matchaaaaa
commited on
Commit
•
15fc2b8
1
Parent(s):
c5bde6a
Upload 23 files
Browse files- .gitattributes +1 -0
- README.md +128 -1
- chaifighter-v3-cute.png +3 -0
- config.json +29 -0
- model-00001-of-00016.safetensors +3 -0
- model-00002-of-00016.safetensors +3 -0
- model-00003-of-00016.safetensors +3 -0
- model-00004-of-00016.safetensors +3 -0
- model-00005-of-00016.safetensors +3 -0
- model-00006-of-00016.safetensors +3 -0
- model-00007-of-00016.safetensors +3 -0
- model-00008-of-00016.safetensors +3 -0
- model-00009-of-00016.safetensors +3 -0
- model-00010-of-00016.safetensors +3 -0
- model-00011-of-00016.safetensors +3 -0
- model-00012-of-00016.safetensors +3 -0
- model-00013-of-00016.safetensors +3 -0
- model-00014-of-00016.safetensors +3 -0
- model-00015-of-00016.safetensors +3 -0
- model-00016-of-00016.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
chaifighter-v3-cute.png filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -1,3 +1,130 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
base_model: []
|
3 |
+
library_name: transformers
|
4 |
+
tags:
|
5 |
+
- mergekit
|
6 |
+
- merge
|
7 |
---
|
8 |
+
|
9 |
+
![cute](https://huggingface.co/matchaaaaa/Chaifighter-v3-20B/resolve/main/chaifighter-v3-cute.png)
|
10 |
+
|
11 |
+
# Chaifighter-v3-20B
|
12 |
+
|
13 |
+
Meet Chaifighter-v3! A flagship frankenmerge blend brewed with love by yours truly!
|
14 |
+
|
15 |
+
Chaifighter-v3 brings back the hyper-attention of the original, vastly expands on the fixes used to make v2 usable, and is built on a modified [Chunky-Lemon-Cookie-11B](https://huggingface.co/FallenMerick/Chunky-Lemon-Cookie-11B). Moreover, it RoPEs up to 8K perfectly, and should work well at 12K and beyond.
|
16 |
+
|
17 |
+
*Native Context Length: 4K/4096 (can be extended to 8K/8192 or more with RoPE)*
|
18 |
+
|
19 |
+
## Prompt Template: Alpaca/Alpaca-based
|
20 |
+
|
21 |
+
```
|
22 |
+
Below is an instruction that describes a task. Write a response that appropriately completes the request.
|
23 |
+
|
24 |
+
### Instruction:
|
25 |
+
{prompt}
|
26 |
+
|
27 |
+
### Response:
|
28 |
+
```
|
29 |
+
|
30 |
+
## Recommended Settings: Universal-Light
|
31 |
+
|
32 |
+
Here are some setting ranges that tend to work for my models. I used these when testing, and they're pretty safe bets. Feel free to tweak according to taste or do whatever you want (but maybe it might maybe break, maybe).
|
33 |
+
|
34 |
+
* Temperature: **1.0** to **1.25**
|
35 |
+
* Min-P: **0.05** to **0.1**
|
36 |
+
* Repetition Penalty: **1.05** *to* **1.1**
|
37 |
+
* Rep. Penalty Range: **256** *or* **512**
|
38 |
+
* *(all other samplers disabled)*
|
39 |
+
|
40 |
+
## The Deets
|
41 |
+
|
42 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
43 |
+
|
44 |
+
### Merge Method
|
45 |
+
|
46 |
+
This model was merged using the passthrough merge method.
