Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- README.md +41 -0
- chat_template.jinja +641 -0
- config.json +99 -0
- generation_config.json +8 -0
- model.safetensors +3 -0
- model.safetensors.index.json +930 -0
- tokenizer.json +3 -0
- tokenizer_config.json +25 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: gemma
|
| 3 |
+
library_name: mlx
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
extra_gated_heading: Access Gemma on Hugging Face
|
| 6 |
+
extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and
|
| 7 |
+
agree to Google’s usage license. To do this, please ensure you’re logged in to Hugging
|
| 8 |
+
Face and click below. Requests are processed immediately.
|
| 9 |
+
extra_gated_button_content: Acknowledge license
|
| 10 |
+
base_model: google/translategemma-4b-it
|
| 11 |
+
tags:
|
| 12 |
+
- mlx
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# async0x42/translategemma-4b-it-4bit
|
| 16 |
+
|
| 17 |
+
This model [async0x42/translategemma-4b-it-4bit](https://huggingface.co/async0x42/translategemma-4b-it-4bit) was
|
| 18 |
+
converted to MLX format from [google/translategemma-4b-it](https://huggingface.co/google/translategemma-4b-it)
|
| 19 |
+
using mlx-lm version **0.30.7**.
|
| 20 |
+
|
| 21 |
+
## Use with mlx
|
| 22 |
+
|
| 23 |
+
```bash
|
| 24 |
+
pip install mlx-lm
|
| 25 |
+
```
|
| 26 |
+
|
| 27 |
+
```python
|
| 28 |
+
from mlx_lm import load, generate
|
| 29 |
+
|
| 30 |
+
model, tokenizer = load("async0x42/translategemma-4b-it-4bit")
|
| 31 |
+
|
| 32 |
+
prompt = "hello"
|
| 33 |
+
|
| 34 |
+
if tokenizer.chat_template is not None:
|
| 35 |
+
messages = [{"role": "user", "content": prompt}]
|
| 36 |
+
prompt = tokenizer.apply_chat_template(
|
| 37 |
+
messages, add_generation_prompt=True, return_dict=False,
|
| 38 |
+
)
|
| 39 |
+
|
| 40 |
+
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
| 41 |
+
```
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,641 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set languages = {
|
| 2 |
+
"aa": "Afar",
|
| 3 |
+
"aa-DJ": "Afar",
|
| 4 |
+
"aa-ER": "Afar",
|
| 5 |
+
"ab": "Abkhazian",
|
| 6 |
+
"af": "Afrikaans",
|
| 7 |
+
"af-NA": "Afrikaans",
|
| 8 |
+
"ak": "Akan",
|
| 9 |
+
"am": "Amharic",
|
| 10 |
+
"an": "Aragonese",
|
| 11 |
+
"ar": "Arabic",
|
| 12 |
+
"ar-AE": "Arabic",
|
| 13 |
+
"ar-BH": "Arabic",
|
| 14 |
+
"ar-DJ": "Arabic",
|
| 15 |
+
"ar-DZ": "Arabic",
|
| 16 |
+
"ar-EG": "Arabic",
|
| 17 |
+
"ar-EH": "Arabic",
|
| 18 |
+
"ar-ER": "Arabic",
|
| 19 |
+
"ar-IL": "Arabic",
|
| 20 |
+
"ar-IQ": "Arabic",
|
| 21 |
+
"ar-JO": "Arabic",
|
| 22 |
+
"ar-KM": "Arabic",
|
| 23 |
+
"ar-KW": "Arabic",
|
| 24 |
+
"ar-LB": "Arabic",
|
| 25 |
+
"ar-LY": "Arabic",
|
| 26 |
+
"ar-MA": "Arabic",
|
| 27 |
+
"ar-MR": "Arabic",
|
| 28 |
+
"ar-OM": "Arabic",
|
| 29 |
+
"ar-PS": "Arabic",
|
| 30 |
+
"ar-QA": "Arabic",
|
| 31 |
+
"ar-SA": "Arabic",
|
| 32 |
+
"ar-SD": "Arabic",
|
| 33 |
+
"ar-SO": "Arabic",
|
| 34 |
+
"ar-SS": "Arabic",
|
| 35 |
+
"ar-SY": "Arabic",
|
| 36 |
+
"ar-TD": "Arabic",
|
| 37 |
+
"ar-TN": "Arabic",
|
| 38 |
+
"ar-YE": "Arabic",
|
| 39 |
+
"as": "Assamese",
|
| 40 |
+
"az": "Azerbaijani",
|
| 41 |
+
"az-Arab": "Azerbaijani",
|
| 42 |
+
"az-Arab-IQ": "Azerbaijani",
|
| 43 |
+
"az-Arab-TR": "Azerbaijani",
|
| 44 |
+
"az-Cyrl": "Azerbaijani",
|
| 45 |
+
"az-Latn": "Azerbaijani",
|
| 46 |
+
"ba": "Bashkir",
|
| 47 |
+
"be": "Belarusian",
|
| 48 |
+
"be-tarask": "Belarusian",
|
| 49 |
+
"bg": "Bulgarian",
|
| 50 |
+
"bg-BG": "Bulgarian",
|
| 51 |
+
"bm": "Bambara",
|
| 52 |
+
"bm-Nkoo": "Bambara",
|
| 53 |
+
"bn": "Bengali",
|
| 54 |
+
"bn-IN": "Bengali",
|
| 55 |
+
"bo": "Tibetan",
|
| 56 |
+
"bo-IN": "Tibetan",
|
| 57 |
+
"br": "Breton",
|
| 58 |
+
"bs": "Bosnian",
|
| 59 |
+
"bs-Cyrl": "Bosnian",
|
| 60 |
+
"bs-Latn": "Bosnian",
|
| 61 |
+
"ca": "Catalan",
|
| 62 |
+
"ca-AD": "Catalan",
|
| 63 |
+
"ca-ES": "Catalan",
|
| 64 |
+
"ca-FR": "Catalan",
|
| 65 |
+
"ca-IT": "Catalan",
|
| 66 |
+
"ce": "Chechen",
|
| 67 |
+
"co": "Corsican",
|
| 68 |
+
"cs": "Czech",
|
| 69 |
+
"cs-CZ": "Czech",
|
| 70 |
+
"cv": "Chuvash",
|
| 71 |
+
"cy": "Welsh",
|
| 72 |
+
"da": "Danish",
|
| 73 |
+
"da-DK": "Danish",
|
| 74 |
+
"da-GL": "Danish",
|
| 75 |
+
"de": "German",
|
| 76 |
+
"de-AT": "German",
|
| 77 |
+
"de-BE": "German",
|
| 78 |
+
"de-CH": "German",
|
| 79 |
+
"de-DE": "German",
|
| 80 |
+
"de-IT": "German",
|
| 81 |
+
"de-LI": "German",
|
| 82 |
+
"de-LU": "German",
|
| 83 |
+
"dv": "Divehi",
|
| 84 |
+
"dz": "Dzongkha",
|
| 85 |
+
"ee": "Ewe",
|
| 86 |
+
"ee-TG": "Ewe",
|
| 87 |
+
"el": "Greek",
|
| 88 |
+
"el-CY": "Greek",
|
| 89 |
+
"el-GR": "Greek",
|
| 90 |
+
"el-polyton": "Greek",
|
| 91 |
+
"en": "English",
|
| 92 |
+
"en-AE": "English",
|
| 93 |
+
"en-AG": "English",
|
| 94 |
+
"en-AI": "English",
|
| 95 |
+
"en-AS": "English",
|
| 96 |
+
"en-AT": "English",
|
| 97 |
+
"en-AU": "English",
|
| 98 |
+
"en-BB": "English",
|
| 99 |
+
"en-BE": "English",
|
| 100 |
+
"en-BI": "English",
|
| 101 |
+
"en-BM": "English",
|
| 102 |
+
"en-BS": "English",
|
| 103 |
+
"en-BW": "English",
|
| 104 |
+
"en-BZ": "English",
|
| 105 |
+
"en-CA": "English",
|
| 106 |
+
"en-CC": "English",
|
| 107 |
+
"en-CH": "English",
|
| 108 |
+
"en-CK": "English",
|
| 109 |
+
"en-CM": "English",
|
| 110 |
+
"en-CX": "English",
|
| 111 |
+
"en-CY": "English",
|
| 112 |
+
"en-CZ": "English",
|
| 113 |
+
"en-DE": "English",
|
| 114 |
+
"en-DG": "English",
|
| 115 |
+
"en-DK": "English",
|
| 116 |
+
"en-DM": "English",
|
| 117 |
+
"en-ER": "English",
|
| 118 |
+
"en-ES": "English",
|
| 119 |
+
"en-FI": "English",
|
| 120 |
+
"en-FJ": "English",
|
| 121 |
+
"en-FK": "English",
|
| 122 |
+
"en-FM": "English",
|
| 123 |
+
"en-FR": "English",
|
| 124 |
+
"en-GB": "English",
|
| 125 |
+
"en-GD": "English",
|
| 126 |
+
"en-GG": "English",
|
| 127 |
+
"en-GH": "English",
|
| 128 |
+
"en-GI": "English",
|
| 129 |
+
"en-GM": "English",
|
| 130 |
+
"en-GS": "English",
|
| 131 |
+
"en-GU": "English",
|
| 132 |
+
"en-GY": "English",
|
| 133 |
+
"en-HK": "English",
|
| 134 |
+
"en-HU": "English",
|
| 135 |
+
"en-ID": "English",
|
| 136 |
+
"en-IE": "English",
|
| 137 |
+
"en-IL": "English",
|
| 138 |
+
"en-IM": "English",
|
| 139 |
+
"en-IN": "English",
|
| 140 |
+
"en-IO": "English",
|
| 141 |
+
"en-IT": "English",
|
| 142 |
+
"en-JE": "English",
|
| 143 |
+
"en-JM": "English",
|
| 144 |
+
"en-KE": "English",
|
| 145 |
+
"en-KI": "English",
|
| 146 |
+
"en-KN": "English",
|
| 147 |
+
"en-KY": "English",
|
| 148 |
+
"en-LC": "English",
|
| 149 |
+
"en-LR": "English",
|
| 150 |
+
"en-LS": "English",
|
| 151 |
+
"en-MG": "English",
|
| 152 |
+
"en-MH": "English",
|
| 153 |
+
"en-MO": "English",
|
| 154 |
+
"en-MP": "English",
|
| 155 |
+
"en-MS": "English",
|
| 156 |
+
"en-MT": "English",
|
| 157 |
+
"en-MU": "English",
|
| 158 |
+
"en-MV": "English",
|
| 159 |
+
"en-MW": "English",
|
| 160 |
+
"en-MY": "English",
|
| 161 |
+
"en-NA": "English",
|
| 162 |
+
"en-NF": "English",
|
| 163 |
+
"en-NG": "English",
|
| 164 |
+
"en-NL": "English",
|
| 165 |
+
"en-NO": "English",
|
| 166 |
+
"en-NR": "English",
|
| 167 |
+
"en-NU": "English",
|
| 168 |
+
"en-NZ": "English",
