melino2000
commited on
Commit
•
fdbb1ff
1
Parent(s):
ce418fe
Upload folder using huggingface_hub
Browse files- README.md +112 -0
- config.json +29 -0
- mergekit_config.yml +84 -0
- model-00001-of-00001.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +42 -0
README.md
ADDED
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: []
|
3 |
+
library_name: transformers
|
4 |
+
tags:
|
5 |
+
- mergekit
|
6 |
+
- merge
|
7 |
+
|
8 |
+
---
|
9 |
+
# final_merge
|
10 |
+
|
11 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
12 |
+
|
13 |
+
## Merge Details
|
14 |
+
### Merge Method
|
15 |
+
|
16 |
+
This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064 as a base.
|
17 |
+
|
18 |
+
### Models Merged
|
19 |
+
|
20 |
+
The following models were included in the merge:
|
21 |
+
* /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
|
22 |
+
|
23 |
+
### Configuration
|
24 |
+
|
25 |
+
The following YAML configuration was used to produce this model:
|
26 |
+
|
27 |
+
```yaml
|
28 |
+
base_model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
|
29 |
+
dtype: bfloat16
|
30 |
+
merge_method: task_arithmetic
|
31 |
+
parameters:
|
32 |
+
int8_mask: 1.0
|
33 |
+
normalize: 0.0
|
34 |
+
slices:
|
35 |
+
- sources:
|
36 |
+
- layer_range: [0, 2]
|
37 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
|
38 |
+
parameters:
|
39 |
+
weight: 0.9572415069321948
|
40 |
+
- layer_range: [0, 2]
|
41 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
|
42 |
+
- sources:
|
43 |
+
- layer_range: [2, 4]
|
44 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
|
45 |
+
parameters:
|
46 |
+
weight: 1.3027552693206474
|
47 |
+
- layer_range: [2, 4]
|
48 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
|
49 |
+
- sources:
|
50 |
+
- layer_range: [4, 6]
|
51 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
|
52 |
+
parameters:
|
53 |
+
weight: 1.1000872891940183
|
54 |
+
- layer_range: [4, 6]
|
55 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
|
56 |
+
- sources:
|
57 |
+
- layer_range: [6, 8]
|
58 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
|
59 |
+
parameters:
|
60 |
+
weight: 0.8472430654902018
|
61 |
+
- layer_range: [6, 8]
|
62 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
|
63 |
+
- sources:
|
64 |
+
- layer_range: [8, 10]
|
65 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
|
66 |
+
parameters:
|
67 |
+
weight: 0.9915310236895785
|
68 |
+
- layer_range: [8, 10]
|
69 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
|
70 |
+
- sources:
|
71 |
+
- layer_range: [10, 12]
|
72 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
|
73 |
+
parameters:
|
74 |
+
weight: 1.1144858726152178
|
75 |
+
- layer_range: [10, 12]
|
76 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
|
77 |
+
- sources:
|
78 |
+
- layer_range: [12, 14]
|
79 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
|
80 |
+
parameters:
|
81 |
+
weight: 0.8140779929520541
|
82 |
+
- layer_range: [12, 14]
|
83 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
|
84 |
+
- sources:
|
85 |
+
- layer_range: [14, 16]
|
86 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
|
87 |
+
parameters:
|
88 |
+
weight: 1.1599951316231072
|
89 |
+
- layer_range: [14, 16]
|
90 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
|
91 |
+
- sources:
|
92 |
+
- layer_range: [16, 18]
|
93 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
|
94 |
+
parameters:
|
95 |
+
weight: 0.5993074778392211
|
96 |
+
- layer_range: [16, 18]
|
97 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
|
98 |
+
- sources:
|
99 |
+
- layer_range: [18, 20]
|
100 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
|
101 |
+
parameters:
|
102 |
+
weight: 0.8145134707653817
|
103 |
+
- layer_range: [18, 20]
|
104 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
|
105 |
+
- sources:
|
106 |
+
- layer_range: [20, 22]
|
107 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
|
108 |
+
parameters:
|
109 |
+
weight: 0.9579703282891905
|
110 |
+
- layer_range: [20, 22]
|
111 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
|
112 |
+
```
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 2048,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 5632,
|
14 |
+
"max_position_embeddings": 2048,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "llama",
