allknowingroger
commited on
Commit
•
2e14b0d
1
Parent(s):
0b05a8e
Upload folder using huggingface_hub
Browse files- README.md +55 -0
- config.json +27 -0
- mergekit_config.yml +10 -0
- model-00001-of-00036.safetensors +3 -0
- model-00002-of-00036.safetensors +3 -0
- model-00003-of-00036.safetensors +3 -0
- model-00004-of-00036.safetensors +3 -0
- model-00005-of-00036.safetensors +3 -0
- model-00006-of-00036.safetensors +3 -0
- model-00007-of-00036.safetensors +3 -0
- model-00008-of-00036.safetensors +3 -0
- model-00009-of-00036.safetensors +3 -0
- model-00010-of-00036.safetensors +3 -0
- model-00011-of-00036.safetensors +3 -0
- model-00012-of-00036.safetensors +3 -0
- model-00013-of-00036.safetensors +3 -0
- model-00014-of-00036.safetensors +3 -0
- model-00015-of-00036.safetensors +3 -0
- model-00016-of-00036.safetensors +3 -0
- model-00017-of-00036.safetensors +3 -0
- model-00018-of-00036.safetensors +3 -0
- model-00019-of-00036.safetensors +3 -0
- model-00020-of-00036.safetensors +3 -0
- model-00021-of-00036.safetensors +3 -0
- model-00022-of-00036.safetensors +3 -0
- model-00023-of-00036.safetensors +3 -0
- model-00024-of-00036.safetensors +3 -0
- model-00025-of-00036.safetensors +3 -0
- model-00026-of-00036.safetensors +3 -0
- model-00027-of-00036.safetensors +3 -0
- model-00028-of-00036.safetensors +3 -0
- model-00029-of-00036.safetensors +3 -0
- model-00030-of-00036.safetensors +3 -0
- model-00031-of-00036.safetensors +3 -0
- model-00032-of-00036.safetensors +3 -0
- model-00033-of-00036.safetensors +3 -0
- model-00034-of-00036.safetensors +3 -0
- model-00035-of-00036.safetensors +3 -0
- model-00036-of-00036.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +131 -0
README.md
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO
|
4 |
+
- Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO
|
5 |
+
tags:
|
6 |
+
- merge
|
7 |
+
- mergekit
|
8 |
+
- lazymergekit
|
9 |
+
- Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO
|
10 |
+
---
|
11 |
+
|
12 |
+
# Phi3-19B-pass
|
13 |
+
|
14 |
+
Phi3-19B-pass is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
15 |
+
* [Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO](https://huggingface.co/Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO)
|
16 |
+
* [Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO](https://huggingface.co/Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO)
|
17 |
+
|
18 |
+
## 🧩 Configuration
|
19 |
+
|
20 |
+
```yaml
|
21 |
+
slices:
|
22 |
+
- sources:
|
23 |
+
- model: Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO
|
24 |
+
layer_range: [0, 24]
|
25 |
+
- sources:
|
26 |
+
- model: Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO
|
27 |
+
layer_range: [8, 32]
|
28 |
+
merge_method: passthrough
|
29 |
+
dtype: float16
|
30 |
+
```
|
31 |
+
|
32 |
+
## 💻 Usage
|
33 |
+
|
34 |
+
```python
|
35 |
+
!pip install -qU transformers accelerate
|
36 |
+
|
37 |
+
from transformers import AutoTokenizer
|
38 |
+
import transformers
|
39 |
+
import torch
|
40 |
+
|
41 |
+
model = "allknowingroger/Phi3-19B-pass"
|
42 |
+
messages = [{"role": "user", "content": "What is a large language model?"}]
|
43 |
+
|
44 |
+
tokenizer = AutoTokenizer.from_pretrained(model)
|
45 |
+
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
46 |
+
pipeline = transformers.pipeline(
|
47 |
+
"text-generation",
|
48 |
+
model=model,
|
49 |
+
torch_dtype=torch.float16,
|
50 |
+
device_map="auto",
|
51 |
+
)
|
52 |
+
|
53 |
+
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
54 |
+
print(outputs[0]["generated_text"])
|
55 |
+
```
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 32000,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 5120,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 17920,
|
13 |
+
"max_position_embeddings": 4096,
|
14 |
+
"model_type": "mistral",
|
15 |
+
"num_attention_heads": 40,
|
16 |
+
"num_hidden_layers": 48,
|
17 |
+
"num_key_value_heads": 10,
|
18 |
+
"pad_token_id": 32009,
|
19 |
+
"rms_norm_eps": 1e-05,
|
20 |
+
"rope_theta": 10000.0,
|
21 |
+
"sliding_window": 2048,
|
22 |
+
"tie_word_embeddings": false,
|
23 |
+
"torch_dtype": "float16",
|
24 |
+
"transformers_version": "4.42.4",
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 32064
|
27 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
slices:
|
3 |
+
- sources:
|
4 |
+
- model: Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO
|
5 |
+
layer_range: [0, 24]
|
6 |
+
- sources:
|
7 |
+
- model: Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO
|
8 |
+
layer_range: [8, 32]
|
9 |
+
merge_method: passthrough
|
10 |
+
dtype: float16
|
model-00001-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2acff22d467f9bc4f29b72c4fb567fb61626d7e36a4f37ab42d7789e501c2b7c
|
3 |
+
size 840182208
|
model-00002-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e8b71952165cc252934101b52cc220fb514e22f14f18fe424becf8dcb77d62a
|
3 |
+
size 865096840
|
model-00003-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90eae761017364ef6cc003c2c76e66383cc73fdfc22c2fee98c55da35dbfcf22
|
3 |
+
size 865107192
|
model-00004-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdff46e8829fc13a214c4f2d65db85967746623a9a22c777d0dc54704ec648ba
|
3 |
+
size 996190016
|
model-00005-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce88f101380e95b31e77074de04fc3a9e23c362551ee28f07d0fac0b221b799d
|
3 |
+
size 996168856
|
model-00006-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c6c4b4f2052f6e91d696950e871601d79721bc9615ee21062e23f2579e9edf7
|
3 |
+
size 917525760
|
model-00007-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56f55eef921d29ca195fd9995ebdbbc33064742f56ca3a6a64469a024e28d69a
|
3 |
+
size 996190016
|
model-00008-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c380b56eabc3c9b90483aa24217f32a788677fee03f76e54e9ae38745f280fbd
|
3 |
+
size 996190016
|
model-00009-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:753665cf7364fed23fb30f15cd54d361a4345fea1128e66e0cde0cf9fcde451f
|
3 |
+
size 917504600
|
model-00010-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c03a25fd1e3deb35de884fc33ae0dbb0f0f4dac2df2afff1a76d4cbfb9687f91
|
3 |
+
size 996190016
|
model-00011-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:557c415d234c190d101b73f21352bd3b6d059fe0962281466063829b13b43c0f
|
3 |
+
size 996190016
|
model-00012-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:daf937b04c71f842f7e6bf358a5b411c23135962ef043f50bd5c89e5362ab6c8
|
3 |
+
size 996168856
|
model-00013-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9449292ecbb21a3d7440ddc5f1fbf661809f909bc51ccdfad6cb39733d4c3be3
|
3 |
+
size 917525760
|
model-00014-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a274c712e26fff58ae55b12bd60e64ba41d1b9ec1f35abfc3c769e0229e4c1a0
|
3 |
+
size 996190016
|
model-00015-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b194891d1499bb69850a4c9e554b8ea7f15ce68c96eb8042ce5fd02a1a720cb
|
3 |
+
size 996190016
|
model-00016-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f76cd2a4a70e07454ec42584f5b2e3576e35ae5da1c226a332424307c90aa8c