|
| 169 |
+
"en-PG": "English",
|
| 170 |
+
"en-PH": "English",
|
| 171 |
+
"en-PK": "English",
|
| 172 |
+
"en-PL": "English",
|
| 173 |
+
"en-PN": "English",
|
| 174 |
+
"en-PR": "English",
|
| 175 |
+
"en-PT": "English",
|
| 176 |
+
"en-PW": "English",
|
| 177 |
+
"en-RO": "English",
|
| 178 |
+
"en-RW": "English",
|
| 179 |
+
"en-SB": "English",
|
| 180 |
+
"en-SC": "English",
|
| 181 |
+
"en-SD": "English",
|
| 182 |
+
"en-SE": "English",
|
| 183 |
+
"en-SG": "English",
|
| 184 |
+
"en-SH": "English",
|
| 185 |
+
"en-SI": "English",
|
| 186 |
+
"en-SK": "English",
|
| 187 |
+
"en-SL": "English",
|
| 188 |
+
"en-SS": "English",
|
| 189 |
+
"en-SX": "English",
|
| 190 |
+
"en-SZ": "English",
|
| 191 |
+
"en-TC": "English",
|
| 192 |
+
"en-TK": "English",
|
| 193 |
+
"en-TO": "English",
|
| 194 |
+
"en-TT": "English",
|
| 195 |
+
"en-TV": "English",
|
| 196 |
+
"en-TZ": "English",
|
| 197 |
+
"en-UG": "English",
|
| 198 |
+
"en-UM": "English",
|
| 199 |
+
"en-VC": "English",
|
| 200 |
+
"en-VG": "English",
|
| 201 |
+
"en-VI": "English",
|
| 202 |
+
"en-VU": "English",
|
| 203 |
+
"en-WS": "English",
|
| 204 |
+
"en-ZA": "English",
|
| 205 |
+
"en-ZM": "English",
|
| 206 |
+
"en-ZW": "English",
|
| 207 |
+
"eo": "Esperanto",
|
| 208 |
+
"es": "Spanish",
|
| 209 |
+
"es-AR": "Spanish",
|
| 210 |
+
"es-BO": "Spanish",
|
| 211 |
+
"es-BR": "Spanish",
|
| 212 |
+
"es-BZ": "Spanish",
|
| 213 |
+
"es-CL": "Spanish",
|
| 214 |
+
"es-CO": "Spanish",
|
| 215 |
+
"es-CR": "Spanish",
|
| 216 |
+
"es-CU": "Spanish",
|
| 217 |
+
"es-DO": "Spanish",
|
| 218 |
+
"es-EA": "Spanish",
|
| 219 |
+
"es-EC": "Spanish",
|
| 220 |
+
"es-ES": "Spanish",
|
| 221 |
+
"es-GQ": "Spanish",
|
| 222 |
+
"es-GT": "Spanish",
|
| 223 |
+
"es-HN": "Spanish",
|
| 224 |
+
"es-IC": "Spanish",
|
| 225 |
+
"es-MX": "Spanish",
|
| 226 |
+
"es-NI": "Spanish",
|
| 227 |
+
"es-PA": "Spanish",
|
| 228 |
+
"es-PE": "Spanish",
|
| 229 |
+
"es-PH": "Spanish",
|
| 230 |
+
"es-PR": "Spanish",
|
| 231 |
+
"es-PY": "Spanish",
|
| 232 |
+
"es-SV": "Spanish",
|
| 233 |
+
"es-US": "Spanish",
|
| 234 |
+
"es-UY": "Spanish",
|
| 235 |
+
"es-VE": "Spanish",
|
| 236 |
+
"et": "Estonian",
|
| 237 |
+
"et-EE": "Estonian",
|
| 238 |
+
"eu": "Basque",
|
| 239 |
+
"fa": "Persian",
|
| 240 |
+
"fa-AF": "Persian",
|
| 241 |
+
"fa-IR": "Persian",
|
| 242 |
+
"ff": "Fulah",
|
| 243 |
+
"ff-Adlm": "Fulah",
|
| 244 |
+
"ff-Adlm-BF": "Fulah",
|
| 245 |
+
"ff-Adlm-CM": "Fulah",
|
| 246 |
+
"ff-Adlm-GH": "Fulah",
|
| 247 |
+
"ff-Adlm-GM": "Fulah",
|
| 248 |
+
"ff-Adlm-GW": "Fulah",
|
| 249 |
+
"ff-Adlm-LR": "Fulah",
|
| 250 |
+
"ff-Adlm-MR": "Fulah",
|
| 251 |
+
"ff-Adlm-NE": "Fulah",
|
| 252 |
+
"ff-Adlm-NG": "Fulah",
|
| 253 |
+
"ff-Adlm-SL": "Fulah",
|
| 254 |
+
"ff-Adlm-SN": "Fulah",
|
| 255 |
+
"ff-Latn": "Fulah",
|
| 256 |
+
"ff-Latn-BF": "Fulah",
|
| 257 |
+
"ff-Latn-CM": "Fulah",
|
| 258 |
+
"ff-Latn-GH": "Fulah",
|
| 259 |
+
"ff-Latn-GM": "Fulah",
|
| 260 |
+
"ff-Latn-GN": "Fulah",
|
| 261 |
+
"ff-Latn-GW": "Fulah",
|
| 262 |
+
"ff-Latn-LR": "Fulah",
|
| 263 |
+
"ff-Latn-MR": "Fulah",
|
| 264 |
+
"ff-Latn-NE": "Fulah",
|
| 265 |
+
"ff-Latn-NG": "Fulah",
|
| 266 |
+
"ff-Latn-SL": "Fulah",
|
| 267 |
+
"fi": "Finnish",
|
| 268 |
+
"fi-FI": "Finnish",
|
| 269 |
+
"fil-PH": "Filipino",
|
| 270 |
+
"fo": "Faroese",
|
| 271 |
+
"fo-DK": "Faroese",
|
| 272 |
+
"fr": "French",
|
| 273 |
+
"fr-BE": "French",
|
| 274 |
+
"fr-BF": "French",
|
| 275 |
+
"fr-BI": "French",
|
| 276 |
+
"fr-BJ": "French",
|
| 277 |
+
"fr-BL": "French",
|
| 278 |
+
"fr-CA": "French",
|
| 279 |
+
"fr-CD": "French",
|
| 280 |
+
"fr-CF": "French",
|
| 281 |
+
"fr-CG": "French",
|
| 282 |
+
"fr-CH": "French",
|
| 283 |
+
"fr-CI": "French",
|
| 284 |
+
"fr-CM": "French",
|
| 285 |
+
"fr-DJ": "French",
|
| 286 |
+
"fr-DZ": "French",
|
| 287 |
+
"fr-FR": "French",
|
| 288 |
+
"fr-GA": "French",
|
| 289 |
+
"fr-GF": "French",
|
| 290 |
+
"fr-GN": "French",
|
| 291 |
+
"fr-GP": "French",
|
| 292 |
+
"fr-GQ": "French",
|
| 293 |
+
"fr-HT": "French",
|
| 294 |
+
"fr-KM": "French",
|
| 295 |
+
"fr-LU": "French",
|
| 296 |
+
"fr-MA": "French",
|
| 297 |
+
"fr-MC": "French",
|
| 298 |
+
"fr-MF": "French",
|
| 299 |
+
"fr-MG": "French",
|
| 300 |
+
"fr-ML": "French",
|
| 301 |
+
"fr-MQ": "French",
|
| 302 |
+
"fr-MR": "French",
|
| 303 |
+
"fr-MU": "French",
|
| 304 |
+
"fr-NC": "French",
|
| 305 |
+
"fr-NE": "French",
|
| 306 |
+
"fr-PF": "French",
|
| 307 |
+
"fr-PM": "French",
|
| 308 |
+
"fr-RE": "French",
|
| 309 |
+
"fr-RW": "French",
|
| 310 |
+
"fr-SC": "French",
|
| 311 |
+
"fr-SN": "French",
|
| 312 |
+
"fr-SY": "French",
|
| 313 |
+
"fr-TD": "French",
|
| 314 |
+
"fr-TG": "French",
|
| 315 |
+
"fr-TN": "French",
|
| 316 |
+
"fr-VU": "French",
|
| 317 |
+
"fr-WF": "French",
|
| 318 |
+
"fr-YT": "French",
|
| 319 |
+
"fy": "Western Frisian",
|
| 320 |
+
"ga": "Irish",
|
| 321 |
+
"ga-GB": "Irish",
|
| 322 |
+
"gd": "Scottish Gaelic",
|
| 323 |
+
"gl": "Galician",
|
| 324 |
+
"gn": "Guarani",
|
| 325 |
+
"gu": "Gujarati",
|
| 326 |
+
"gu-IN": "Gujarati",
|
| 327 |
+
"gv": "Manx",
|
| 328 |
+
"ha": "Hausa",
|
| 329 |
+
"ha-Arab": "Hausa",
|
| 330 |
+
"ha-Arab-SD": "Hausa",
|
| 331 |
+
"ha-GH": "Hausa",
|
| 332 |
+
"ha-NE": "Hausa",
|
| 333 |
+
"he": "Hebrew",
|
| 334 |
+
"he-IL": "Hebrew",
|
| 335 |
+
"hi": "Hindi",
|
| 336 |
+
"hi-IN": "Hindi",
|
| 337 |
+
"hi-Latn": "Hindi",
|
| 338 |
+
"hr": "Croatian",
|
| 339 |
+
"hr-BA": "Croatian",
|
| 340 |
+
"hr-HR": "Croatian",
|
| 341 |
+
"ht": "Haitian",
|
| 342 |
+
"hu": "Hungarian",
|
| 343 |
+
"hu-HU": "Hungarian",
|
| 344 |
+
"hy": "Armenian",
|
| 345 |
+
"ia": "Interlingua",
|
| 346 |
+
"id": "Indonesian",
|
| 347 |
+
"id-ID": "Indonesian",
|
| 348 |
+
"ie": "Interlingue",
|
| 349 |
+
"ig": "Igbo",
|
| 350 |
+
"ii": "Sichuan Yi",
|
| 351 |
+
"ik": "Inupiaq",
|
| 352 |
+
"io": "Ido",
|
| 353 |
+
"is": "Icelandic",
|
| 354 |
+
"it": "Italian",
|
| 355 |
+
"it-CH": "Italian",
|
| 356 |
+
"it-IT": "Italian",
|
| 357 |
+
"it-SM": "Italian",
|
| 358 |
+
"it-VA": "Italian",
|
| 359 |
+
"iu": "Inuktitut",
|
| 360 |
+
"iu-Latn": "Inuktitut",
|
| 361 |
+
"ja": "Japanese",
|
| 362 |
+
"ja-JP": "Japanese",
|
| 363 |
+
"jv": "Javanese",
|
| 364 |
+
"ka": "Georgian",
|
| 365 |
+
"ki": "Kikuyu",
|
| 366 |
+
"kk": "Kazakh",
|
| 367 |
+
"kk-Arab": "Kazakh",
|
| 368 |
+
"kk-Cyrl": "Kazakh",
|
| 369 |
+
"kk-KZ": "Kazakh",
|
| 370 |
+
"kl": "Kalaallisut",
|
| 371 |
+
"km": "Central Khmer",
|
| 372 |
+
"kn": "Kannada",
|
| 373 |
+
"kn-IN": "Kannada",
|
| 374 |
+
"ko": "Korean",
|
| 375 |
+
"ko-CN": "Korean",
|
| 376 |
+
"ko-KP": "Korean",
|
| 377 |
+
"ko-KR": "Korean",
|
| 378 |
+
"ks": "Kashmiri",
|
| 379 |
+
"ks-Arab": "Kashmiri",
|
| 380 |
+
"ks-Deva": "Kashmiri",
|
| 381 |
+
"ku": "Kurdish",
|
| 382 |
+
"kw": "Cornish",
|
| 383 |
+
"ky": "Kyrgyz",
|
| 384 |
+
"la": "Latin",
|
| 385 |
+
"lb": "Luxembourgish",
|
| 386 |
+
"lg": "Ganda",
|
| 387 |
+
"ln": "Lingala",
|
| 388 |
+
"ln-AO": "Lingala",
|
| 389 |
+
"ln-CF": "Lingala",
|
| 390 |
+
"ln-CG": "Lingala",
|
| 391 |
+
"lo": "Lao",
|
| 392 |
+
"lt": "Lithuanian",
|
| 393 |
+
"lt-LT": "Lithuanian",
|
| 394 |
+
"lu": "Luba-Katanga",
|
| 395 |
