of-00030.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00016-of-00030.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00016-of-00030.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00016-of-00030.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00016-of-00030.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00016-of-00030.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00016-of-00030.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00016-of-00030.safetensors", "model.layers.46.input_layernorm.weight": "model-00016-of-00030.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00016-of-00030.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00016-of-00030.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00016-of-00030.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00016-of-00030.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00016-of-00030.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00016-of-00030.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00016-of-00030.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00016-of-00030.safetensors", "model.layers.47.input_layernorm.weight": "model-00016-of-00030.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00016-of-00030.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00017-of-00030.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00017-of-00030.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00017-of-00030.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00017-of-00030.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00017-of-00030.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00017-of-00030.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00017-of-00030.safetensors", "model.layers.48.input_layernorm.weight": "model-00017-of-00030.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00017-of-00030.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00017-of-00030.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00017-of-00030.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00017-of-00030.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00017-of-00030.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00017-of-00030.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00017-of-00030.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00017-of-00030.safetensors", "model.layers.49.input_layernorm.weight": "model-00017-of-00030.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00017-of-00030.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00017-of-00030.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00017-of-00030.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00017-of-00030.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00017-of-00030.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00017-of-00030.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00017-of-00030.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00017-of-00030.safetensors", "model.layers.5.input_layernorm.weight": "model-00017-of-00030.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00018-of-00030.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00018-of-00030.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00018-of-00030.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00018-of-00030.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00018-of-00030.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00018-of-00030.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00018-of-00030.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00018-of-00030.safetensors", "model.layers.50.input_layernorm.weight": "model-00018-of-00030.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00018-of-00030.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00018-of-00030.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00018-of-00030.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00018-of-00030.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00018-of-00030.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00018-of-00030.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00018-of-00030.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00018-of-00030.safetensors", "model.layers.51.input_layernorm.weight": "model-00018-of-00030.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00018-of-00030.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00018-of-00030.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00018-of-00030.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00018-of-00030.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00018-of-00030.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00018-of-00030.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00030.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00030.safetensors", "model.layers.52.input_layernorm.weight": "model-00019-of-00030.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00019-of-00030.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00019-of-00030.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00019-of-00030.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00019-of-00030.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00019-of-00030.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00019-of-00030.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00019-of-00030.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00019-of-00030.safetensors", "model.layers.53.input_layernorm.weight": "model-00019-of-00030.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00019-of-00030.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00019-of-00030.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00019-of-00030.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00019-of-00030.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00019-of-00030.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00019-of-00030.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00019-of-00030.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00019-of-00030.safetensors", "model.layers.54.input_layernorm.weight": "model-00019-of-00030.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00019-of-00030.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00019-of-00030.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00019-of-00030.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00019-of-00030.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00019-of-00030.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00030.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00030.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00030.safetensors", "model.layers.55.input_layernorm.weight": "model-00020-of-00030.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00020-of-00030.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00020-of-00030.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00020-of-00030.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00020-of-00030.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00020-of-00030.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00020-of-00030.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00020-of-00030.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00020-of-00030.safetensors", "model.layers.56.input_layernorm.weight": "model-00020-of-00030.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00020-of-00030.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00020-of-00030.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00020-of-00030.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00020-of-00030.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00020-of-00030.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00020-of-00030.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00020-of-00030.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00020-of-00030.safetensors", "model.layers.57.input_layernorm.weight": "model-00020-of-00030.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00020-of-00030.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00020-of-00030.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00021-of-00030.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00021-of-00030.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00030.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00030.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00030.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00030.safetensors", "model.layers.58.input_layernorm.weight": "model-00021-of-00030.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00021-of-00030.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00021-of-00030.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00021-of-00030.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00021-of-00030.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00021-of-00030.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00021-of-00030.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00021-of-00030.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00021-of-00030.safetensors", "model.layers.59.input_layernorm.weight": "model-00021-of-00030.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00021-of-00030.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00021-of-00030.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00021-of-00030.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00021-of-00030.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00021-of-00030.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00021-of-00030.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00021-of-00030.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00021-of-00030.safetensors", "model.layers.6.input_layernorm.weight": "model-00021-of-00030.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00021-of-00030.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00022-of-00030.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00022-of-00030.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00022-of-00030.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00022-of-00030.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00022-of-00030.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00022-of-00030.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00022-of-00030.safetensors", "model.layers.60.input_layernorm.weight": "model-00022-of-00030.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00022-of-00030.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00022-of-00030.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00022-of-00030.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00022-of-00030.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00030.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00022-of-00030.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00022-of-00030.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00022-of-00030.safetensors", "model.layers.61.input_layernorm.weight": "model-00022-of-00030.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00022-of-00030.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00022-of-00030.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00022-of-00030.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00022-of-00030.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00022-of-00030.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00022-of-00030.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00022-of-00030.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00022-of-00030.safetensors", "model.layers.62.input_layernorm.weight": "model-00022-of-00030.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00023-of-00030.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00023-of-00030.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00023-of-00030.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00030.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00030.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00030.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00030.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00030.safetensors", "model.layers.63.input_layernorm.weight": "model-00023-of-00030.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00023-of-00030.