|
3 |
+
size 917504600
|
model-00017-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15049989e68b5e48ec7f7a02098376f0ffffc0c98d3df899fa9b032d47b1cc5d
|
3 |
+
size 996190024
|
model-00018-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:418fe7420976765052eb827b1e83018335afe0aab905797ce523478e0112803a
|
3 |
+
size 865096840
|
model-00019-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29022fc055dafc6f8b284c51ddbd896372332a6ace4356bfa36aa37f90855759
|
3 |
+
size 996190016
|
model-00020-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79798bf5c3bb1075c2904e21157396b228ef3b223ae8b2ca3f4a1f2d4ebdddda
|
3 |
+
size 996190016
|
model-00021-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd9a20e371d42d61b6ca95ad0fb4bcdeb546b5df85f413ebbaac9142c1603d32
|
3 |
+
size 917504600
|
model-00022-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:524fe6d27780dce51f168817e37dd444675e3224d4bc956bcc05be781aaef37a
|
3 |
+
size 996190016
|
model-00023-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c690e20f60a08194ee13d2a6fe088a73df27b5a50efd1533a6818b552445b1d8
|
3 |
+
size 996179672
|
model-00024-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9293f0967fb739f2902ae2999a721adfa6bdf21ea0b99738b186c68c502b9897
|
3 |
+
size 865096856
|
model-00025-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8207f40df1cb54463623ae8efc10683746a8da2163233fc6a804c91e328f5244
|
3 |
+
size 996190016
|
model-00026-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7ce15ab7e3d771732548a488bbe4c2cc3f9630190437d34e775e43855639a14
|
3 |
+
size 865096856
|
model-00027-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:396a81790ff19aecaa338055fa6e96e8b51d071a385b0a05c8c5392cb969203f
|
3 |
+
size 865096856
|
model-00028-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97001463c6a86ae4247399e0e6775ad063bbd4f8a7fb77176045eab844209196
|
3 |
+
size 996190000
|
model-00029-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:556c8fa43b5dd49b4c2d87ae8da54b0564203dd56e7b34c9f3ac7231af7b39b8
|
3 |
+
size 865096856
|
model-00030-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3438272e2701905fb177f273bd00cb754bf743783b7b4b2f95f3b63cdaede5f0
|
3 |
+
size 865096840
|
model-00031-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb58cde51ac7eb0a2618c40177fdd152ac841fb3eb651ef052c7ec0b09a66fc1
|
3 |
+
size 996190000
|
model-00032-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0aef74aef25b6fa4a5def5163be0d0f5ef44b1cd99c2d1c7bba0f40c00f16f1a
|
3 |
+
size 865096840
|
model-00033-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac7c26da982090feb8a88e1e7e8704c7f5de46bb8c8e688d17bd328e92464b2a
|
3 |
+
size 865107184
|
model-00034-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fb1b5443ac23dd9d28d0d7a11b38ce4a386537c8015ef70bde0fc3478da42aa
|
3 |
+
size 996190008
|
model-00035-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cee6826680a67fddac3cac400be7f3e178c0d10711f974ed3f59cb13852c3783
|
3 |
+
size 917504600
|
model-00036-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:073b2f8ca9ff6ab84180e18c5d84242cc713269d9a77b05fbe08a34b5c84768e
|
3 |
+
size 445676896
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 33373235200}, "weight_map": {"lm_head.weight": "model-00001-of-00036.safetensors", "model.embed_tokens.weight": "model-00001-of-00036.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00036.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00036.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00036.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00036.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00036.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00036.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00036.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00036.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00036.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00036.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00036.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00036.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00036.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00036.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00036.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00036.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00036.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00036.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00036.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00036.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00036.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00036.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00036.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00036.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00036.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00036.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00036.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00036.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00036.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00036.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00036.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00036.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00036.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00036.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00036.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00036.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00036.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00036.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00004-of-00036.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00005-of-00036.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00036.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00036.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00005-of-00036.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00005-of-00036.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00036.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00036.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00036.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00036.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00036.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00036.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00036.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00036.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00036.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00036.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00036.safetensors", "model.layers.12.input_layernorm.weight": "model-00006-of-00036.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00036.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00006-of-00036.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00036.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00036.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00036.