Malikeh1375
commited on
Commit
•
a7278d5
1
Parent(s):
f0ef0c3
Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +36 -0
- config.json +28 -0
- mergekit_config.yml +18 -0
- model-00001-of-00009.safetensors +3 -0
- model-00002-of-00009.safetensors +3 -0
- model-00003-of-00009.safetensors +3 -0
- model-00004-of-00009.safetensors +3 -0
- model-00005-of-00009.safetensors +3 -0
- model-00006-of-00009.safetensors +3 -0
- model-00007-of-00009.safetensors +3 -0
- model-00008-of-00009.safetensors +3 -0
- model-00009-of-00009.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +30 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +49 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- merge
|
5 |
+
- mergekit
|
6 |
+
- google/gemma-7b-it
|
7 |
+
- google/gemma-7b
|
8 |
+
---
|
9 |
+
|
10 |
+
# Test-7B-slerp
|
11 |
+
|
12 |
+
Test-7B-slerp is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|
13 |
+
* [google/gemma-7b-it](https://huggingface.co/google/gemma-7b-it)
|
14 |
+
* [google/gemma-7b](https://huggingface.co/google/gemma-7b)
|
15 |
+
|
16 |
+
## 🧩 Configuration
|
17 |
+
|
18 |
+
```yaml
|
19 |
+
slices:
|
20 |
+
- sources:
|
21 |
+
- model: google/gemma-7b-it
|
22 |
+
layer_range: [0, 28]
|
23 |
+
- model: google/gemma-7b
|
24 |
+
layer_range: [0, 28]
|
25 |
+
merge_method: slerp
|
26 |
+
base_model: google/gemma-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: bfloat16
|
35 |
+
|
36 |
+
```
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/gemma-7b",
|
3 |
+
"architectures": [
|
4 |
+
"GemmaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 2,
|
9 |
+
"eos_token_id": 1,
|
10 |
+
"head_dim": 256,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_size": 3072,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 24576,
|
15 |
+
"max_position_embeddings": 8192,
|
16 |
+
"model_type": "gemma",
|
17 |
+
"num_attention_heads": 16,
|
18 |
+
"num_hidden_layers": 28,
|
19 |
+
"num_key_value_heads": 16,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"rms_norm_eps": 1e-06,
|
22 |
+
"rope_scaling": null,
|
23 |
+
"rope_theta": 10000.0,
|
24 |
+
"torch_dtype": "bfloat16",
|
25 |
+
"transformers_version": "4.38.1",
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 256000
|
28 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
slices:
|
3 |
+
- sources:
|
4 |
+
- model: google/gemma-7b-it
|
5 |
+
layer_range: [0, 28]
|
6 |
+
- model: google/gemma-7b
|
7 |
+
layer_range: [0, 28]
|
8 |
+
merge_method: slerp
|
9 |
+
base_model: google/gemma-7b
|
10 |
+
parameters:
|
11 |
+
t:
|
12 |
+
- filter: self_attn
|
13 |
+
value: [0, 0.5, 0.3, 0.7, 1]
|
14 |
+
- filter: mlp
|
15 |
+
value: [1, 0.5, 0.7, 0.3, 0]
|
16 |
+
- value: 0.5
|
17 |
+
dtype: bfloat16
|
18 |
+
|
model-00001-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:571982c5863ce6ee2b9e517d1989de0a01e56d0c41e35ef9920e5e551b1a7311
|
3 |
+
size 1912643208
|
model-00002-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c29250877aaf41c646718abdc5595b9abbabb490f5ab507effec3d096aa68d2
|
3 |
+
size 1509989312
|
model-00003-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74d0cbb547f5500e122d2d12b7b321e417bbcce667e1675911635d63973cb99c
|
3 |
+
size 1975518032
|
model-00004-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0783d0905efec1f23845261be11d7e286830dce5992953c113a968886612fba
|
3 |
+
size 1912655752
|
model-00005-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44913d8720b9e8b018fd47152f23d528c178088f8a1406df76a5c5232b8bfe48
|
3 |
+
size 1962974504
|
model-00006-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5108b83c5596db19742ef688e39c59416555b3890e246aa99bb328a413b8e83c
|
3 |
+
size 1912655736
|
model-00007-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acaa5d1ee0ae21db7365bb9f5c65c20101d55fad9b61b1b8ed169426b02d978e
|
3 |
+
size 1962974528
|
model-00008-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20c8753693b9bc0915d2227363a6e76027bd78316d0791bf21d9c73dea5cd292
|
3 |
+
size 1962993272
|
model-00009-of-00009.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cff14cf5a8a5922d29fd7ed41b2aa37f5cb8c331a3f54f71ceda937b6416c188
|
3 |
+
size 1962987040
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.embed_tokens.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.6.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.16.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.15.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.norm.weight": "model-00008-of-00009.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.26.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00009.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<bos>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<eos>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0d908b4f9326e0998815690e325b6abbd378978553e10627924dd825db7e243
|
3 |
+
size 17477553
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
|
3 |
+
size 4241003
|
tokenizer_config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<pad>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<eos>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "<bos>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"3": {
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"bos_token": "<bos>",
|
39 |
+
"clean_up_tokenization_spaces": false,
|
40 |
+
"eos_token": "<eos>",
|
41 |
+
"legacy": null,
|
42 |
+
"model_max_length": 1000000000000000019884624838656,
|
43 |
+
"pad_token": "<pad>",
|
44 |
+
"sp_model_kwargs": {},
|
45 |
+
"spaces_between_special_tokens": false,
|
46 |
+
"tokenizer_class": "GemmaTokenizer",
|
47 |
+
"unk_token": "<unk>",
|
48 |
+
"use_default_system_prompt": false
|
49 |
+
}
|