AlekseiPravdin
commited on
Commit
•
0f19b7a
1
Parent(s):
e4d7d8c
Upload folder using huggingface_hub
Browse files- README.md +34 -0
- config.json +27 -0
- mergekit_config.yml +16 -0
- model-00001-of-00015.safetensors +3 -0
- model-00002-of-00015.safetensors +3 -0
- model-00003-of-00015.safetensors +3 -0
- model-00004-of-00015.safetensors +3 -0
- model-00005-of-00015.safetensors +3 -0
- model-00006-of-00015.safetensors +3 -0
- model-00007-of-00015.safetensors +3 -0
- model-00008-of-00015.safetensors +3 -0
- model-00009-of-00015.safetensors +3 -0
- model-00010-of-00015.safetensors +3 -0
- model-00011-of-00015.safetensors +3 -0
- model-00012-of-00015.safetensors +3 -0
- model-00013-of-00015.safetensors +3 -0
- model-00014-of-00015.safetensors +3 -0
- model-00015-of-00015.safetensors +3 -0
- model.safetensors.index.json +1 -0
- slerp_config.yaml +16 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +43 -0
README.md
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- merge
|
5 |
+
- mergekit
|
6 |
+
- lazymergekit
|
7 |
+
- Nitral-AI/KukulStanta-7B
|
8 |
+
- AlekseiPravdin/Seamaiiza-7B-v1
|
9 |
+
---
|
10 |
+
|
11 |
+
# KukulStanta-Seamaiiza-slerp-merge5
|
12 |
+
|
13 |
+
KukulStanta-Seamaiiza-slerp-merge5 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|
14 |
+
* [Nitral-AI/KukulStanta-7B](https://huggingface.co/Nitral-AI/KukulStanta-7B)
|
15 |
+
* [AlekseiPravdin/Seamaiiza-7B-v1](https://huggingface.co/AlekseiPravdin/Seamaiiza-7B-v1)
|
16 |
+
|
17 |
+
## 🧩 Configuration
|
18 |
+
|
19 |
+
```yamlslices:
|
20 |
+
- sources:
|
21 |
+
- model: Nitral-AI/KukulStanta-7B
|
22 |
+
layer_range: [0, 31]
|
23 |
+
- model: AlekseiPravdin/Seamaiiza-7B-v1
|
24 |
+
layer_range: [0, 31]
|
25 |
+
merge_method: slerp
|
26 |
+
base_model: Nitral-AI/KukulStanta-7B
|
27 |
+
parameters:
|
28 |
+
t:
|
29 |
+
- filter: self_attn
|
30 |
+
value: [0, 0.5, 0.3, 0.7, 1]
|
31 |
+
- filter: mlp
|
32 |
+
value: [1, 0.5, 0.7, 0.3, 0]
|
33 |
+
- value: 0.5
|
34 |
+
dtype: float16
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Nitral-AI/KukulStanta-7B",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"head_dim": 128,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 14336,
|
14 |
+
"max_position_embeddings": 32768,
|
15 |
+
"model_type": "mistral",
|
16 |
+
"num_attention_heads": 32,
|
17 |
+
"num_hidden_layers": 31,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"rms_norm_eps": 1e-05,
|
20 |
+
"rope_theta": 10000.0,
|
21 |
+
"sliding_window": 4096,
|
22 |
+
"tie_word_embeddings": false,
|
23 |
+
"torch_dtype": "float16",
|
24 |
+
"transformers_version": "4.44.0",
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 32000
|
27 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
slices:
|
2 |
+
- sources:
|
3 |
+
- model: Nitral-AI/KukulStanta-7B
|
4 |
+
layer_range: [0, 31]
|
5 |
+
- model: AlekseiPravdin/Seamaiiza-7B-v1
|
6 |
+
layer_range: [0, 31]
|
7 |
+
merge_method: slerp
|
8 |
+
base_model: Nitral-AI/KukulStanta-7B
|
9 |
+
parameters:
|
10 |
+
t:
|
11 |
+
- filter: self_attn
|
12 |
+
value: [0, 0.5, 0.3, 0.7, 1]
|
13 |
+
- filter: mlp
|
14 |
+
value: [1, 0.5, 0.7, 0.3, 0]
|
15 |
+
- value: 0.5
|
16 |
+
dtype: float16
|
model-00001-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e88f0eccef1c8f02077fbd7b0ec8f26274c18f94a6fdd714efa64da8b890c26
|
3 |
+
size 960521544
|
model-00002-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b8b962c5805974f2e66941c48ccb81dabd5b59b6c8acbf9792a275252cb8770
|
3 |
+
size 989890704
|
model-00003-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc5c03b42830e59c010ae35b180ddfb82b9d95afc8628eec77c247eb7bf94f5a
|
3 |
+
size 989890712