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00007-of-00036.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00036.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00036.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00036.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00036.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00036.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00036.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00036.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00036.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00036.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00036.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00036.safetensors", "model.layers.13.input_layernorm.weight": "model-00007-of-00036.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00007-of-00036.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00007-of-00036.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00036.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00008-of-00036.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00008-of-00036.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00008-of-00036.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00036.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00008-of-00036.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00036.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00036.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00036.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00036.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00036.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00036.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00036.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00036.safetensors", "model.layers.30.input_layernorm.weight": "model-00008-of-00036.safetensors", "model.layers.14.input_layernorm.weight": "model-00008-of-00036.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00009-of-00036.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00009-of-00036.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00036.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00009-of-00036.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00009-of-00036.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00010-of-00036.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00036.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00010-of-00036.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00036.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00010-of-00036.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00036.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00010-of-00036.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00036.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00010-of-00036.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00036.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00010-of-00036.safetensors", "model.layers.31.input_layernorm.weight": "model-00010-of-00036.safetensors", "model.layers.15.input_layernorm.weight": "model-00010-of-00036.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00010-of-00036.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00010-of-00036.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00010-of-00036.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00011-of-00036.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00036.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00011-of-00036.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00036.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00011-of-00036.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00036.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00011-of-00036.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00036.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00011-of-00036.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00036.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00011-of-00036.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00036.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00011-of-00036.safetensors", "model.layers.32.input_layernorm.weight": "model-00011-of-00036.safetensors", "model.layers.16.input_layernorm.weight": "model-00011-of-00036.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00011-of-00036.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00012-of-00036.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00012-of-00036.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00012-of-00036.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00012-of-00036.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00012-of-00036.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00012-of-00036.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00012-of-00036.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00036.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00012-of-00036.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00036.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00013-of-00036.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00013-of-00036.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00013-of-00036.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00013-of-00036.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00013-of-00036.safetensors", "model.layers.33.input_layernorm.weight": "model-00013-of-00036.safetensors", "model.layers.17.input_layernorm.weight": "model-00013-of-00036.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00013-of-00036.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00013-of-00036.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00036.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00013-of-00036.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00014-of-00036.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00014-of-00036.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00014-of-00036.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00014-of-00036.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00014-of-00036.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00014-of-00036.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00014-of-00036.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00014-of-00036.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00014-of-00036.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00014-of-00036.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00014-of-00036.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00014-of-00036.safetensors", "model.layers.34.input_layernorm.weight": "model-00014-of-00036.safetensors", "model.layers.18.input_layernorm.weight": "model-00014-of-00036.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00014-of-00036.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00014-of-00036.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00015-of-00036.