|
47 |
+
|
48 |
+
### Models Merged
|
49 |
+
|
50 |
+
The following models were included in the merge:
|
51 |
+
|
52 |
+
* [Fimbulvetr-11B-v2](https://huggingface.co/Sao10K/Fimbulvetr-11B-v2)
|
53 |
+
* Pop-Taro-11B, *a variation of [Chunky-Lemon-Cookie-11B](https://huggingface.co/FallenMerick/Chunky-Lemon-Cookie-11B)*
|
54 |
+
* [SanjiWatsuki/Kunoichi-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-7B)
|
55 |
+
* [crestf411/daybreak-kunoichi-2dpo-7b](https://huggingface.co/crestf411/daybreak-kunoichi-2dpo-7b)
|
56 |
+
* [KatyTheCutie/LemonadeRP-4.5.3](https://huggingface.co/KatyTheCutie/LemonadeRP-4.5.3)
|
57 |
+
* [Fimbulvetr-11B-v2](https://huggingface.co/Sao10K/Fimbulvetr-11B-v2)
|
58 |
+
* [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
|
59 |
+
* [Undi95/Mistral-11B-OmniMix-pippa-sharegpt-11b-qlora](https://huggingface.co/Undi95/Mistral-11B-OmniMix-pippa-sharegpt-11b-qlora)
|
60 |
+
|
61 |
+
### The Special Sauce
|
62 |
+
|
63 |
+
The following YAML configuration was used to produce this model:
|
64 |
+
|
65 |
+
```yaml
|
66 |
+
slices: # modified Big-Lemon-Cookie recipe
|
67 |
+
- sources:
|
68 |
+
- model: SanjiWatsuki/Kunoichi-7B
|
69 |
+
layer_range: [0, 24]
|
70 |
+
- sources:
|
71 |
+
- model: crestf411/daybreak-kunoichi-2dpo-7b # this was Silicon-Maid in the OG
|
72 |
+
layer_range: [8, 24]
|
73 |
+
- sources:
|
74 |
+
- model: KatyTheCutie/LemonadeRP-4.5.3
|
75 |
+
layer_range: [24, 32]
|
76 |
+
merge_method: passthrough
|
77 |
+
dtype: float32
|
78 |
+
name: pre-Taro-11B
|
79 |
+
---
|
80 |
+
models: # this is what FallenMerick did for the Chunky-Lemon-Cookie
|
81 |
+
- model: pre-Taro-11B
|
82 |
+
parameters:
|
83 |
+
weight: 0.85
|
84 |
+
- model: Sao10K/Fimbulvetr-11B-v2
|
85 |
+
parameters:
|
86 |
+
weight: 0.15
|
87 |
+
merge_method: linear
|
88 |
+
dtype: float32
|
89 |
+
name: Taro-11B
|
90 |
+
---
|
91 |
+
models: # further healing with PEFT qLoRA, thanks undi
|
92 |
+
- model: Taro-11B
|
93 |
+
parameters:
|
94 |
+
weight: 0.68 # these values were a good balance
|
95 |
+
- model: Taro-11B+Undi95/Mistral-11B-OmniMix-pippa-sharegpt-11b-qlora # picked PIPPA because I'm old school
|
96 |
+
parameters:
|
97 |
+
weight: 0.32 # good balance pt. 2
|
98 |
+
merge_method: linear
|
99 |
+
dtype: float32
|
100 |
+
name: Pop-Taro-11B
|
101 |
+
---
|
102 |
+
slices: # this is the really cursed part
|
103 |
+
- sources:
|
104 |
+
- model: Sao10K/Fimbulvetr-11B-v2
|
105 |
+
layer_range: [0, 40]
|
106 |
+
- sources:
|
107 |
+
- model: Pop-Taro-11B # probably will release this later especially if it's good on its own and there's interest for it
|
108 |
+
layer_range: [0, 48] # includes the first 8 layers to boost attention, why does it worK???
|
109 |
+
merge_method: passthrough
|
110 |
+
dtype: float32
|
111 |
+
name: Chaifighter-v3-20B
|
112 |
+
```
|
113 |
+
|
114 |
+
All merging was done at float32 precision to minimize quality loss.
|
115 |
+
|
116 |
+
### The Thought Process
|
117 |
+
**Alternate title: "Input Layers Placed Halfway Through Your Frankenmerge Is All You Need"**
|
118 |
+
|
119 |
+
Note: much of this is conjecture. Thanks to [@ToastyPigeon](https://huggingface.co/ToastyPigeon) and the "Jeb's mad science 11B and 16B" thread on the Kobold discord. Without them, my understanding of this model would be much, much worse. Their help and insights were crucial in making this model happen!