+
"lv": "Latvian",
|
| 396 |
+
"lv-LV": "Latvian",
|
| 397 |
+
"mg": "Malagasy",
|
| 398 |
+
"mi": "Maori",
|
| 399 |
+
"mk": "Macedonian",
|
| 400 |
+
"ml": "Malayalam",
|
| 401 |
+
"ml-IN": "Malayalam",
|
| 402 |
+
"mn": "Mongolian",
|
| 403 |
+
"mn-Mong": "Mongolian",
|
| 404 |
+
"mn-Mong-MN": "Mongolian",
|
| 405 |
+
"mr": "Marathi",
|
| 406 |
+
"mr-IN": "Marathi",
|
| 407 |
+
"ms": "Malay",
|
| 408 |
+
"ms-Arab": "Malay",
|
| 409 |
+
"ms-Arab-BN": "Malay",
|
| 410 |
+
"ms-BN": "Malay",
|
| 411 |
+
"ms-ID": "Malay",
|
| 412 |
+
"ms-SG": "Malay",
|
| 413 |
+
"mt": "Maltese",
|
| 414 |
+
"my": "Burmese",
|
| 415 |
+
"nb": "Norwegian Bokmål",
|
| 416 |
+
"nb-SJ": "Norwegian Bokmål",
|
| 417 |
+
"nd": "North Ndebele",
|
| 418 |
+
"ne": "Nepali",
|
| 419 |
+
"ne-IN": "Nepali",
|
| 420 |
+
"nl": "Dutch",
|
| 421 |
+
"nl-AW": "Dutch",
|
| 422 |
+
"nl-BE": "Dutch",
|
| 423 |
+
"nl-BQ": "Dutch",
|
| 424 |
+
"nl-CW": "Dutch",
|
| 425 |
+
"nl-NL": "Dutch",
|
| 426 |
+
"nl-SR": "Dutch",
|
| 427 |
+
"nl-SX": "Dutch",
|
| 428 |
+
"nn": "Norwegian Nynorsk",
|
| 429 |
+
"no": "Norwegian",
|
| 430 |
+
"no-NO": "Norwegian",
|
| 431 |
+
"nr": "South Ndebele",
|
| 432 |
+
"nv": "Navajo",
|
| 433 |
+
"ny": "Chichewa",
|
| 434 |
+
"oc": "Occitan",
|
| 435 |
+
"oc-ES": "Occitan",
|
| 436 |
+
"om": "Oromo",
|
| 437 |
+
"om-KE": "Oromo",
|
| 438 |
+
"or": "Oriya",
|
| 439 |
+
"os": "Ossetian",
|
| 440 |
+
"os-RU": "Ossetian",
|
| 441 |
+
"pa": "Punjabi",
|
| 442 |
+
"pa-IN": "Punjabi",
|
| 443 |
+
"pa-Arab": "Punjabi",
|
| 444 |
+
"pa-Guru": "Punjabi",
|
| 445 |
+
"pl": "Polish",
|
| 446 |
+
"pl-PL": "Polish",
|
| 447 |
+
"ps": "Pashto",
|
| 448 |
+
"ps-PK": "Pashto",
|
| 449 |
+
"pt": "Portuguese",
|
| 450 |
+
"pt-AO": "Portuguese",
|
| 451 |
+
"pt-BR": "Portuguese",
|
| 452 |
+
"pt-CH": "Portuguese",
|
| 453 |
+
"pt-CV": "Portuguese",
|
| 454 |
+
"pt-GQ": "Portuguese",
|
| 455 |
+
"pt-GW": "Portuguese",
|
| 456 |
+
"pt-LU": "Portuguese",
|
| 457 |
+
"pt-MO": "Portuguese",
|
| 458 |
+
"pt-MZ": "Portuguese",
|
| 459 |
+
"pt-PT": "Portuguese",
|
| 460 |
+
"pt-ST": "Portuguese",
|
| 461 |
+
"pt-TL": "Portuguese",
|
| 462 |
+
"qu": "Quechua",
|
| 463 |
+
"qu-BO": "Quechua",
|
| 464 |
+
"qu-EC": "Quechua",
|
| 465 |
+
"rm": "Romansh",
|
| 466 |
+
"rn": "Rundi",
|
| 467 |
+
"ro": "Romanian",
|
| 468 |
+
"ro-MD": "Romanian",
|
| 469 |
+
"ro-RO": "Romanian",
|
| 470 |
+
"ru": "Russian",
|
| 471 |
+
"ru-BY": "Russian",
|
| 472 |
+
"ru-KG": "Russian",
|
| 473 |
+
"ru-KZ": "Russian",
|
| 474 |
+
"ru-MD": "Russian",
|
| 475 |
+
"ru-RU": "Russian",
|
| 476 |
+
"ru-UA": "Russian",
|
| 477 |
+
"rw": "Kinyarwanda",
|
| 478 |
+
"sa": "Sanskrit",
|
| 479 |
+
"sc": "Sardinian",
|
| 480 |
+
"sd": "Sindhi",
|
| 481 |
+
"sd-Arab": "Sindhi",
|
| 482 |
+
"sd-Deva": "Sindhi",
|
| 483 |
+
"se": "Northern Sami",
|
| 484 |
+
"se-FI": "Northern Sami",
|
| 485 |
+
"se-SE": "Northern Sami",
|
| 486 |
+
"sg": "Sango",
|
| 487 |
+
"si": "Sinhala",
|
| 488 |
+
"sk": "Slovak",
|
| 489 |
+
"sk-SK": "Slovak",
|
| 490 |
+
"sl": "Slovenian",
|
| 491 |
+
"sl-SI": "Slovenian",
|
| 492 |
+
"sn": "Shona",
|
| 493 |
+
"so": "Somali",
|
| 494 |
+
"so-DJ": "Somali",
|
| 495 |
+
"so-ET": "Somali",
|
| 496 |
+
"so-KE": "Somali",
|
| 497 |
+
"sq": "Albanian",
|
| 498 |
+
"sq-MK": "Albanian",
|
| 499 |
+
"sq-XK": "Albanian",
|
| 500 |
+
"sr": "Serbian",
|
| 501 |
+
"sr-RS": "Serbian",
|
| 502 |
+
"sr-Cyrl": "Serbian",
|
| 503 |
+
"sr-Cyrl-BA": "Serbian",
|
| 504 |
+
"sr-Cyrl-ME": "Serbian",
|
| 505 |
+
"sr-Cyrl-XK": "Serbian",
|
| 506 |
+
"sr-Latn": "Serbian",
|
| 507 |
+
"sr-Latn-BA": "Serbian",
|
| 508 |
+
"sr-Latn-ME": "Serbian",
|
| 509 |
+
"sr-Latn-XK": "Serbian",
|
| 510 |
+
"ss": "Swati",
|
| 511 |
+
"ss-SZ": "Swati",
|
| 512 |
+
"st": "Southern Sotho",
|
| 513 |
+
"st-LS": "Southern Sotho",
|
| 514 |
+
"su": "Sundanese",
|
| 515 |
+
"su-Latn": "Sundanese",
|
| 516 |
+
"sv": "Swedish",
|
| 517 |
+
"sv-AX": "Swedish",
|
| 518 |
+
"sv-FI": "Swedish",
|
| 519 |
+
"sv-SE": "Swedish",
|
| 520 |
+
"sw": "Swahili",
|
| 521 |
+
"sw-CD": "Swahili",
|
| 522 |
+
"sw-KE": "Swahili",
|
| 523 |
+
"sw-TZ": "Swahili",
|
| 524 |
+
"sw-UG": "Swahili",
|
| 525 |
+
"ta": "Tamil",
|
| 526 |
+
"ta-IN": "Tamil",
|
| 527 |
+
"ta-LK": "Tamil",
|
| 528 |
+
"ta-MY": "Tamil",
|
| 529 |
+
"ta-SG": "Tamil",
|
| 530 |
+
"te": "Telugu",
|
| 531 |
+
"te-IN": "Telugu",
|
| 532 |
+
"tg": "Tajik",
|
| 533 |
+
"th": "Thai",
|
| 534 |
+
"th-TH": "Thai",
|
| 535 |
+
"ti": "Tigrinya",
|
| 536 |
+
"ti-ER": "Tigrinya",
|
| 537 |
+
"tk": "Turkmen",
|
| 538 |
+
"tl": "Tagalog",
|
| 539 |
+
"tn": "Tswana",
|
| 540 |
+
"tn-BW": "Tswana",
|
| 541 |
+
"to": "Tonga",
|
| 542 |
+
"tr": "Turkish",
|
| 543 |
+
"tr-CY": "Turkish",
|
| 544 |
+
"tr-TR": "Turkish",
|
| 545 |
+
"ts": "Tsonga",
|
| 546 |
+
"tt": "Tatar",
|
| 547 |
+
"ug": "Uyghur",
|
| 548 |
+
"uk": "Ukrainian",
|
| 549 |
+
"uk-UA": "Ukrainian",
|
| 550 |
+
"ur": "Urdu",
|
| 551 |
+
"ur-IN": "Urdu",
|
| 552 |
+
"ur-PK": "Urdu",
|
| 553 |
+
"uz": "Uzbek",
|
| 554 |
+
"uz-Arab": "Uzbek",
|
| 555 |
+
"uz-Cyrl": "Uzbek",
|
| 556 |
+
"uz-Latn": "Uzbek",
|
| 557 |
+
"ve": "Venda",
|
| 558 |
+
"vi": "Vietnamese",
|
| 559 |
+
"vi-VN": "Vietnamese",
|
| 560 |
+
"vo": "Volapük",
|
| 561 |
+
"wa": "Walloon",
|
| 562 |
+
"wo": "Wolof",
|
| 563 |
+
"xh": "Xhosa",
|
| 564 |
+
"yi": "Yiddish",
|
| 565 |
+
"yo": "Yoruba",
|
| 566 |
+
"yo-BJ": "Yoruba",
|
| 567 |
+
"za": "Zhuang",
|
| 568 |
+
"zh": "Chinese",
|
| 569 |
+
"zh-CH": "Chinese",
|
| 570 |
+
"zh-TW": "Chinese",
|
| 571 |
+
"zh-Hans": "Chinese",
|
| 572 |
+
"zh-Hans-HK": "Chinese",
|
| 573 |
+
"zh-Hans-MO": "Chinese",
|
| 574 |
+
"zh-Hans-MY": "Chinese",
|
| 575 |
+
"zh-Hans-SG": "Chinese",
|
| 576 |
+
"zh-Hant": "Chinese",
|
| 577 |
+
"zh-Hant-HK": "Chinese",
|
| 578 |
+
"zh-Hant-MO": "Chinese",
|
| 579 |
+
"zh-Hant-MY": "Chinese",
|
| 580 |
+
"zh-Latn": "Chinese",
|
| 581 |
+
"zu": "Zulu",
|
| 582 |
+
"zu-ZA": "Zulu",
|
| 583 |
+
}
|
| 584 |
+
-%}
|
| 585 |
+
{{ bos_token }}
|
| 586 |
+
{%- if (messages[0]['role'] != 'user') -%}
|
| 587 |
+
{{ raise_exception("Conversations must start with a user prompt.") }}
|
| 588 |
+
{%- endif -%}
|
| 589 |
+
{%- for message in messages -%}
|
| 590 |
+
{%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
|
| 591 |
+
{{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
|
| 592 |
+
{%- endif -%}
|
| 593 |
+
{%- if (message['role'] == 'assistant') -%}
|
| 594 |
+
{%- if message['content'] is none or message['content'] is not string -%}
|
| 595 |
+
{{ raise_exception("Assistant role must provide content as a string") }}
|
| 596 |
+
{%- endif -%}
|
| 597 |
+
{{ '<start_of_turn>model\n'}}
|
| 598 |
+
{{ message["content"] | trim }}
|
| 599 |
+
{%- elif (message['role'] == 'user') -%}
|
| 600 |
+
{%- if message['content'] is none or message['content'] is not iterable or message['content'] | length != 1 -%}
|
| 601 |
+
{{ raise_exception(
|
| 602 |
+
"User role must provide `content` as an iterable with exactly one item. That item must be a " +
|
| 603 |
+
"`mapping(type:'text' | 'image', source_lang_code:string, target_lang_code:string, " +
|
| 604 |
+
"text:string | none, image:string | none)`."