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00023-of-00030.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00023-of-00030.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00023-of-00030.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00023-of-00030.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00023-of-00030.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00023-of-00030.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00023-of-00030.safetensors", "model.layers.64.input_layernorm.weight": "model-00023-of-00030.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00023-of-00030.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00023-of-00030.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00023-of-00030.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00023-of-00030.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00023-of-00030.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00023-of-00030.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00024-of-00030.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00030.safetensors", "model.layers.65.input_layernorm.weight": "model-00024-of-00030.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00024-of-00030.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00024-of-00030.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00024-of-00030.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00024-of-00030.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00024-of-00030.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00024-of-00030.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00030.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00030.safetensors", "model.layers.66.input_layernorm.weight": "model-00024-of-00030.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00024-of-00030.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00024-of-00030.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00024-of-00030.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00024-of-00030.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00024-of-00030.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00024-of-00030.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00024-of-00030.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00024-of-00030.safetensors", "model.layers.67.input_layernorm.weight": "model-00024-of-00030.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00024-of-00030.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00024-of-00030.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00024-of-00030.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00024-of-00030.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00024-of-00030.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00030.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00030.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00030.safetensors", "model.layers.68.input_layernorm.weight": "model-00025-of-00030.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00025-of-00030.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00025-of-00030.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00025-of-00030.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00025-of-00030.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00025-of-00030.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00025-of-00030.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00025-of-00030.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00030.safetensors", "model.layers.69.input_layernorm.weight": "model-00025-of-00030.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00025-of-00030.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00025-of-00030.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00025-of-00030.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00025-of-00030.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00025-of-00030.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00025-of-00030.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00025-of-00030.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00025-of-00030.safetensors", "model.layers.7.input_layernorm.weight": "model-00025-of-00030.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00025-of-00030.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00025-of-00030.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00026-of-00030.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00026-of-00030.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00026-of-00030.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00026-of-00030.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00026-of-00030.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00026-of-00030.safetensors", "model.layers.70.input_layernorm.weight": "model-00026-of-00030.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00026-of-00030.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00026-of-00030.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00026-of-00030.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00026-of-00030.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00026-of-00030.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00026-of-00030.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00026-of-00030.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00026-of-00030.safetensors", "model.layers.71.input_layernorm.weight": "model-00026-of-00030.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00026-of-00030.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00026-of-00030.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00026-of-00030.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00026-of-00030.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00026-of-00030.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00026-of-00030.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00026-of-00030.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00026-of-00030.safetensors", "model.layers.72.input_layernorm.weight": "model-00026-of-00030.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00026-of-00030.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00027-of-00030.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00027-of-00030.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00027-of-00030.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00027-of-00030.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00027-of-00030.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00027-of-00030.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00027-of-00030.safetensors", "model.layers.73.input_layernorm.weight": "model-00027-of-00030.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00027-of-00030.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00030.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00027-of-00030.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00027-of-00030.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00027-of-00030.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00027-of-00030.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00027-of-00030.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00027-of-00030.safetensors", "model.layers.74.input_layernorm.weight": "model-00027-of-00030.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00027-of-00030.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00027-of-00030.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00027-of-00030.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00027-of-00030.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00027-of-00030.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00027-of-00030.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00027-of-00030.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00027-of-00030.safetensors", "model.layers.75.input_layernorm.weight": "model-00027-of-00030.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00028-of-00030.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00030.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00028-of-00030.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00030.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00030.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00030.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00030.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00030.safetensors", "model.layers.76.input_layernorm.weight": "model-00028-of-00030.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00028-of-00030.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00028-of-00030.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00028-of-00030.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00028-of-00030.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00028-of-00030.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00028-of-00030.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00028-of-00030.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00028-of-00030.safetensors", "model.layers.77.input_layernorm.weight": "model-00028-of-00030.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00028-of-00030.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00028-of-00030.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00028-of-00030.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00028-of-00030.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00028-of-00030.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00028-of-00030.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00029-of-00030.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00029-of-00030.safetensors", "model.layers.78.input_layernorm.weight": "model-00029-of-00030.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00029-of-00030.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00029-of-00030.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00029-of-00030.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00029-of-00030.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00029-of-00030.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00030.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00029-of-00030.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00029-of-00030.safetensors", "model.layers.79.input_layernorm.weight": "model-00029-of-00030.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00029-of-00030.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00029-of-00030.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00029-of-00030.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00029-of-00030.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00029-of-00030.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00029-of-00030.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00029-of-00030.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00029-of-00030.safetensors", "model.layers.8.input_layernorm.weight": "model-00029-of-00030.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00029-of-00030.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00029-of-00030.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00029-of-00030.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00029-of-00030.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00029-of-00030.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00030-of-00030.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00030-of-00030.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00030-of-00030.safetensors", "model.layers.9.input_layernorm.weight": "model-00030-of-00030.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00030-of-00030.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00030-of-00030.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00030-of-00030.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00030-of-00030.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00030-of-00030.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00030-of-00030.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00030-of-00030.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00030-of-00030.safetensors", "model.norm.weight": "model-00030-of-00030.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|