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00015-of-00036.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00015-of-00036.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00015-of-00036.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00015-of-00036.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00015-of-00036.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00015-of-00036.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00015-of-00036.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00015-of-00036.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00015-of-00036.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00015-of-00036.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00015-of-00036.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00015-of-00036.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00015-of-00036.safetensors", "model.layers.35.input_layernorm.weight": "model-00015-of-00036.safetensors", "model.layers.19.input_layernorm.weight": "model-00015-of-00036.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00016-of-00036.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00016-of-00036.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00016-of-00036.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00016-of-00036.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00016-of-00036.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00017-of-00036.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00017-of-00036.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00017-of-00036.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00017-of-00036.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00017-of-00036.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00017-of-00036.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00017-of-00036.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00017-of-00036.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00017-of-00036.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00017-of-00036.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00017-of-00036.safetensors", "model.layers.2.input_layernorm.weight": "model-00017-of-00036.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00017-of-00036.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00017-of-00036.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00017-of-00036.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00017-of-00036.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00018-of-00036.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00018-of-00036.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00018-of-00036.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00018-of-00036.safetensors", "model.layers.36.input_layernorm.weight": "model-00018-of-00036.safetensors", "model.layers.20.input_layernorm.weight": "model-00018-of-00036.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00018-of-00036.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00018-of-00036.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00018-of-00036.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00018-of-00036.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00019-of-00036.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00019-of-00036.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00019-of-00036.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00019-of-00036.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00019-of-00036.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00019-of-00036.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00019-of-00036.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00019-of-00036.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00019-of-00036.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00019-of-00036.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00019-of-00036.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00019-of-00036.safetensors", "model.layers.37.input_layernorm.weight": "model-00019-of-00036.safetensors", "model.layers.21.input_layernorm.weight": "model-00019-of-00036.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00019-of-00036.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00019-of-00036.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00020-of-00036.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00020-of-00036.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00020-of-00036.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00020-of-00036.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00020-of-00036.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00020-of-00036.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00020-of-00036.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00020-of-00036.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00020-of-00036.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00020-of-00036.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00020-of-00036.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00020-of-00036.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00020-of-00036.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00020-of-00036.safetensors", "model.layers.38.input_layernorm.weight": "model-00020-of-00036.safetensors", "model.layers.22.input_layernorm.weight": "model-00020-of-00036.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00021-of-00036.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00021-of-00036.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00021-of-00036.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00021-of-00036.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00021-of-00036.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00022-of-00036.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00022-of-00036.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00022-of-00036.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00022-of-00036.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00022-of-00036.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00022-of-00036.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00022-of-00036.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00022-of-00036.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00022-of-00036.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00022-of-00036.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00022-of-00036.safetensors", "model.layers.39.input_layernorm.weight": "model-00022-of-00036.safetensors", "model.layers.23.input_layernorm.weight": "model-00022-of-00036.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00022-of-00036.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00022-of-00036.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00022-of-00036.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00023-of-00036.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00023-of-00036.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00023-of-00036.