|
| 605 |
+
) }}
|
| 606 |
+
{%- endif -%}
|
| 607 |
+
{%- set content = message["content"][0] -%}
|
| 608 |
+
{%- set source_lang_code = content["source_lang_code"] | replace("_", "-") -%}
|
| 609 |
+
{%- set source_lang = languages[source_lang_code] -%}
|
| 610 |
+
{%- set target_lang_code = content["target_lang_code"] | replace("_", "-") -%}
|
| 611 |
+
{%- set target_lang = languages[target_lang_code] -%}
|
| 612 |
+
{{ '<start_of_turn>user\nYou are a professional ' + source_lang + ' (' + source_lang_code + ') to ' +
|
| 613 |
+
target_lang + ' (' + target_lang_code + ') translator. Your goal is to accurately convey the meaning and '
|
| 614 |
+
'nuances of the original ' + source_lang + ' text while adhering to ' + target_lang + ' grammar, '
|
| 615 |
+
'vocabulary, and cultural sensitivities.\n'
|
| 616 |
+
}}
|
| 617 |
+
{%- if content["type"] == 'text' -%}
|
| 618 |
+
{{
|
| 619 |
+
'Produce only the ' + target_lang + ' translation, without any additional explanations or ' +
|
| 620 |
+
'commentary. Please translate the following ' + source_lang + ' text into ' + target_lang + ':\n\n\n' +
|
| 621 |
+
content["text"] | trim
|
| 622 |
+
}}
|
| 623 |
+
{%- elif content["type"] == 'image' -%}
|
| 624 |
+
{{
|
| 625 |
+
'Please translate the ' + source_lang + ' text in the provided image into ' + target_lang + '. ' +
|
| 626 |
+
'Produce only the ' + target_lang + ' translation, without any additional explanations, ' +
|
| 627 |
+
'alternatives or commentary. Focus only on the text, do not output where the text is located, ' +
|
| 628 |
+
'surrounding objects or any other explanation about the picture. Ignore symbols, pictogram, and ' +
|
| 629 |
+
'arrows!\n\n\n<start_of_image>'
|
| 630 |
+
}}
|
| 631 |
+
{%- else -%}
|
| 632 |
+
{{ raise_exception("User role `content` can contain either `text` or `image` data.") }}
|
| 633 |
+
{%- endif -%}
|
| 634 |
+
{%- else -%}
|
| 635 |
+
{{ raise_exception("Conversations must only contain user or assistant roles.") }}
|
| 636 |
+
{%- endif -%}
|
| 637 |
+
{{ '<end_of_turn>\n' }}
|
| 638 |
+
{%- endfor -%}
|
| 639 |
+
{%- if add_generation_prompt -%}
|
| 640 |
+
{{'<start_of_turn>model\n'}}
|
| 641 |
+
{%- endif -%}
|
config.json
ADDED
|
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Gemma3ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"boi_token_index": 255999,
|
| 6 |
+
"dtype": "bfloat16",
|
| 7 |
+
"eoi_token_index": 256000,
|
| 8 |
+
"eos_token_id": [
|
| 9 |
+
1,
|
| 10 |
+
106
|
| 11 |
+
],
|
| 12 |
+
"image_token_index": 262144,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"mm_tokens_per_image": 256,
|
| 15 |
+
"model_type": "gemma3",
|
| 16 |
+
"quantization": {
|
| 17 |
+
"group_size": 64,
|
| 18 |
+
"bits": 4,
|
| 19 |
+
"mode": "affine"
|
| 20 |
+
},
|
| 21 |
+
"quantization_config": {
|
| 22 |
+
"group_size": 64,
|
| 23 |
+
"bits": 4,
|
| 24 |
+
"mode": "affine"
|
| 25 |
+
},
|
| 26 |
+
"text_config": {
|
| 27 |
+
"_sliding_window_pattern": 6,
|
| 28 |
+
"attention_bias": false,
|
| 29 |
+
"attention_dropout": 0.0,
|
| 30 |
+
"attn_logit_softcapping": null,
|
| 31 |
+
"dtype": "bfloat16",
|
| 32 |
+
"final_logit_softcapping": null,
|
| 33 |
+
"head_dim": 256,
|
| 34 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 35 |
+
"hidden_size": 2560,
|
| 36 |
+
"initializer_range": 0.02,
|
| 37 |
+
"intermediate_size": 10240,
|
| 38 |
+
"layer_types": [
|
| 39 |
+
"sliding_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
+
"sliding_attention",
|
| 43 |
+
"sliding_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"sliding_attention",
|
| 46 |
+
"sliding_attention",
|
| 47 |
+
"sliding_attention",
|
| 48 |
+
"sliding_attention",
|
| 49 |
+
"sliding_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"sliding_attention",
|
| 52 |
+
"sliding_attention",
|
| 53 |
+
"sliding_attention",
|
| 54 |
+
"sliding_attention",
|
| 55 |
+
"sliding_attention",
|
| 56 |
+
"full_attention",
|
| 57 |
+
"sliding_attention",
|
| 58 |
+
"sliding_attention",
|
| 59 |
+
"sliding_attention",
|
| 60 |
+
"sliding_attention",
|
| 61 |
+
"sliding_attention",
|
| 62 |
+
"full_attention",
|
| 63 |
+
"sliding_attention",
|
| 64 |
+
"sliding_attention",
|
| 65 |
+
"sliding_attention",
|
| 66 |
+
"sliding_attention",
|
| 67 |
+
"sliding_attention",
|
| 68 |
+
"full_attention",
|
| 69 |
+
"sliding_attention",
|
| 70 |
+
"sliding_attention",
|
| 71 |
+
"sliding_attention",
|
| 72 |
+
"sliding_attention"
|
| 73 |
+
],
|
| 74 |
+
"max_position_embeddings": 131072,
|
| 75 |
+
"model_type": "gemma3_text",
|
| 76 |
+
"num_attention_heads": 8,
|
| 77 |
+
"num_hidden_layers": 34,
|
| 78 |
+
"num_key_value_heads": 4,
|
| 79 |
+
"query_pre_attn_scalar": 256,
|
| 80 |
+
"rms_norm_eps": 1e-06,
|
| 81 |
+
"rope_local_base_freq": 10000,
|
| 82 |
+
"rope_parameters": {
|
| 83 |
+
"full_attention": {
|
| 84 |
+
"factor": 8.0,
|
| 85 |
+
"rope_type": "linear"
|
| 86 |
+
},
|
| 87 |
+
"sliding_attention": {
|
| 88 |
+
"rope_type": "default"
|
| 89 |
+
}
|
| 90 |
+
},
|
| 91 |
+
"rope_scaling": null,
|
| 92 |
+
"rope_theta": 1000000,
|
| 93 |
+
"sliding_window": 1024,
|
| 94 |
+
"use_bidirectional_attention": false,
|
| 95 |
+
"use_cache": true,
|
| 96 |
+
"vocab_size": 262208
|
| 97 |
+
},
|
| 98 |
+
"transformers_version": "4.57.3"
|
| 99 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cache_implementation": "hybrid",
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [1, 106],
|
| 5 |
+
"top_k": 64,
|
| 6 |
+
"top_p": 0.95,
|
| 7 |
+
"transformers_version": "4.57.3"
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:113acb0c29997a3015af84bec2c8f967cb7b15f8959d1c26b9628b921e324c40
|
| 3 |
+
size 2183295977
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,930 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 2183177216,
|
| 4 |
+
"total_parameters": 3880263168
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"language_model.model.embed_tokens.biases": "model.safetensors",
|
| 8 |
+
"language_model.model.embed_tokens.scales": "model.safetensors",
|
| 9 |
+
"language_model.model.embed_tokens.weight": "model.safetensors",
|
| 10 |
+
"language_model.model.layers.0.input_layernorm.weight": "model.safetensors",
|
| 11 |
+
"language_model.model.layers.0.mlp.down_proj.biases": "model.safetensors",
|
| 12 |
+
"language_model.model.layers.0.mlp.down_proj.scales": "model.safetensors",
|
| 13 |
+
"language_model.model.layers.0.mlp.down_proj.weight": "model.safetensors",
|
| 14 |
+
"language_model.model.layers.0.mlp.gate_proj.biases": "model.safetensors",
|
| 15 |
+
"language_model.model.layers.0.mlp.gate_proj.scales": "model.safetensors",
|
| 16 |
+
"language_model.model.layers.0.mlp.gate_proj.weight": "model.safetensors",
|
| 17 |
+
"language_model.model.layers.0.mlp.up_proj.biases": "model.safetensors",
|
| 18 |
+
"language_model.model.layers.0.mlp.up_proj.scales": "model.safetensors",
|
| 19 |
+
"language_model.model.layers.0.mlp.up_proj.weight": "model.safetensors",
|
| 20 |
+
"language_model.model.layers.0.post_attention_layernorm.weight": "model.safetensors",
|
| 21 |
+
"language_model.model.layers.0.post_feedforward_layernorm.weight": "model.safetensors",
|
| 22 |
+
"language_model.model.layers.0.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 23 |
+
"language_model.model.layers.0.self_attn.k_norm.weight": "model.safetensors",
|
| 24 |
+
"language_model.model.layers.0.self_attn.k_proj.biases": "model.safetensors",
|
| 25 |
+
"language_model.model.layers.0.self_attn.k_proj.scales": "model.safetensors",
|
| 26 |
+
"language_model.model.layers.0.self_attn.k_proj.weight": "model.safetensors",
|
| 27 |
+
"language_model.model.layers.0.self_attn.o_proj.biases": "model.safetensors",
|
| 28 |
+
"language_model.model.layers.0.self_attn.o_proj.scales": "model.safetensors",
|
| 29 |
+
"language_model.model.layers.0.self_attn.o_proj.weight": "model.safetensors",
|
| 30 |
+
"language_model.model.layers.0.self_attn.q_norm.weight": "model.safetensors",
|
| 31 |
+
"language_model.model.layers.0.self_attn.q_proj.biases": "model.safetensors",
|
| 32 |
+
"language_model.model.layers.0.self_attn.q_proj.scales": "model.safetensors",
|
| 33 |
+
"language_model.model.layers.0.self_attn.q_proj.weight": "model.safetensors",
|
| 34 |
+
"language_model.model.layers.0.self_attn.v_proj.biases": "model.safetensors",
|
| 35 |
+
"language_model.model.layers.0.self_attn.v_proj.scales": "model.safetensors",
|
| 36 |
+
"language_model.model.layers.0.self_attn.v_proj.weight": "model.safetensors",
|
| 37 |
+
"language_model.model.layers.1.input_layernorm.weight": "model.safetensors",
|
| 38 |
+
"language_model.model.layers.1.mlp.down_proj.biases": "model.safetensors",
|
| 39 |
+
"language_model.model.layers.1.mlp.down_proj.scales": "model.safetensors",
|
| 40 |
+
"language_model.model.layers.1.mlp.down_proj.weight": "model.safetensors",
|
| 41 |
+
"language_model.model.layers.1.mlp.gate_proj.biases": "model.safetensors",
|
| 42 |
+
"language_model.model.layers.1.mlp.gate_proj.scales": "model.safetensors",
|
| 43 |
+
"language_model.model.layers.1.mlp.gate_proj.weight": "model.safetensors",
|
| 44 |
+
"language_model.model.layers.1.mlp.up_proj.biases": "model.safetensors",
|
| 45 |
+
"language_model.model.layers.1.mlp.up_proj.scales": "model.safetensors",
|
| 46 |
+
"language_model.model.layers.1.mlp.up_proj.weight": "model.safetensors",
|
| 47 |
+
"language_model.model.layers.1.post_attention_layernorm.weight": "model.safetensors",
|
| 48 |
+
"language_model.model.layers.1.post_feedforward_layernorm.weight": "model.safetensors",
|
| 49 |
+
"language_model.model.layers.1.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 50 |
+
"language_model.model.layers.1.self_attn.k_norm.weight": "model.safetensors",
|
| 51 |
+
"language_model.model.layers.1.self_attn.k_proj.biases": "model.safetensors",
|
| 52 |
+
"language_model.model.layers.1.self_attn.k_proj.scales": "model.safetensors",
|
| 53 |
+
"language_model.model.layers.1.self_attn.k_proj.weight": "model.safetensors",
|
| 54 |
+
"language_model.model.layers.1.self_attn.o_proj.biases": "model.safetensors",
|
| 55 |
+
"language_model.model.layers.1.self_attn.o_proj.scales": "model.safetensors",
|
| 56 |
+
"language_model.model.layers.1.self_attn.o_proj.weight": "model.safetensors",
|
| 57 |
+
"language_model.model.layers.1.self_attn.q_norm.weight": "model.safetensors",
|
| 58 |
+
"language_model.model.layers.1.self_attn.q_proj.biases": "model.safetensors",
|
| 59 |
+
"language_model.model.layers.1.self_attn.q_proj.scales": "model.safetensors",
|
| 60 |
+
"language_model.model.layers.1.self_attn.q_proj.weight": "model.safetensors",
|
| 61 |
+
"language_model.model.layers.1.self_attn.v_proj.biases": "model.safetensors",
|
| 62 |
+
"language_model.model.layers.1.self_attn.v_proj.scales": "model.safetensors",
|
| 63 |
+
"language_model.model.layers.1.self_attn.v_proj.weight": "model.safetensors",
|
| 64 |
+
"language_model.model.layers.10.input_layernorm.weight": "model.safetensors",
|
| 65 |
+
"language_model.model.layers.10.mlp.down_proj.biases": "model.safetensors",
|
| 66 |
+
"language_model.model.layers.10.mlp.down_proj.scales": "model.safetensors",
|
| 67 |
+
"language_model.model.layers.10.mlp.down_proj.weight": "model.safetensors",
|
| 68 |
+
"language_model.model.layers.10.mlp.gate_proj.biases": "model.safetensors",
|
| 69 |
+
"language_model.model.layers.10.mlp.gate_proj.scales": "model.safetensors",
|
| 70 |
+
"language_model.model.layers.10.mlp.gate_proj.weight": "model.safetensors",
|
| 71 |
+
"language_model.model.layers.10.mlp.up_proj.biases": "model.safetensors",
|
| 72 |
+
"language_model.model.layers.10.mlp.up_proj.scales": "model.safetensors",
