allknowingroger
commited on
Commit
•
b1bbc36
1
Parent(s):
f274ddb
Upload folder using huggingface_hub
Browse files- README.md +74 -0
- config.json +27 -0
- mergekit_config.yml +19 -0
- model-00001-of-00011.safetensors +3 -0
- model-00002-of-00011.safetensors +3 -0
- model-00003-of-00011.safetensors +3 -0
- model-00004-of-00011.safetensors +3 -0
- model-00005-of-00011.safetensors +3 -0
- model-00006-of-00011.safetensors +3 -0
- model-00007-of-00011.safetensors +3 -0
- model-00008-of-00011.safetensors +3 -0
- model-00009-of-00011.safetensors +3 -0
- model-00010-of-00011.safetensors +3 -0
- model-00011-of-00011.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +44 -0
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- merge
|
4 |
+
- mergekit
|
5 |
+
- lazymergekit
|
6 |
+
- allknowingroger/limyClown-7B-slerp
|
7 |
+
- allknowingroger/limyClown-7B-slerp
|
8 |
+
- allknowingroger/limyClown-7B-slerp
|
9 |
+
- allknowingroger/limyClown-7B-slerp
|
10 |
+
- allknowingroger/limyClown-7B-slerp
|
11 |
+
base_model:
|
12 |
+
- allknowingroger/limyClown-7B-slerp
|
13 |
+
- allknowingroger/limyClown-7B-slerp
|
14 |
+
- allknowingroger/limyClown-7B-slerp
|
15 |
+
- allknowingroger/limyClown-7B-slerp
|
16 |
+
- allknowingroger/limyClown-7B-slerp
|
17 |
+
---
|
18 |
+
|
19 |
+
# FrankenRoger-7B-passthrough
|
20 |
+
|
21 |
+
FrankenRoger-7B-passthrough is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
22 |
+
* [allknowingroger/limyClown-7B-slerp](https://huggingface.co/allknowingroger/limyClown-7B-slerp)
|
23 |
+
* [allknowingroger/limyClown-7B-slerp](https://huggingface.co/allknowingroger/limyClown-7B-slerp)
|
24 |
+
* [allknowingroger/limyClown-7B-slerp](https://huggingface.co/allknowingroger/limyClown-7B-slerp)
|
25 |
+
* [allknowingroger/limyClown-7B-slerp](https://huggingface.co/allknowingroger/limyClown-7B-slerp)
|
26 |
+
* [allknowingroger/limyClown-7B-slerp](https://huggingface.co/allknowingroger/limyClown-7B-slerp)
|
27 |
+
|
28 |
+
## 🧩 Configuration
|
29 |
+
|
30 |
+
```yaml
|
31 |
+
dtype: float16
|
32 |
+
merge_method: passthrough
|
33 |
+
slices:
|
34 |
+
- sources:
|
35 |
+
- model: allknowingroger/limyClown-7B-slerp
|
36 |
+
layer_range: [0,9]
|
37 |
+
- sources:
|
38 |
+
- model: allknowingroger/limyClown-7B-slerp
|
39 |
+
layer_range: [5,14]
|
40 |
+
- sources:
|
41 |
+
- model: allknowingroger/limyClown-7B-slerp
|
42 |
+
layer_range: [10,19]
|
43 |
+
- sources:
|
44 |
+
- model: allknowingroger/limyClown-7B-slerp
|
45 |
+
layer_range: [15,24]
|
46 |
+
- sources:
|
47 |
+
- model: allknowingroger/limyClown-7B-slerp
|
48 |
+
layer_range: [20,32]
|
49 |
+
```
|
50 |
+
|
51 |
+
## 💻 Usage
|
52 |
+
|
53 |
+
```python
|
54 |
+
!pip install -qU transformers accelerate
|
55 |
+
|
56 |
+
from transformers import AutoTokenizer
|
57 |
+
import transformers
|
58 |
+
import torch
|
59 |
+
|
60 |
+
model = "allknowingroger/FrankenRoger-7B-passthrough"
|
61 |
+
messages = [{"role": "user", "content": "What is a large language model?"}]
|
62 |
+
|
63 |
+
tokenizer = AutoTokenizer.from_pretrained(model)
|
64 |
+
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
65 |
+
pipeline = transformers.pipeline(
|
66 |
+
"text-generation",
|
67 |
+
model=model,
|
68 |
+
torch_dtype=torch.float16,
|
69 |
+
device_map="auto",
|
70 |
+
)
|
71 |
+
|
72 |
+
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
73 |
+
print(outputs[0]["generated_text"])
|
74 |
+
```
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "allknowingroger/limyClown-7B-slerp",
|
3 |
+
"add_gates": false,
|
4 |
+
"architectures": [
|
5 |
+
"MistralForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
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": 48,
|
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": "4.38.2",
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 32000
|
27 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