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00023-of-00036.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00023-of-00036.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00023-of-00036.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00023-of-00036.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00023-of-00036.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00023-of-00036.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00023-of-00036.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00023-of-00036.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00023-of-00036.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00023-of-00036.safetensors", "model.layers.40.input_layernorm.weight": "model-00023-of-00036.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00023-of-00036.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00024-of-00036.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00024-of-00036.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00024-of-00036.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00024-of-00036.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00024-of-00036.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00024-of-00036.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00024-of-00036.safetensors", "model.layers.41.input_layernorm.weight": "model-00024-of-00036.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00024-of-00036.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00024-of-00036.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00025-of-00036.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00025-of-00036.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00025-of-00036.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00025-of-00036.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00025-of-00036.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00025-of-00036.safetensors", "model.layers.42.input_layernorm.weight": "model-00025-of-00036.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00025-of-00036.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00025-of-00036.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00025-of-00036.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00025-of-00036.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00025-of-00036.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00025-of-00036.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00025-of-00036.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00025-of-00036.safetensors", "model.layers.43.input_layernorm.weight": "model-00025-of-00036.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00026-of-00036.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00026-of-00036.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00026-of-00036.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00026-of-00036.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00026-of-00036.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00026-of-00036.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00026-of-00036.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00026-of-00036.safetensors", "model.layers.44.input_layernorm.weight": "model-00026-of-00036.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00026-of-00036.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00027-of-00036.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00027-of-00036.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00027-of-00036.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00027-of-00036.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00027-of-00036.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00027-of-00036.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00027-of-00036.safetensors", "model.layers.45.input_layernorm.weight": "model-00027-of-00036.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00027-of-00036.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00027-of-00036.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00028-of-00036.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00028-of-00036.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00028-of-00036.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00028-of-00036.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00028-of-00036.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00028-of-00036.safetensors", "model.layers.3.input_layernorm.weight": "model-00028-of-00036.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00028-of-00036.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00028-of-00036.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00028-of-00036.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00028-of-00036.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00028-of-00036.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00028-of-00036.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00028-of-00036.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00028-of-00036.safetensors", "model.layers.46.input_layernorm.weight": "model-00028-of-00036.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00029-of-00036.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00029-of-00036.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00029-of-00036.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00029-of-00036.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00029-of-00036.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00029-of-00036.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00029-of-00036.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00029-of-00036.safetensors", "model.layers.47.input_layernorm.weight": "model-00029-of-00036.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00029-of-00036.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00030-of-00036.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00030-of-00036.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00030-of-00036.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00030-of-00036.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00030-of-00036.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00030-of-00036.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00030-of-00036.safetensors", "model.layers.4.input_layernorm.weight": "model-00030-of-00036.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00030-of-00036.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00030-of-00036.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00031-of-00036.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00031-of-00036.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00031-of-00036.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00031-of-00036.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00031-of-00036.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00031-of-00036.safetensors", "model.layers.5.input_layernorm.weight": "model-00031-of-00036.