|
| 73 |
+
"language_model.model.layers.10.mlp.up_proj.weight": "model.safetensors",
|
| 74 |
+
"language_model.model.layers.10.post_attention_layernorm.weight": "model.safetensors",
|
| 75 |
+
"language_model.model.layers.10.post_feedforward_layernorm.weight": "model.safetensors",
|
| 76 |
+
"language_model.model.layers.10.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 77 |
+
"language_model.model.layers.10.self_attn.k_norm.weight": "model.safetensors",
|
| 78 |
+
"language_model.model.layers.10.self_attn.k_proj.biases": "model.safetensors",
|
| 79 |
+
"language_model.model.layers.10.self_attn.k_proj.scales": "model.safetensors",
|
| 80 |
+
"language_model.model.layers.10.self_attn.k_proj.weight": "model.safetensors",
|
| 81 |
+
"language_model.model.layers.10.self_attn.o_proj.biases": "model.safetensors",
|
| 82 |
+
"language_model.model.layers.10.self_attn.o_proj.scales": "model.safetensors",
|
| 83 |
+
"language_model.model.layers.10.self_attn.o_proj.weight": "model.safetensors",
|
| 84 |
+
"language_model.model.layers.10.self_attn.q_norm.weight": "model.safetensors",
|
| 85 |
+
"language_model.model.layers.10.self_attn.q_proj.biases": "model.safetensors",
|
| 86 |
+
"language_model.model.layers.10.self_attn.q_proj.scales": "model.safetensors",
|
| 87 |
+
"language_model.model.layers.10.self_attn.q_proj.weight": "model.safetensors",
|
| 88 |
+
"language_model.model.layers.10.self_attn.v_proj.biases": "model.safetensors",
|
| 89 |
+
"language_model.model.layers.10.self_attn.v_proj.scales": "model.safetensors",
|
| 90 |
+
"language_model.model.layers.10.self_attn.v_proj.weight": "model.safetensors",
|
| 91 |
+
"language_model.model.layers.11.input_layernorm.weight": "model.safetensors",
|
| 92 |
+
"language_model.model.layers.11.mlp.down_proj.biases": "model.safetensors",
|
| 93 |
+
"language_model.model.layers.11.mlp.down_proj.scales": "model.safetensors",
|
| 94 |
+
"language_model.model.layers.11.mlp.down_proj.weight": "model.safetensors",
|
| 95 |
+
"language_model.model.layers.11.mlp.gate_proj.biases": "model.safetensors",
|
| 96 |
+
"language_model.model.layers.11.mlp.gate_proj.scales": "model.safetensors",
|
| 97 |
+
"language_model.model.layers.11.mlp.gate_proj.weight": "model.safetensors",
|
| 98 |
+
"language_model.model.layers.11.mlp.up_proj.biases": "model.safetensors",
|
| 99 |
+
"language_model.model.layers.11.mlp.up_proj.scales": "model.safetensors",
|
| 100 |
+
"language_model.model.layers.11.mlp.up_proj.weight": "model.safetensors",
|
| 101 |
+
"language_model.model.layers.11.post_attention_layernorm.weight": "model.safetensors",
|
| 102 |
+
"language_model.model.layers.11.post_feedforward_layernorm.weight": "model.safetensors",
|
| 103 |
+
"language_model.model.layers.11.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 104 |
+
"language_model.model.layers.11.self_attn.k_norm.weight": "model.safetensors",
|
| 105 |
+
"language_model.model.layers.11.self_attn.k_proj.biases": "model.safetensors",
|
| 106 |
+
"language_model.model.layers.11.self_attn.k_proj.scales": "model.safetensors",
|
| 107 |
+
"language_model.model.layers.11.self_attn.k_proj.weight": "model.safetensors",
|
| 108 |
+
"language_model.model.layers.11.self_attn.o_proj.biases": "model.safetensors",
|
| 109 |
+
"language_model.model.layers.11.self_attn.o_proj.scales": "model.safetensors",
|
| 110 |
+
"language_model.model.layers.11.self_attn.o_proj.weight": "model.safetensors",
|
| 111 |
+
"language_model.model.layers.11.self_attn.q_norm.weight": "model.safetensors",
|
| 112 |
+
"language_model.model.layers.11.self_attn.q_proj.biases": "model.safetensors",
|
| 113 |
+
"language_model.model.layers.11.self_attn.q_proj.scales": "model.safetensors",
|
| 114 |
+
"language_model.model.layers.11.self_attn.q_proj.weight": "model.safetensors",
|
| 115 |
+
"language_model.model.layers.11.self_attn.v_proj.biases": "model.safetensors",
|
| 116 |
+
"language_model.model.layers.11.self_attn.v_proj.scales": "model.safetensors",
|
| 117 |
+
"language_model.model.layers.11.self_attn.v_proj.weight": "model.safetensors",
|
| 118 |
+
"language_model.model.layers.12.input_layernorm.weight": "model.safetensors",
|
| 119 |
+
"language_model.model.layers.12.mlp.down_proj.biases": "model.safetensors",
|
| 120 |
+
"language_model.model.layers.12.mlp.down_proj.scales": "model.safetensors",
|
| 121 |
+
"language_model.model.layers.12.mlp.down_proj.weight": "model.safetensors",
|
| 122 |
+
"language_model.model.layers.12.mlp.gate_proj.biases": "model.safetensors",
|
| 123 |
+
"language_model.model.layers.12.mlp.gate_proj.scales": "model.safetensors",
|
| 124 |
+
"language_model.model.layers.12.mlp.gate_proj.weight": "model.safetensors",
|
| 125 |
+
"language_model.model.layers.12.mlp.up_proj.biases": "model.safetensors",
|
| 126 |
+
"language_model.model.layers.12.mlp.up_proj.scales": "model.safetensors",
|
| 127 |
+
"language_model.model.layers.12.mlp.up_proj.weight": "model.safetensors",
|
| 128 |
+
"language_model.model.layers.12.post_attention_layernorm.weight": "model.safetensors",
|
| 129 |
+
"language_model.model.layers.12.post_feedforward_layernorm.weight": "model.safetensors",
|
| 130 |
+
"language_model.model.layers.12.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 131 |
+
"language_model.model.layers.12.self_attn.k_norm.weight": "model.safetensors",
|
| 132 |
+
"language_model.model.layers.12.self_attn.k_proj.biases": "model.safetensors",
|
| 133 |
+
"language_model.model.layers.12.self_attn.k_proj.scales": "model.safetensors",
|
| 134 |
+
"language_model.model.layers.12.self_attn.k_proj.weight": "model.safetensors",
|
| 135 |
+
"language_model.model.layers.12.self_attn.o_proj.biases": "model.safetensors",
|
| 136 |
+
"language_model.model.layers.12.self_attn.o_proj.scales": "model.safetensors",
|
| 137 |
+
"language_model.model.layers.12.self_attn.o_proj.weight": "model.safetensors",
|
| 138 |
+
"language_model.model.layers.12.self_attn.q_norm.weight": "model.safetensors",
|
| 139 |
+
"language_model.model.layers.12.self_attn.q_proj.biases": "model.safetensors",
|
| 140 |
+
"language_model.model.layers.12.self_attn.q_proj.scales": "model.safetensors",
|
| 141 |
+
"language_model.model.layers.12.self_attn.q_proj.weight": "model.safetensors",
|
| 142 |
+
"language_model.model.layers.12.self_attn.v_proj.biases": "model.safetensors",
|
| 143 |
+
"language_model.model.layers.12.self_attn.v_proj.scales": "model.safetensors",
|
| 144 |
+
"language_model.model.layers.12.self_attn.v_proj.weight": "model.safetensors",
|
| 145 |
+
"language_model.model.layers.13.input_layernorm.weight": "model.safetensors",
|
| 146 |
+
"language_model.model.layers.13.mlp.down_proj.biases": "model.safetensors",
|
| 147 |
+
"language_model.model.layers.13.mlp.down_proj.scales": "model.safetensors",
|
| 148 |
+
"language_model.model.layers.13.mlp.down_proj.weight": "model.safetensors",
|
| 149 |
+
"language_model.model.layers.13.mlp.gate_proj.biases": "model.safetensors",
|
| 150 |
+
"language_model.model.layers.13.mlp.gate_proj.scales": "model.safetensors",
|
| 151 |
+
"language_model.model.layers.13.mlp.gate_proj.weight": "model.safetensors",
|
| 152 |
+
"language_model.model.layers.13.mlp.up_proj.biases": "model.safetensors",
|
| 153 |
+
"language_model.model.layers.13.mlp.up_proj.scales": "model.safetensors",
|
| 154 |
+
"language_model.model.layers.13.mlp.up_proj.weight": "model.safetensors",
|
| 155 |
+
"language_model.model.layers.13.post_attention_layernorm.weight": "model.safetensors",
|
| 156 |
+
"language_model.model.layers.13.post_feedforward_layernorm.weight": "model.safetensors",
|
| 157 |
+
"language_model.model.layers.13.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 158 |
+
"language_model.model.layers.13.self_attn.k_norm.weight": "model.safetensors",
|
| 159 |
+
"language_model.model.layers.13.self_attn.k_proj.biases": "model.safetensors",
|
| 160 |
+
"language_model.model.layers.13.self_attn.k_proj.scales": "model.safetensors",
|
| 161 |
+
"language_model.model.layers.13.self_attn.k_proj.weight": "model.safetensors",
|
| 162 |
+
"language_model.model.layers.13.self_attn.o_proj.biases": "model.safetensors",
|
| 163 |
+
"language_model.model.layers.13.self_attn.o_proj.scales": "model.safetensors",
|
| 164 |
+
"language_model.model.layers.13.self_attn.o_proj.weight": "model.safetensors",
|
| 165 |
+
"language_model.model.layers.13.self_attn.q_norm.weight": "model.safetensors",
|
| 166 |
+
"language_model.model.layers.13.self_attn.q_proj.biases": "model.safetensors",
|
| 167 |
+
"language_model.model.layers.13.self_attn.q_proj.scales": "model.safetensors",
|
| 168 |
+
"language_model.model.layers.13.self_attn.q_proj.weight": "model.safetensors",
|
| 169 |
+
"language_model.model.layers.13.self_attn.v_proj.biases": "model.safetensors",
|
| 170 |
+
"language_model.model.layers.13.self_attn.v_proj.scales": "model.safetensors",
|
| 171 |
+
"language_model.model.layers.13.self_attn.v_proj.weight": "model.safetensors",
|
| 172 |
+
"language_model.model.layers.14.input_layernorm.weight": "model.safetensors",
|
| 173 |
+
"language_model.model.layers.14.mlp.down_proj.biases": "model.safetensors",
|
| 174 |
+
"language_model.model.layers.14.mlp.down_proj.scales": "model.safetensors",
|
| 175 |
+
"language_model.model.layers.14.mlp.down_proj.weight": "model.safetensors",
|
| 176 |
+
"language_model.model.layers.14.mlp.gate_proj.biases": "model.safetensors",
|
| 177 |
+
"language_model.model.layers.14.mlp.gate_proj.scales": "model.safetensors",
|
| 178 |
+
"language_model.model.layers.14.mlp.gate_proj.weight": "model.safetensors",
|
| 179 |
+
"language_model.model.layers.14.mlp.up_proj.biases": "model.safetensors",
|
| 180 |
+
"language_model.model.layers.14.mlp.up_proj.scales": "model.safetensors",
|
| 181 |
+
"language_model.model.layers.14.mlp.up_proj.weight": "model.safetensors",
|
| 182 |
+
"language_model.model.layers.14.post_attention_layernorm.weight": "model.safetensors",
|
| 183 |
+
"language_model.model.layers.14.post_feedforward_layernorm.weight": "model.safetensors",
|
| 184 |
+
"language_model.model.layers.14.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 185 |
+
"language_model.model.layers.14.self_attn.k_norm.weight": "model.safetensors",
|
| 186 |
+
"language_model.model.layers.14.self_attn.k_proj.biases": "model.safetensors",
|
| 187 |
+
"language_model.model.layers.14.self_attn.k_proj.scales": "model.safetensors",
|
| 188 |
+
"language_model.model.layers.14.self_attn.k_proj.weight": "model.safetensors",
|
| 189 |
+
"language_model.model.layers.14.self_attn.o_proj.biases": "model.safetensors",
|
| 190 |
+
"language_model.model.layers.14.self_attn.o_proj.scales": "model.safetensors",
|
| 191 |
+
"language_model.model.layers.14.self_attn.o_proj.weight": "model.safetensors",
|
| 192 |
+
"language_model.model.layers.14.self_attn.q_norm.weight": "model.safetensors",
|
| 193 |
+
"language_model.model.layers.14.self_attn.q_proj.biases": "model.safetensors",
|
| 194 |
+
"language_model.model.layers.14.self_attn.q_proj.scales": "model.safetensors",
|
| 195 |
+
"language_model.model.layers.14.self_attn.q_proj.weight": "model.safetensors",
|
| 196 |
+
"language_model.model.layers.14.self_attn.v_proj.biases": "model.safetensors",
|
| 197 |
+
"language_model.model.layers.14.self_attn.v_proj.scales": "model.safetensors",
|
| 198 |
+
"language_model.model.layers.14.self_attn.v_proj.weight": "model.safetensors",
|
| 199 |
+
"language_model.model.layers.15.input_layernorm.weight": "model.safetensors",
|
| 200 |
+
"language_model.model.layers.15.mlp.down_proj.biases": "model.safetensors",
|
| 201 |
+