|
model-00004-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d2d0de891637d2922a4b975acab8e8daaf89ab0d86c16a5705114327c6229f4
|
3 |
+
size 998287736
|
model-00005-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ca025d488ee4663f0b5bee06441d074ef5dd75503a6d35127b2cbb3f1b91826
|
3 |
+
size 947956192
|
model-00006-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4040978d2aa0b082074c495eee7099f1250726f1873d8162ebcdce4ee67004df
|
3 |
+
size 989890704
|
model-00007-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0688c245893b96e2fb6c9430372622ce5a8f32731619cf59bf6182b9fd1d2042
|
3 |
+
size 989890704
|
model-00008-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:897534ae9ec8ecb72a2d0732d7249f2b20f550e64908cbbce8fe5f5ddafa6b6d
|
3 |
+
size 998287736
|
model-00009-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df47d410751b2e7804cf72b9e592211d9807029b5fc3ff160bb31ab3c9213f94
|
3 |
+
size 947956192
|
model-00010-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7c2caae53d43592378dd8a6d9aeff5145ad6e1838f1b709f36f29eee84d5860
|
3 |
+
size 989890712
|
model-00011-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:deaf3debd670f997d8ba5a8e1b446bb3cadd024ade62e8b608913f1275f5dd92
|
3 |
+
size 989890704
|
model-00012-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d841af242441fc4734cda69d07876cc1e0e8cf2f085dca52629fc6195a6b81a2
|
3 |
+
size 998287728
|
model-00013-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6affae840902094a5c06e96bd63e1ad3916ed3ac70897549ea3d28aaec11965a
|
3 |
+
size 947956168
|
model-00014-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5deab08236366a738e9039b5da13c3c5cd045448ec26f0e0b25a4530b084d171
|
3 |
+
size 989890688
|
model-00015-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92daac17d4a7dac5ad3f56ce3a817d0489aed42a49ee30b6a30ab4240154c3b8
|
3 |
+
size 318784408
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 14047240192}, "weight_map": {"lm_head.weight": "model-00001-of-00015.safetensors", "model.embed_tokens.weight": "model-00001-of-00015.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.26.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.28.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.29.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.3.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.30.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.4.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.6.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.7.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.9.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00015-of-00015.safetensors", "model.norm.weight": "model-00015-of-00015.safetensors"}}
|
slerp_config.yaml
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
slices:
|
2 |
+
- sources:
|
3 |
+
- model: Nitral-AI/KukulStanta-7B
|
4 |
+
layer_range: [0, 31]
|
5 |
+
- model: AlekseiPravdin/Seamaiiza-7B-v1
|
6 |
+
layer_range: [0, 31]
|
7 |
+
merge_method: slerp
|
8 |
+
base_model: Nitral-AI/KukulStanta-7B
|
9 |
+
parameters:
|
10 |
+
t:
|
11 |
+
- filter: self_attn
|
12 |
+
value: [0, 0.5, 0.3, 0.7, 1]
|
13 |
+
- filter: mlp
|
14 |
+
value: [1, 0.5, 0.7, 0.3, 0]
|
15 |
+
- value: 0.5
|
16 |
+
dtype: float16
|
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"additional_special_tokens": [],
|
32 |
+
"bos_token": "<s>",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 1000000000000000019884624838656,
|
37 |
+
"pad_token": null,
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"spaces_between_special_tokens": false,
|
40 |
+
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false
|
43 |
+
}
|