dtype: float16
|
3 |
+
merge_method: passthrough
|
4 |
+
slices:
|
5 |
+
- sources:
|
6 |
+
- model: allknowingroger/limyClown-7B-slerp
|
7 |
+
layer_range: [0,9]
|
8 |
+
- sources:
|
9 |
+
- model: allknowingroger/limyClown-7B-slerp
|
10 |
+
layer_range: [5,14]
|
11 |
+
- sources:
|
12 |
+
- model: allknowingroger/limyClown-7B-slerp
|
13 |
+
layer_range: [10,19]
|
14 |
+
- sources:
|
15 |
+
- model: allknowingroger/limyClown-7B-slerp
|
16 |
+
layer_range: [15,24]
|
17 |
+
- sources:
|
18 |
+
- model: allknowingroger/limyClown-7B-slerp
|
19 |
+
layer_range: [20,32]
|
model-00001-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68fc6b6dcfb6723059f1c3516b823c0d05a229245080cfa390c7c455bc0ce46f
|
3 |
+
size 1946210704
|
model-00002-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e4a99d7280ef4d488a3c724ebcedac2f45da7659e9574e0a334e0a566328a00
|
3 |
+
size 1963004752
|
model-00003-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:edcd8ce320c4644913f541d44a696d4bb438d8428e517fc8b5fb022dad90f9f4
|
3 |
+
size 1979789696
|
model-00004-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ed455cb68e308f48f151ea34a2a2492ff920f842dc486eb578f5b560dd46d1a
|
3 |
+
size 1979773576
|
model-00005-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:feb8cb30c22c4b32d48e1955a88279c52cf2fd3f1a035bc39f68f27444a620dc
|
3 |
+
size 1956712248
|
model-00006-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8324b293ff26b98a1a2f2b9014811e457e0df8abf8c3843b9eed77a202e85a7c
|
3 |
+
size 1979798040
|
model-00007-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a52d2e7bb88f8f77dc22df2f3823e0d0683bbd1e1a3a18c4062c13605c26b5f
|
3 |
+
size 1946227344
|
model-00008-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e721bfc5eda8a0d90ace60806ea2b40696343a0874321eec31363a6ffe5a126e
|
3 |
+
size 1979798040
|
model-00009-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e5400dc2118a66a221db9ad64611dc697fef36372d28678c143ad44f31b30d0
|
3 |
+
size 1973498456
|
model-00010-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fc5483b28912f4e2d869da70c50c6d6104e4bea0c4e8873db9b19c921e77894
|
3 |
+
size 1979814640
|
model-00011-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09ea981be23f674b2d3698ac2e5eb9013af44a90eed67a3042b9d740ef377f55
|
3 |
+
size 1778470856
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.37.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.36.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.32.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.embed_tokens.weight": "model-00005-of-00011.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00009-of-00011.safetensors", "lm_head.weight": "model-00009-of-00011.safetensors", "model.norm.weight": "model-00009-of-00011.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.47.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.46.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.45.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.40.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.39.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.35.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.38.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.34.input_layernorm.weight": "model-00011-of-00011.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"pad_token": {
|
17 |
+
"content": "<unk>",
|
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
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 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
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": 32768,
|
37 |
+
"pad_token": "<unk>",
|
38 |
+
"padding_side": "left",
|
39 |
+
"sp_model_kwargs": {},
|
40 |
+
"spaces_between_special_tokens": false,
|
41 |
+
"tokenizer_class": "LlamaTokenizer",
|
42 |
+
"unk_token": "<unk>",
|
43 |
+
"use_default_system_prompt": false
|
44 |
+
}
|