|
120 |
+
|
121 |
+
This model started with the original recipe. According to everything my friends and I know, it just shouldn't have worked nearly as well as it did. I wondered what it would take to make it work, and as it turns out, it was the repeated Mistral "output layers" (meaning, the last 8 or so hidden layers) that caused most of the model's trouble. There was still stack damage, though. Essentially, this is a 7B base model expanded to 19.5B parameters. If that sounds like a lot, that's because it is a lot.
|
122 |
+
One of the core reasons it works, we believe, is because of [Fimbulvetr-v2](https://huggingface.co/Sao10K/Fimbulvetr-11B-v2) being based on [SOLAR 10.7B](https://huggingface.co/upstage/SOLAR-10.7B-v1.0). When SOLAR was being made, it received finetuning after being stacked up to 48 layers to heal the "stack damage". We think that this finetuning helped differentiate the layers enough from Mistral for the "input layers" (the first 8 or so hidden layers) for the whole model to actually function. Jeb's mad lads did a lot of testing and have concluded that one of the countless ways to break a model is to repeat these "input layers", and well, apparently (evidently) SOLAR somehow allows this cursedness to work.
|
123 |
+
As a side note, [Fimbulvetr-v2.1-16K](https://huggingface.co/Sao10K/Fimbulvetr-11B-v2.1-16K) was also tested in this merge. For some reason, it just wasn't happy there, and it caused all kinds of problems and a first-person bias (which I thought might be annoying to most people).
|
124 |
+
[Kunoichi](https://huggingface.co/SanjiWatsuki/Kunoichi-7B) has always been one of my favorites because of how great it is at prompt-following and awareness. That's why its second set of "input layers" are chosen. [@Kromeurus](https://huggingface.co/kromeurus) recommended [daybreak-kunoichi-2dpo-7b](https://huggingface.co/crestf411/daybreak-kunoichi-2dpo-7b), which was trained on the [Storyteller's Diamond Law](https://files.catbox.moe/d15m3g.txt) and in theory should increase the model's knowledge a little. [LemonadeRP-4.5.3](KatyTheCutie/LemonadeRP-4.5.3) is a solid performer as well, being part of [@FallenMerick's](https://huggingface.co/FallenMerick) [Chunky-Lemon-Cookie-11B](https://huggingface.co/FallenMerick/Chunky-Lemon-Cookie-11B) and by extension, [Honey-Yuzu-13B](https://huggingface.co/matchaaaaa/Honey-Yuzu-13B) (by me). It was also part of Chaifighter-v2's recipe, and as such, v3's writing should be familiar (in a good way :skull:) for those who liked v2.
|
125 |
+
Finally, this second stack of models was merged with Fimbulvetr-v2 to help heal the stack damage. In theory, this helps "smoothen" the layers together and make the model more put together overall. I went further with this idea by using [a PIPPA qLoRA trained for a Mistral 11B DUS stack called OmniMix](https://huggingface.co/Undi95/Mistral-11B-OmniMix-pippa-sharegpt-11b-qlora). I played with the values to ensure the end result was sufficiently stable without being overpowered by PIPPA.
|
126 |
+
There was a lot of trial and error involved in the creation of this model. Additionally, many many great minds helped shape this model. Thank you very much to everyone who kindly gave feedback, encouragement, or helped in any other way, big or small, with the development of this model and any past model. I really, really appreciate it. <3
|
127 |
+
|
128 |
+
And thank YOU for taking the time to read this and for checking out my model!