"language_model.model.layers.15.mlp.down_proj.scales": "model.safetensors",
|
| 202 |
+
"language_model.model.layers.15.mlp.down_proj.weight": "model.safetensors",
|
| 203 |
+
"language_model.model.layers.15.mlp.gate_proj.biases": "model.safetensors",
|
| 204 |
+
"language_model.model.layers.15.mlp.gate_proj.scales": "model.safetensors",
|
| 205 |
+
"language_model.model.layers.15.mlp.gate_proj.weight": "model.safetensors",
|
| 206 |
+
"language_model.model.layers.15.mlp.up_proj.biases": "model.safetensors",
|
| 207 |
+
"language_model.model.layers.15.mlp.up_proj.scales": "model.safetensors",
|
| 208 |
+
"language_model.model.layers.15.mlp.up_proj.weight": "model.safetensors",
|
| 209 |
+
"language_model.model.layers.15.post_attention_layernorm.weight": "model.safetensors",
|
| 210 |
+
"language_model.model.layers.15.post_feedforward_layernorm.weight": "model.safetensors",
|
| 211 |
+
"language_model.model.layers.15.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 212 |
+
"language_model.model.layers.15.self_attn.k_norm.weight": "model.safetensors",
|
| 213 |
+
"language_model.model.layers.15.self_attn.k_proj.biases": "model.safetensors",
|
| 214 |
+
"language_model.model.layers.15.self_attn.k_proj.scales": "model.safetensors",
|
| 215 |
+
"language_model.model.layers.15.self_attn.k_proj.weight": "model.safetensors",
|
| 216 |
+
"language_model.model.layers.15.self_attn.o_proj.biases": "model.safetensors",
|
| 217 |
+
"language_model.model.layers.15.self_attn.o_proj.scales": "model.safetensors",
|
| 218 |
+
"language_model.model.layers.15.self_attn.o_proj.weight": "model.safetensors",
|
| 219 |
+
"language_model.model.layers.15.self_attn.q_norm.weight": "model.safetensors",
|
| 220 |
+
"language_model.model.layers.15.self_attn.q_proj.biases": "model.safetensors",
|
| 221 |
+
"language_model.model.layers.15.self_attn.q_proj.scales": "model.safetensors",
|
| 222 |
+
"language_model.model.layers.15.self_attn.q_proj.weight": "model.safetensors",
|
| 223 |
+
"language_model.model.layers.15.self_attn.v_proj.biases": "model.safetensors",
|
| 224 |
+
"language_model.model.layers.15.self_attn.v_proj.scales": "model.safetensors",
|
| 225 |
+
"language_model.model.layers.15.self_attn.v_proj.weight": "model.safetensors",
|
| 226 |
+
"language_model.model.layers.16.input_layernorm.weight": "model.safetensors",
|
| 227 |
+
"language_model.model.layers.16.mlp.down_proj.biases": "model.safetensors",
|
| 228 |
+
"language_model.model.layers.16.mlp.down_proj.scales": "model.safetensors",
|
| 229 |
+
"language_model.model.layers.16.mlp.down_proj.weight": "model.safetensors",
|
| 230 |
+
"language_model.model.layers.16.mlp.gate_proj.biases": "model.safetensors",
|
| 231 |
+
"language_model.model.layers.16.mlp.gate_proj.scales": "model.safetensors",
|
| 232 |
+
"language_model.model.layers.16.mlp.gate_proj.weight": "model.safetensors",
|
| 233 |
+
"language_model.model.layers.16.mlp.up_proj.biases": "model.safetensors",
|
| 234 |
+
"language_model.model.layers.16.mlp.up_proj.scales": "model.safetensors",
|
| 235 |
+
"language_model.model.layers.16.mlp.up_proj.weight": "model.safetensors",
|
| 236 |
+
"language_model.model.layers.16.post_attention_layernorm.weight": "model.safetensors",
|
| 237 |
+
"language_model.model.layers.16.post_feedforward_layernorm.weight": "model.safetensors",
|
| 238 |
+
"language_model.model.layers.16.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 239 |
+
"language_model.model.layers.16.self_attn.k_norm.weight": "model.safetensors",
|
| 240 |
+
"language_model.model.layers.16.self_attn.k_proj.biases": "model.safetensors",
|
| 241 |
+
"language_model.model.layers.16.self_attn.k_proj.scales": "model.safetensors",
|
| 242 |
+
"language_model.model.layers.16.self_attn.k_proj.weight": "model.safetensors",
|
| 243 |
+
"language_model.model.layers.16.self_attn.o_proj.biases": "model.safetensors",
|
| 244 |
+
"language_model.model.layers.16.self_attn.o_proj.scales": "model.safetensors",
|
| 245 |
+
"language_model.model.layers.16.self_attn.o_proj.weight": "model.safetensors",
|
| 246 |
+
"language_model.model.layers.16.self_attn.q_norm.weight": "model.safetensors",
|
| 247 |
+
"language_model.model.layers.16.self_attn.q_proj.biases": "model.safetensors",
|
| 248 |
+
"language_model.model.layers.16.self_attn.q_proj.scales": "model.safetensors",
|
| 249 |
+
"language_model.model.layers.16.self_attn.q_proj.weight": "model.safetensors",
|
| 250 |
+
"language_model.model.layers.16.self_attn.v_proj.biases": "model.safetensors",
|
| 251 |
+
"language_model.model.layers.16.self_attn.v_proj.scales": "model.safetensors",
|
| 252 |
+
"language_model.model.layers.16.self_attn.v_proj.weight": "model.safetensors",
|
| 253 |
+
"language_model.model.layers.17.input_layernorm.weight": "model.safetensors",
|
| 254 |
+
"language_model.model.layers.17.mlp.down_proj.biases": "model.safetensors",
|
| 255 |
+
"language_model.model.layers.17.mlp.down_proj.scales": "model.safetensors",
|
| 256 |
+
"language_model.model.layers.17.mlp.down_proj.weight": "model.safetensors",
|
| 257 |
+
"language_model.model.layers.17.mlp.gate_proj.biases": "model.safetensors",
|
| 258 |
+
"language_model.model.layers.17.mlp.gate_proj.scales": "model.safetensors",
|
| 259 |
+
"language_model.model.layers.17.mlp.gate_proj.weight": "model.safetensors",
|
| 260 |
+
"language_model.model.layers.17.mlp.up_proj.biases": "model.safetensors",
|
| 261 |
+
"language_model.model.layers.17.mlp.up_proj.scales": "model.safetensors",
|
| 262 |
+
"language_model.model.layers.17.mlp.up_proj.weight": "model.safetensors",
|
| 263 |
+
"language_model.model.layers.17.post_attention_layernorm.weight": "model.safetensors",
|
| 264 |
+
"language_model.model.layers.17.post_feedforward_layernorm.weight": "model.safetensors",
|
| 265 |
+
"language_model.model.layers.17.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 266 |
+
"language_model.model.layers.17.self_attn.k_norm.weight": "model.safetensors",
|
| 267 |
+
"language_model.model.layers.17.self_attn.k_proj.biases": "model.safetensors",
|
| 268 |
+
"language_model.model.layers.17.self_attn.k_proj.scales": "model.safetensors",
|
| 269 |
+
"language_model.model.layers.17.self_attn.k_proj.weight": "model.safetensors",
|
| 270 |
+
"language_model.model.layers.17.self_attn.o_proj.biases": "model.safetensors",
|
| 271 |
+
"language_model.model.layers.17.self_attn.o_proj.scales": "model.safetensors",
|
| 272 |
+
"language_model.model.layers.17.self_attn.o_proj.weight": "model.safetensors",
|
| 273 |
+
"language_model.model.layers.17.self_attn.q_norm.weight": "model.safetensors",
|
| 274 |
+
"language_model.model.layers.17.self_attn.q_proj.biases": "model.safetensors",
|
| 275 |
+
"language_model.model.layers.17.self_attn.q_proj.scales": "model.safetensors",
|
| 276 |
+
"language_model.model.layers.17.self_attn.q_proj.weight": "model.safetensors",
|
| 277 |
+
"language_model.model.layers.17.self_attn.v_proj.biases": "model.safetensors",
|
| 278 |
+
"language_model.model.layers.17.self_attn.v_proj.scales": "model.safetensors",
|
| 279 |
+
"language_model.model.layers.17.self_attn.v_proj.weight": "model.safetensors",
|
| 280 |
+
"language_model.model.layers.18.input_layernorm.weight": "model.safetensors",
|
| 281 |
+
"language_model.model.layers.18.mlp.down_proj.biases": "model.safetensors",
|
| 282 |
+
"language_model.model.layers.18.mlp.down_proj.scales": "model.safetensors",
|
| 283 |
+
"language_model.model.layers.18.mlp.down_proj.weight": "model.safetensors",
|
| 284 |
+
"language_model.model.layers.18.mlp.gate_proj.biases": "model.safetensors",
|
| 285 |
+
"language_model.model.layers.18.mlp.gate_proj.scales": "model.safetensors",
|
| 286 |
+
"language_model.model.layers.18.mlp.gate_proj.weight": "model.safetensors",
|
| 287 |
+
"language_model.model.layers.18.mlp.up_proj.biases": "model.safetensors",
|
| 288 |
+
"language_model.model.layers.18.mlp.up_proj.scales": "model.safetensors",
|
| 289 |
+
"language_model.model.layers.18.mlp.up_proj.weight": "model.safetensors",
|
| 290 |
+
"language_model.model.layers.18.post_attention_layernorm.weight": "model.safetensors",
|
| 291 |
+
"language_model.model.layers.18.post_feedforward_layernorm.weight": "model.safetensors",
|
| 292 |
+
"language_model.model.layers.18.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 293 |
+
"language_model.model.layers.18.self_attn.k_norm.weight": "model.safetensors",
|
| 294 |
+
"language_model.model.layers.18.self_attn.k_proj.biases": "model.safetensors",
|
| 295 |
+
"language_model.model.layers.18.self_attn.k_proj.scales": "model.safetensors",
|
| 296 |
+
"language_model.model.layers.18.self_attn.k_proj.weight": "model.safetensors",
|
| 297 |
+
"language_model.model.layers.18.self_attn.o_proj.biases": "model.safetensors",
|
| 298 |
+
"language_model.model.layers.18.self_attn.o_proj.scales": "model.safetensors",
|
| 299 |
+
"language_model.model.layers.18.self_attn.o_proj.weight": "model.safetensors",
|
| 300 |
+
"language_model.model.layers.18.self_attn.q_norm.weight": "model.safetensors",
|
| 301 |
+
"language_model.model.layers.18.self_attn.q_proj.biases": "model.safetensors",
|
| 302 |
+
"language_model.model.layers.18.self_attn.q_proj.scales": "model.safetensors",
|
| 303 |
+
"language_model.model.layers.18.self_attn.q_proj.weight": "model.safetensors",
|
| 304 |
+
"language_model.model.layers.18.self_attn.v_proj.biases": "model.safetensors",
|
| 305 |
+
"language_model.model.layers.18.self_attn.v_proj.scales": "model.safetensors",
|
| 306 |
+
"language_model.model.layers.18.self_attn.v_proj.weight": "model.safetensors",
|
| 307 |
+
"language_model.model.layers.19.input_layernorm.weight": "model.safetensors",
|
| 308 |
+
"language_model.model.layers.19.mlp.down_proj.biases": "model.safetensors",
|
| 309 |
+
"language_model.model.layers.19.mlp.down_proj.scales": "model.safetensors",
|
| 310 |
+
"language_model.model.layers.19.mlp.down_proj.weight": "model.safetensors",
|
| 311 |
+
"language_model.model.layers.19.mlp.gate_proj.biases": "model.safetensors",
|
| 312 |
+
"language_model.model.layers.19.mlp.gate_proj.scales": "model.safetensors",
|
| 313 |
+
"language_model.model.layers.19.mlp.gate_proj.weight": "model.safetensors",
|
| 314 |
+
"language_model.model.layers.19.mlp.up_proj.biases": "model.safetensors",
|
| 315 |
+
"language_model.model.layers.19.mlp.up_proj.scales": "model.safetensors",
|
| 316 |
+
"language_model.model.layers.19.mlp.up_proj.weight": "model.safetensors",
|
| 317 |
+
"language_model.model.layers.19.post_attention_layernorm.weight": "model.safetensors",
|
| 318 |
+
"language_model.model.layers.19.post_feedforward_layernorm.weight": "model.safetensors",
|
| 319 |
+
"language_model.model.layers.19.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 320 |
+
"language_model.model.layers.19.self_attn.k_norm.weight": "model.safetensors",
|
| 321 |
+
"language_model.model.layers.19.self_attn.k_proj.biases": "model.safetensors",
|
| 322 |
+
"language_model.model.layers.19.self_attn.k_proj.scales": "model.safetensors",
|
| 323 |
+
"language_model.model.layers.19.self_attn.k_proj.weight": "model.safetensors",
|
| 324 |
+
"language_model.model.layers.19.self_attn.o_proj.biases": "model.safetensors",
|
| 325 |
+
"language_model.model.layers.19.self_attn.o_proj.scales": "model.safetensors",
|
| 326 |
+
"language_model.model.layers.19.self_attn.o_proj.weight": "model.safetensors",
|
| 327 |
+
"language_model.model.layers.19.self_attn.q_norm.weight": "model.safetensors",
|
| 328 |
+
"language_model.model.layers.19.self_attn.q_proj.biases": "model.safetensors",
|
| 329 |
+
"language_model.model.layers.19.self_attn.q_proj.scales": "model.safetensors",