|
17 |
+
"num_attention_heads": 32,
|
18 |
+
"num_hidden_layers": 22,
|
19 |
+
"num_key_value_heads": 4,
|
20 |
+
"pretraining_tp": 1,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_scaling": null,
|
23 |
+
"rope_theta": 10000.0,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "bfloat16",
|
26 |
+
"transformers_version": "4.44.0",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 32000
|
29 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
base_model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
|
2 |
+
dtype: bfloat16
|
3 |
+
merge_method: task_arithmetic
|
4 |
+
parameters:
|
5 |
+
int8_mask: 1.0
|
6 |
+
normalize: 0.0
|
7 |
+
slices:
|
8 |
+
- sources:
|
9 |
+
- layer_range: [0, 2]
|
10 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
|
11 |
+
parameters:
|
12 |
+
weight: 0.9572415069321948
|
13 |
+
- layer_range: [0, 2]
|
14 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
|
15 |
+
- sources:
|
16 |
+
- layer_range: [2, 4]
|
17 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
|
18 |
+
parameters:
|
19 |
+
weight: 1.3027552693206474
|
20 |
+
- layer_range: [2, 4]
|
21 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
|
22 |
+
- sources:
|
23 |
+
- layer_range: [4, 6]
|
24 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
|
25 |
+
parameters:
|
26 |
+
weight: 1.1000872891940183
|
27 |
+
- layer_range: [4, 6]
|
28 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
|
29 |
+
- sources:
|
30 |
+
- layer_range: [6, 8]
|
31 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
|
32 |
+
parameters:
|
33 |
+
weight: 0.8472430654902018
|
34 |
+
- layer_range: [6, 8]
|
35 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
|
36 |
+
- sources:
|
37 |
+
- layer_range: [8, 10]
|
38 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
|
39 |
+
parameters:
|
40 |
+
weight: 0.9915310236895785
|
41 |
+
- layer_range: [8, 10]
|
42 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
|
43 |
+
- sources:
|
44 |
+
- layer_range: [10, 12]
|
45 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
|
46 |
+
parameters:
|
47 |
+
weight: 1.1144858726152178
|
48 |
+
- layer_range: [10, 12]
|
49 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
|
50 |
+
- sources:
|
51 |
+
- layer_range: [12, 14]
|
52 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
|
53 |
+
parameters:
|
54 |
+
weight: 0.8140779929520541
|
55 |
+
- layer_range: [12, 14]
|
56 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
|
57 |
+
- sources:
|
58 |
+
- layer_range: [14, 16]
|
59 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
|
60 |
+
parameters:
|
61 |
+
weight: 1.1599951316231072
|
62 |
+
- layer_range: [14, 16]
|
63 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
|
64 |
+
- sources:
|
65 |
+
- layer_range: [16, 18]
|
66 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
|
67 |
+
parameters:
|
68 |
+
weight: 0.5993074778392211
|
69 |
+
- layer_range: [16, 18]
|
70 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
|
71 |
+
- sources:
|
72 |
+
- layer_range: [18, 20]
|
73 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
|
74 |
+
parameters:
|
75 |
+
weight: 0.8145134707653817
|
76 |
+
- layer_range: [18, 20]
|
77 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
|
78 |
+
- sources:
|
79 |
+
- layer_range: [20, 22]
|
80 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_chinese_1905817950
|
81 |
+
parameters:
|
82 |
+
weight: 0.9579703282891905
|
83 |
+
- layer_range: [20, 22]
|
84 |
+
model: /home/m_nobakhtian/evol_merge_storage/input_models/TinyLlama_v1.1_684560064
|
model-00001-of-00001.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d4480255bb3eeae421b75a8a7e2d2b7365d397c90c686eae7ef179eac7ce3de
|
3 |
+
size 2200119864
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 2200096768}, "weight_map": {"lm_head.weight": "model-00001-of-00001.safetensors", "model.embed_tokens.weight": "model-00001-of-00001.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.norm.weight": "model-00001-of-00001.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": false,
|
35 |
+
"model_max_length": 1000000000000000019884624838656,
|
36 |
+
"pad_token": null,
|
37 |
+
"padding_side": "right",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false
|
42 |
+
}
|