|
129 |
+
|
130 |
+
Have feedback? Comments? Questions? Don't hesitate to let me know! As always, have a fantastice day, and remember to take care of yourself! :)
|
chaifighter-v3-cute.png
ADDED
Git LFS Details
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "matchaaaaa/Chaifighter-v3-20B",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 14336,
|
14 |
+
"max_position_embeddings": 4096,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "llama",
|
17 |
+
"num_attention_heads": 32,
|
18 |
+
"num_hidden_layers": 88,
|
19 |
+
"num_key_value_heads": 8,
|
20 |
+
"pretraining_tp": 1,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_scaling": null,
|
23 |
+
"rope_theta": 10000.0,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.45.0.dev0",
|
27 |
+
"use_cache": false,
|
28 |
+
"vocab_size": 32000
|
29 |
+
}
|
model-00001-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9c10b753196df7681a6c4eb457cb3556698720d4d2e34fff7ca6f92f6b643b7
|
3 |
+
size 4773286512
|
model-00002-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ea9d7b974cead1f49b46e7e1fe4236343eed0961b5b7b52fb7a3a11fc6fe1bd
|
3 |
+
size 4999813128
|
model-00003-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e9d02fd5a0e3975f7cd95d7d6be5732f5498a8cd3f66374782154f2df3252d9
|
3 |
+
size 4999779672
|
model-00004-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cecc641bcb054a3e5cc74816336fe08bea88f5bf37e5c1873ee4bf44301d752
|
3 |
+
size 4899116472
|
model-00005-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd9ec9339c6aa94e2e9e19df1933402f43e6098e8841ba612e19b1993d7c5498
|
3 |
+
size 4999813120
|
model-00006-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99227679630e4d24967f54aecc8198d905f6506dd1931ca096f646be98ed59a2
|
3 |
+
size 4999813128
|
model-00007-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b1842bf17101782c1e3de43b162a7a370bf08f166931f49eb38b95d5cb99434
|
3 |
+
size 4999813128
|
model-00008-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f1b4435aa0fefa46e93aedbfcbaa01e2502bab9048875ccf864f8922d4608cf
|
3 |
+
size 4999813128
|
model-00009-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ba0b3f57816a759d6a4a2e80ec997bd17c7831a22867ff105d7691fcfc66fe0
|
3 |
+
size 4999813120
|
model-00010-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e57870100c6468f22e21d502c31e2e84339d123ef1b13fa70c29354186b10555
|
3 |
+
size 4999779672
|
model-00011-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cdd95e809c3051e31607605baffe403bcc4ea767f6e9638bbb31fc85ee1f6b6
|
3 |
+
size 4899116472
|
model-00012-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a96393f2ecd008990deaa2278942e3cc065fa5f8896f06eb69b3efcb3ca5e13
|
3 |
+
size 4999813128
|
model-00013-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18e9ba7aa2a3e804916c31abf65b7a085443187ad140c0b8cd76fed4cf8e8b36
|
3 |
+
size 4999813128
|
model-00014-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0191022024a19f62854475d902285fbe9f7af21a0691d584a7adc91731f9ea0
|
3 |
+
size 4999813112
|
model-00015-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92966ecb88a4525b8f866709699b603262155da94db61bcaf152770bdde04ed8
|
3 |
+
size 4999813104
|
model-00016-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e73fd9efeb79bc0daf9557fd32a8814cbd77f5e7b4813a3695b7c1dab29f4d9c
|
3 |
+
size 3254898512
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 77824016384}, "weight_map": {"lm_head.weight": "model-00001-of-00016.safetensors", "model.embed_tokens.weight": "model-00001-of-00016.safetensors", "model.layers.40.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00016.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00016.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00016.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.41.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00016.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00016.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00016.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.50.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00001-of-00016.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.51.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.52.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.53.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.54.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.55.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.56.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.57.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.58.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.59.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.42.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.2.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.60.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.61.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.62.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.63.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.64.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.65.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.66.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.67.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.27.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.68.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.28.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.69.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.29.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.43.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.3.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.70.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.30.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.71.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.31.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.72.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.32.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.73.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.33.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.74.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.34.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.75.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.35.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.76.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.36.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.77.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.37.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.78.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.38.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.79.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.39.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.44.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.4.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.80.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.81.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.82.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.83.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.84.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.85.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.86.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.87.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.45.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.5.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.46.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.6.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.47.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.7.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.48.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.8.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00016-of-00016.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00016-of-00016.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00016-of-00016.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.layers.49.input_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.9.input_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00016-of-00016.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00016-of-00016.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00016-of-00016.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.norm.weight": "model-00016-of-00016.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|