|
| 330 |
+
"language_model.model.layers.19.self_attn.q_proj.weight": "model.safetensors",
|
| 331 |
+
"language_model.model.layers.19.self_attn.v_proj.biases": "model.safetensors",
|
| 332 |
+
"language_model.model.layers.19.self_attn.v_proj.scales": "model.safetensors",
|
| 333 |
+
"language_model.model.layers.19.self_attn.v_proj.weight": "model.safetensors",
|
| 334 |
+
"language_model.model.layers.2.input_layernorm.weight": "model.safetensors",
|
| 335 |
+
"language_model.model.layers.2.mlp.down_proj.biases": "model.safetensors",
|
| 336 |
+
"language_model.model.layers.2.mlp.down_proj.scales": "model.safetensors",
|
| 337 |
+
"language_model.model.layers.2.mlp.down_proj.weight": "model.safetensors",
|
| 338 |
+
"language_model.model.layers.2.mlp.gate_proj.biases": "model.safetensors",
|
| 339 |
+
"language_model.model.layers.2.mlp.gate_proj.scales": "model.safetensors",
|
| 340 |
+
"language_model.model.layers.2.mlp.gate_proj.weight": "model.safetensors",
|
| 341 |
+
"language_model.model.layers.2.mlp.up_proj.biases": "model.safetensors",
|
| 342 |
+
"language_model.model.layers.2.mlp.up_proj.scales": "model.safetensors",
|
| 343 |
+
"language_model.model.layers.2.mlp.up_proj.weight": "model.safetensors",
|
| 344 |
+
"language_model.model.layers.2.post_attention_layernorm.weight": "model.safetensors",
|
| 345 |
+
"language_model.model.layers.2.post_feedforward_layernorm.weight": "model.safetensors",
|
| 346 |
+
"language_model.model.layers.2.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 347 |
+
"language_model.model.layers.2.self_attn.k_norm.weight": "model.safetensors",
|
| 348 |
+
"language_model.model.layers.2.self_attn.k_proj.biases": "model.safetensors",
|
| 349 |
+
"language_model.model.layers.2.self_attn.k_proj.scales": "model.safetensors",
|
| 350 |
+
"language_model.model.layers.2.self_attn.k_proj.weight": "model.safetensors",
|
| 351 |
+
"language_model.model.layers.2.self_attn.o_proj.biases": "model.safetensors",
|
| 352 |
+
"language_model.model.layers.2.self_attn.o_proj.scales": "model.safetensors",
|
| 353 |
+
"language_model.model.layers.2.self_attn.o_proj.weight": "model.safetensors",
|
| 354 |
+
"language_model.model.layers.2.self_attn.q_norm.weight": "model.safetensors",
|
| 355 |
+
"language_model.model.layers.2.self_attn.q_proj.biases": "model.safetensors",
|
| 356 |
+
"language_model.model.layers.2.self_attn.q_proj.scales": "model.safetensors",
|
| 357 |
+
"language_model.model.layers.2.self_attn.q_proj.weight": "model.safetensors",
|
| 358 |
+
"language_model.model.layers.2.self_attn.v_proj.biases": "model.safetensors",
|
| 359 |
+
"language_model.model.layers.2.self_attn.v_proj.scales": "model.safetensors",
|
| 360 |
+
"language_model.model.layers.2.self_attn.v_proj.weight": "model.safetensors",
|
| 361 |
+
"language_model.model.layers.20.input_layernorm.weight": "model.safetensors",
|
| 362 |
+
"language_model.model.layers.20.mlp.down_proj.biases": "model.safetensors",
|
| 363 |
+
"language_model.model.layers.20.mlp.down_proj.scales": "model.safetensors",
|
| 364 |
+
"language_model.model.layers.20.mlp.down_proj.weight": "model.safetensors",
|
| 365 |
+
"language_model.model.layers.20.mlp.gate_proj.biases": "model.safetensors",
|
| 366 |
+
"language_model.model.layers.20.mlp.gate_proj.scales": "model.safetensors",
|
| 367 |
+
"language_model.model.layers.20.mlp.gate_proj.weight": "model.safetensors",
|
| 368 |
+
"language_model.model.layers.20.mlp.up_proj.biases": "model.safetensors",
|
| 369 |
+
"language_model.model.layers.20.mlp.up_proj.scales": "model.safetensors",
|
| 370 |
+
"language_model.model.layers.20.mlp.up_proj.weight": "model.safetensors",
|
| 371 |
+
"language_model.model.layers.20.post_attention_layernorm.weight": "model.safetensors",
|
| 372 |
+
"language_model.model.layers.20.post_feedforward_layernorm.weight": "model.safetensors",
|
| 373 |
+
"language_model.model.layers.20.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 374 |
+
"language_model.model.layers.20.self_attn.k_norm.weight": "model.safetensors",
|
| 375 |
+
"language_model.model.layers.20.self_attn.k_proj.biases": "model.safetensors",
|
| 376 |
+
"language_model.model.layers.20.self_attn.k_proj.scales": "model.safetensors",
|
| 377 |
+
"language_model.model.layers.20.self_attn.k_proj.weight": "model.safetensors",
|
| 378 |
+
"language_model.model.layers.20.self_attn.o_proj.biases": "model.safetensors",
|
| 379 |
+
"language_model.model.layers.20.self_attn.o_proj.scales": "model.safetensors",
|
| 380 |
+
"language_model.model.layers.20.self_attn.o_proj.weight": "model.safetensors",
|
| 381 |
+
"language_model.model.layers.20.self_attn.q_norm.weight": "model.safetensors",
|
| 382 |
+
"language_model.model.layers.20.self_attn.q_proj.biases": "model.safetensors",
|
| 383 |
+
"language_model.model.layers.20.self_attn.q_proj.scales": "model.safetensors",
|
| 384 |
+
"language_model.model.layers.20.self_attn.q_proj.weight": "model.safetensors",
|
| 385 |
+
"language_model.model.layers.20.self_attn.v_proj.biases": "model.safetensors",
|
| 386 |
+
"language_model.model.layers.20.self_attn.v_proj.scales": "model.safetensors",
|
| 387 |
+
"language_model.model.layers.20.self_attn.v_proj.weight": "model.safetensors",
|
| 388 |
+
"language_model.model.layers.21.input_layernorm.weight": "model.safetensors",
|
| 389 |
+
"language_model.model.layers.21.mlp.down_proj.biases": "model.safetensors",
|
| 390 |
+
"language_model.model.layers.21.mlp.down_proj.scales": "model.safetensors",
|
| 391 |
+
"language_model.model.layers.21.mlp.down_proj.weight": "model.safetensors",
|
| 392 |
+
"language_model.model.layers.21.mlp.gate_proj.biases": "model.safetensors",
|
| 393 |
+
"language_model.model.layers.21.mlp.gate_proj.scales": "model.safetensors",
|
| 394 |
+
"language_model.model.layers.21.mlp.gate_proj.weight": "model.safetensors",
|
| 395 |
+
"language_model.model.layers.21.mlp.up_proj.biases": "model.safetensors",
|
| 396 |
+
"language_model.model.layers.21.mlp.up_proj.scales": "model.safetensors",
|
| 397 |
+
"language_model.model.layers.21.mlp.up_proj.weight": "model.safetensors",
|
| 398 |
+
"language_model.model.layers.21.post_attention_layernorm.weight": "model.safetensors",
|
| 399 |
+
"language_model.model.layers.21.post_feedforward_layernorm.weight": "model.safetensors",
|
| 400 |
+
"language_model.model.layers.21.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 401 |
+
"language_model.model.layers.21.self_attn.k_norm.weight": "model.safetensors",
|
| 402 |
+
"language_model.model.layers.21.self_attn.k_proj.biases": "model.safetensors",
|
| 403 |
+
"language_model.model.layers.21.self_attn.k_proj.scales": "model.safetensors",
|
| 404 |
+
"language_model.model.layers.21.self_attn.k_proj.weight": "model.safetensors",
|
| 405 |
+
"language_model.model.layers.21.self_attn.o_proj.biases": "model.safetensors",
|
| 406 |
+
"language_model.model.layers.21.self_attn.o_proj.scales": "model.safetensors",
|
| 407 |
+
"language_model.model.layers.21.self_attn.o_proj.weight": "model.safetensors",
|
| 408 |
+
"language_model.model.layers.21.self_attn.q_norm.weight": "model.safetensors",
|
| 409 |
+
"language_model.model.layers.21.self_attn.q_proj.biases": "model.safetensors",
|
| 410 |
+
"language_model.model.layers.21.self_attn.q_proj.scales": "model.safetensors",
|
| 411 |
+
"language_model.model.layers.21.self_attn.q_proj.weight": "model.safetensors",
|
| 412 |
+
"language_model.model.layers.21.self_attn.v_proj.biases": "model.safetensors",
|
| 413 |
+
"language_model.model.layers.21.self_attn.v_proj.scales": "model.safetensors",
|
| 414 |
+
"language_model.model.layers.21.self_attn.v_proj.weight": "model.safetensors",
|
| 415 |
+
"language_model.model.layers.22.input_layernorm.weight": "model.safetensors",
|
| 416 |
+
"language_model.model.layers.22.mlp.down_proj.biases": "model.safetensors",
|
| 417 |
+
"language_model.model.layers.22.mlp.down_proj.scales": "model.safetensors",
|
| 418 |
+
"language_model.model.layers.22.mlp.down_proj.weight": "model.safetensors",
|
| 419 |
+
"language_model.model.layers.22.mlp.gate_proj.biases": "model.safetensors",
|
| 420 |
+
"language_model.model.layers.22.mlp.gate_proj.scales": "model.safetensors",
|
| 421 |
+
"language_model.model.layers.22.mlp.gate_proj.weight": "model.safetensors",
|
| 422 |
+
"language_model.model.layers.22.mlp.up_proj.biases": "model.safetensors",
|
| 423 |
+
"language_model.model.layers.22.mlp.up_proj.scales": "model.safetensors",
|
| 424 |
+
"language_model.model.layers.22.mlp.up_proj.weight": "model.safetensors",
|
| 425 |
+
"language_model.model.layers.22.post_attention_layernorm.weight": "model.safetensors",
|
| 426 |
+
"language_model.model.layers.22.post_feedforward_layernorm.weight": "model.safetensors",
|
| 427 |
+
"language_model.model.layers.22.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 428 |
+
"language_model.model.layers.22.self_attn.k_norm.weight": "model.safetensors",
|
| 429 |
+
"language_model.model.layers.22.self_attn.k_proj.biases": "model.safetensors",
|
| 430 |
+
"language_model.model.layers.22.self_attn.k_proj.scales": "model.safetensors",
|
| 431 |
+
"language_model.model.layers.22.self_attn.k_proj.weight": "model.safetensors",
|
| 432 |
+
"language_model.model.layers.22.self_attn.o_proj.biases": "model.safetensors",
|
| 433 |
+
"language_model.model.layers.22.self_attn.o_proj.scales": "model.safetensors",
|
| 434 |
+
"language_model.model.layers.22.self_attn.o_proj.weight": "model.safetensors",
|
| 435 |
+
"language_model.model.layers.22.self_attn.q_norm.weight": "model.safetensors",
|
| 436 |
+
"language_model.model.layers.22.self_attn.q_proj.biases": "model.safetensors",
|
| 437 |
+
"language_model.model.layers.22.self_attn.q_proj.scales": "model.safetensors",
|
| 438 |
+
"language_model.model.layers.22.self_attn.q_proj.weight": "model.safetensors",
|
| 439 |
+
"language_model.model.layers.22.self_attn.v_proj.biases": "model.safetensors",
|
| 440 |
+
"language_model.model.layers.22.self_attn.v_proj.scales": "model.safetensors",
|
| 441 |
+
"language_model.model.layers.22.self_attn.v_proj.weight": "model.safetensors",
|
| 442 |
+
"language_model.model.layers.23.input_layernorm.weight": "model.safetensors",
|
| 443 |
+
"language_model.model.layers.23.mlp.down_proj.biases": "model.safetensors",
|
| 444 |
+
"language_model.model.layers.23.mlp.down_proj.scales": "model.safetensors",
|
| 445 |
+
"language_model.model.layers.23.mlp.down_proj.weight": "model.safetensors",
|
| 446 |
+
"language_model.model.layers.23.mlp.gate_proj.biases": "model.safetensors",
|
| 447 |
+
"language_model.model.layers.23.mlp.gate_proj.scales": "model.safetensors",
|
| 448 |
+
"language_model.model.layers.23.mlp.gate_proj.weight": "model.safetensors",
|
| 449 |
+
"language_model.model.layers.23.mlp.up_proj.biases": "model.safetensors",
|
| 450 |
+
"language_model.model.layers.23.mlp.up_proj.scales": "model.safetensors",
|
| 451 |
+
"language_model.model.layers.23.mlp.up_proj.weight": "model.safetensors",
|
| 452 |
+
"language_model.model.layers.23.post_attention_layernorm.weight": "model.safetensors",
|
| 453 |
+
"language_model.model.layers.23.post_feedforward_layernorm.weight": "model.safetensors",
|
| 454 |
+
"language_model.model.layers.23.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 455 |
+
"language_model.model.layers.23.self_attn.k_norm.weight": "model.safetensors",
|
| 456 |
+
"language_model.model.layers.23.self_attn.k_proj.biases": "model.safetensors",
|
| 457 |
+
"language_model.model.layers.23.self_attn.k_proj.scales": "model.safetensors",
|
| 458 |
+
"language_model.model.layers.23.self_attn.k_proj.weight": "model.safetensors",