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00031-of-00036.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00031-of-00036.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00031-of-00036.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00031-of-00036.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00031-of-00036.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00031-of-00036.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00031-of-00036.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00031-of-00036.safetensors", "model.layers.6.input_layernorm.weight": "model-00031-of-00036.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00032-of-00036.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00032-of-00036.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00032-of-00036.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00032-of-00036.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00032-of-00036.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00032-of-00036.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00032-of-00036.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00032-of-00036.safetensors", "model.layers.7.input_layernorm.weight": "model-00032-of-00036.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00032-of-00036.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00033-of-00036.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00033-of-00036.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00033-of-00036.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00033-of-00036.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00033-of-00036.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00033-of-00036.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00033-of-00036.safetensors", "model.layers.24.input_layernorm.weight": "model-00033-of-00036.safetensors", "model.layers.8.input_layernorm.weight": "model-00033-of-00036.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00033-of-00036.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00033-of-00036.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00034-of-00036.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00034-of-00036.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00034-of-00036.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00034-of-00036.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00034-of-00036.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00034-of-00036.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00034-of-00036.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00034-of-00036.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00034-of-00036.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00034-of-00036.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00034-of-00036.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00034-of-00036.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00034-of-00036.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00034-of-00036.safetensors", "model.layers.25.input_layernorm.weight": "model-00034-of-00036.safetensors", "model.layers.9.input_layernorm.weight": "model-00034-of-00036.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00035-of-00036.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00035-of-00036.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00035-of-00036.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00035-of-00036.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00035-of-00036.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00036-of-00036.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00036-of-00036.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00036-of-00036.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00036-of-00036.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00036-of-00036.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00036-of-00036.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00036-of-00036.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00036-of-00036.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00036-of-00036.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00036-of-00036.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00036-of-00036.safetensors", "model.norm.weight": "model-00036-of-00036.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": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|placeholder6|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": true,
|
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_config.json
ADDED
@@ -0,0 +1,131 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
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": true,
|
27 |
+
"single_word": false,
|
28 |
+
"special": false
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<|endoftext|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<|assistant|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": true,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"32002": {
|
47 |
+
"content": "<|placeholder1|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": true,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"32003": {
|
55 |
+
"content": "<|placeholder2|>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": true,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"32004": {
|
63 |
+
"content": "<|placeholder3|>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": true,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"32005": {
|
71 |
+
"content": "<|placeholder4|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": true,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"32006": {
|
79 |
+
"content": "<|system|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": true,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"32007": {
|
87 |
+
"content": "<|end|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": true,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"32008": {
|
95 |
+
"content": "<|placeholder5|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": true,
|
99 |
+
"single_word": false,
|
100 |
+
"special": true
|
101 |
+
},
|
102 |
+
"32009": {
|
103 |
+
"content": "<|placeholder6|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": true,
|
107 |
+
"single_word": false,
|
108 |
+
"special": true
|
109 |
+
},
|
110 |
+
"32010": {
|
111 |
+
"content": "<|user|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": true,
|
115 |
+
"single_word": false,
|
116 |
+
"special": true
|
117 |
+
}
|
118 |
+
},
|
119 |
+
"bos_token": "<s>",
|
120 |
+
"chat_template": "{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
|
121 |
+
"clean_up_tokenization_spaces": false,
|
122 |
+
"eos_token": "<|endoftext|>",
|
123 |
+
"legacy": true,
|
124 |
+
"model_max_length": 4096,
|
125 |
+
"pad_token": "<|placeholder6|>",
|
126 |
+
"padding_side": "left",
|
127 |
+
"sp_model_kwargs": {},
|
128 |
+
"tokenizer_class": "LlamaTokenizer",
|
129 |
+
"unk_token": "<unk>",
|
130 |
+
"use_default_system_prompt": false
|
131 |
+
}
|