|
| 459 |
+
"language_model.model.layers.23.self_attn.o_proj.biases": "model.safetensors",
|
| 460 |
+
"language_model.model.layers.23.self_attn.o_proj.scales": "model.safetensors",
|
| 461 |
+
"language_model.model.layers.23.self_attn.o_proj.weight": "model.safetensors",
|
| 462 |
+
"language_model.model.layers.23.self_attn.q_norm.weight": "model.safetensors",
|
| 463 |
+
"language_model.model.layers.23.self_attn.q_proj.biases": "model.safetensors",
|
| 464 |
+
"language_model.model.layers.23.self_attn.q_proj.scales": "model.safetensors",
|
| 465 |
+
"language_model.model.layers.23.self_attn.q_proj.weight": "model.safetensors",
|
| 466 |
+
"language_model.model.layers.23.self_attn.v_proj.biases": "model.safetensors",
|
| 467 |
+
"language_model.model.layers.23.self_attn.v_proj.scales": "model.safetensors",
|
| 468 |
+
"language_model.model.layers.23.self_attn.v_proj.weight": "model.safetensors",
|
| 469 |
+
"language_model.model.layers.24.input_layernorm.weight": "model.safetensors",
|
| 470 |
+
"language_model.model.layers.24.mlp.down_proj.biases": "model.safetensors",
|
| 471 |
+
"language_model.model.layers.24.mlp.down_proj.scales": "model.safetensors",
|
| 472 |
+
"language_model.model.layers.24.mlp.down_proj.weight": "model.safetensors",
|
| 473 |
+
"language_model.model.layers.24.mlp.gate_proj.biases": "model.safetensors",
|
| 474 |
+
"language_model.model.layers.24.mlp.gate_proj.scales": "model.safetensors",
|
| 475 |
+
"language_model.model.layers.24.mlp.gate_proj.weight": "model.safetensors",
|
| 476 |
+
"language_model.model.layers.24.mlp.up_proj.biases": "model.safetensors",
|
| 477 |
+
"language_model.model.layers.24.mlp.up_proj.scales": "model.safetensors",
|
| 478 |
+
"language_model.model.layers.24.mlp.up_proj.weight": "model.safetensors",
|
| 479 |
+
"language_model.model.layers.24.post_attention_layernorm.weight": "model.safetensors",
|
| 480 |
+
"language_model.model.layers.24.post_feedforward_layernorm.weight": "model.safetensors",
|
| 481 |
+
"language_model.model.layers.24.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 482 |
+
"language_model.model.layers.24.self_attn.k_norm.weight": "model.safetensors",
|
| 483 |
+
"language_model.model.layers.24.self_attn.k_proj.biases": "model.safetensors",
|
| 484 |
+
"language_model.model.layers.24.self_attn.k_proj.scales": "model.safetensors",
|
| 485 |
+
"language_model.model.layers.24.self_attn.k_proj.weight": "model.safetensors",
|
| 486 |
+
"language_model.model.layers.24.self_attn.o_proj.biases": "model.safetensors",
|
| 487 |
+
"language_model.model.layers.24.self_attn.o_proj.scales": "model.safetensors",
|
| 488 |
+
"language_model.model.layers.24.self_attn.o_proj.weight": "model.safetensors",
|
| 489 |
+
"language_model.model.layers.24.self_attn.q_norm.weight": "model.safetensors",
|
| 490 |
+
"language_model.model.layers.24.self_attn.q_proj.biases": "model.safetensors",
|
| 491 |
+
"language_model.model.layers.24.self_attn.q_proj.scales": "model.safetensors",
|
| 492 |
+
"language_model.model.layers.24.self_attn.q_proj.weight": "model.safetensors",
|
| 493 |
+
"language_model.model.layers.24.self_attn.v_proj.biases": "model.safetensors",
|
| 494 |
+
"language_model.model.layers.24.self_attn.v_proj.scales": "model.safetensors",
|
| 495 |
+
"language_model.model.layers.24.self_attn.v_proj.weight": "model.safetensors",
|
| 496 |
+
"language_model.model.layers.25.input_layernorm.weight": "model.safetensors",
|
| 497 |
+
"language_model.model.layers.25.mlp.down_proj.biases": "model.safetensors",
|
| 498 |
+
"language_model.model.layers.25.mlp.down_proj.scales": "model.safetensors",
|
| 499 |
+
"language_model.model.layers.25.mlp.down_proj.weight": "model.safetensors",
|
| 500 |
+
"language_model.model.layers.25.mlp.gate_proj.biases": "model.safetensors",
|
| 501 |
+
"language_model.model.layers.25.mlp.gate_proj.scales": "model.safetensors",
|
| 502 |
+
"language_model.model.layers.25.mlp.gate_proj.weight": "model.safetensors",
|
| 503 |
+
"language_model.model.layers.25.mlp.up_proj.biases": "model.safetensors",
|
| 504 |
+
"language_model.model.layers.25.mlp.up_proj.scales": "model.safetensors",
|
| 505 |
+
"language_model.model.layers.25.mlp.up_proj.weight": "model.safetensors",
|
| 506 |
+
"language_model.model.layers.25.post_attention_layernorm.weight": "model.safetensors",
|
| 507 |
+
"language_model.model.layers.25.post_feedforward_layernorm.weight": "model.safetensors",
|
| 508 |
+
"language_model.model.layers.25.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 509 |
+
"language_model.model.layers.25.self_attn.k_norm.weight": "model.safetensors",
|
| 510 |
+
"language_model.model.layers.25.self_attn.k_proj.biases": "model.safetensors",
|
| 511 |
+
"language_model.model.layers.25.self_attn.k_proj.scales": "model.safetensors",
|
| 512 |
+
"language_model.model.layers.25.self_attn.k_proj.weight": "model.safetensors",
|
| 513 |
+
"language_model.model.layers.25.self_attn.o_proj.biases": "model.safetensors",
|
| 514 |
+
"language_model.model.layers.25.self_attn.o_proj.scales": "model.safetensors",
|
| 515 |
+
"language_model.model.layers.25.self_attn.o_proj.weight": "model.safetensors",
|
| 516 |
+
"language_model.model.layers.25.self_attn.q_norm.weight": "model.safetensors",
|
| 517 |
+
"language_model.model.layers.25.self_attn.q_proj.biases": "model.safetensors",
|
| 518 |
+
"language_model.model.layers.25.self_attn.q_proj.scales": "model.safetensors",
|
| 519 |
+
"language_model.model.layers.25.self_attn.q_proj.weight": "model.safetensors",
|
| 520 |
+
"language_model.model.layers.25.self_attn.v_proj.biases": "model.safetensors",
|
| 521 |
+
"language_model.model.layers.25.self_attn.v_proj.scales": "model.safetensors",
|
| 522 |
+
"language_model.model.layers.25.self_attn.v_proj.weight": "model.safetensors",
|
| 523 |
+
"language_model.model.layers.26.input_layernorm.weight": "model.safetensors",
|
| 524 |
+
"language_model.model.layers.26.mlp.down_proj.biases": "model.safetensors",
|
| 525 |
+
"language_model.model.layers.26.mlp.down_proj.scales": "model.safetensors",
|
| 526 |
+
"language_model.model.layers.26.mlp.down_proj.weight": "model.safetensors",
|
| 527 |
+
"language_model.model.layers.26.mlp.gate_proj.biases": "model.safetensors",
|
| 528 |
+
"language_model.model.layers.26.mlp.gate_proj.scales": "model.safetensors",
|
| 529 |
+
"language_model.model.layers.26.mlp.gate_proj.weight": "model.safetensors",
|
| 530 |
+
"language_model.model.layers.26.mlp.up_proj.biases": "model.safetensors",
|
| 531 |
+
"language_model.model.layers.26.mlp.up_proj.scales": "model.safetensors",
|
| 532 |
+
"language_model.model.layers.26.mlp.up_proj.weight": "model.safetensors",
|
| 533 |
+
"language_model.model.layers.26.post_attention_layernorm.weight": "model.safetensors",
|
| 534 |
+
"language_model.model.layers.26.post_feedforward_layernorm.weight": "model.safetensors",
|
| 535 |
+
"language_model.model.layers.26.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 536 |
+
"language_model.model.layers.26.self_attn.k_norm.weight": "model.safetensors",
|
| 537 |
+
"language_model.model.layers.26.self_attn.k_proj.biases": "model.safetensors",
|
| 538 |
+
"language_model.model.layers.26.self_attn.k_proj.scales": "model.safetensors",
|
| 539 |
+
"language_model.model.layers.26.self_attn.k_proj.weight": "model.safetensors",
|
| 540 |
+
"language_model.model.layers.26.self_attn.o_proj.biases": "model.safetensors",
|
| 541 |
+
"language_model.model.layers.26.self_attn.o_proj.scales": "model.safetensors",
|
| 542 |
+
"language_model.model.layers.26.self_attn.o_proj.weight": "model.safetensors",
|
| 543 |
+
"language_model.model.layers.26.self_attn.q_norm.weight": "model.safetensors",
|
| 544 |
+
"language_model.model.layers.26.self_attn.q_proj.biases": "model.safetensors",
|
| 545 |
+
"language_model.model.layers.26.self_attn.q_proj.scales": "model.safetensors",
|
| 546 |
+
"language_model.model.layers.26.self_attn.q_proj.weight": "model.safetensors",
|
| 547 |
+
"language_model.model.layers.26.self_attn.v_proj.biases": "model.safetensors",
|
| 548 |
+
"language_model.model.layers.26.self_attn.v_proj.scales": "model.safetensors",
|
| 549 |
+
"language_model.model.layers.26.self_attn.v_proj.weight": "model.safetensors",
|
| 550 |
+
"language_model.model.layers.27.input_layernorm.weight": "model.safetensors",
|
| 551 |
+
"language_model.model.layers.27.mlp.down_proj.biases": "model.safetensors",
|
| 552 |
+
"language_model.model.layers.27.mlp.down_proj.scales": "model.safetensors",
|
| 553 |
+
"language_model.model.layers.27.mlp.down_proj.weight": "model.safetensors",
|
| 554 |
+
"language_model.model.layers.27.mlp.gate_proj.biases": "model.safetensors",
|
| 555 |
+
"language_model.model.layers.27.mlp.gate_proj.scales": "model.safetensors",
|
| 556 |
+
"language_model.model.layers.27.mlp.gate_proj.weight": "model.safetensors",
|
| 557 |
+
"language_model.model.layers.27.mlp.up_proj.biases": "model.safetensors",
|
| 558 |
+
"language_model.model.layers.27.mlp.up_proj.scales": "model.safetensors",
|
| 559 |
+
"language_model.model.layers.27.mlp.up_proj.weight": "model.safetensors",
|
| 560 |
+
"language_model.model.layers.27.post_attention_layernorm.weight": "model.safetensors",
|
| 561 |
+
"language_model.model.layers.27.post_feedforward_layernorm.weight": "model.safetensors",
|
| 562 |
+
"language_model.model.layers.27.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 563 |
+
"language_model.model.layers.27.self_attn.k_norm.weight": "model.safetensors",
|
| 564 |
+
"language_model.model.layers.27.self_attn.k_proj.biases": "model.safetensors",
|
| 565 |
+
"language_model.model.layers.27.self_attn.k_proj.scales": "model.safetensors",
|
| 566 |
+
"language_model.model.layers.27.self_attn.k_proj.weight": "model.safetensors",
|
| 567 |
+
"language_model.model.layers.27.self_attn.o_proj.biases": "model.safetensors",
|
| 568 |
+
"language_model.model.layers.27.self_attn.o_proj.scales": "model.safetensors",
|
| 569 |
+
"language_model.model.layers.27.self_attn.o_proj.weight": "model.safetensors",
|
| 570 |
+
"language_model.model.layers.27.self_attn.q_norm.weight": "model.safetensors",
|
| 571 |
+
"language_model.model.layers.27.self_attn.q_proj.biases": "model.safetensors",
|
| 572 |
+
"language_model.model.layers.27.self_attn.q_proj.scales": "model.safetensors",
|
| 573 |
+
"language_model.model.layers.27.self_attn.q_proj.weight": "model.safetensors",
|
| 574 |
+
"language_model.model.layers.27.self_attn.v_proj.biases": "model.safetensors",
|
| 575 |
+
"language_model.model.layers.27.self_attn.v_proj.scales": "model.safetensors",
|
| 576 |
+
"language_model.model.layers.27.self_attn.v_proj.weight": "model.safetensors",
|
| 577 |
+
"language_model.model.layers.28.input_layernorm.weight": "model.safetensors",
|
| 578 |
+
"language_model.model.layers.28.mlp.down_proj.biases": "model.safetensors",
|
| 579 |
+
"language_model.model.layers.28.mlp.down_proj.scales": "model.safetensors",
|
| 580 |
+
"language_model.model.layers.28.mlp.down_proj.weight": "model.safetensors",
|
| 581 |
+
"language_model.model.layers.28.mlp.gate_proj.biases": "model.safetensors",
|
| 582 |
+
"language_model.model.layers.28.mlp.gate_proj.scales": "model.safetensors",
|
| 583 |
+
"language_model.model.layers.28.mlp.gate_proj.weight": "model.safetensors",
|
| 584 |
+
"language_model.model.layers.28.mlp.up_proj.biases": "model.safetensors",
|
| 585 |
+
"language_model.model.layers.28.mlp.up_proj.scales": "model.safetensors",
|
| 586 |
+
"language_model.model.layers.28.mlp.up_proj.weight": "model.safetensors",
|
| 587 |
+
"language_model.model.layers.28.post_attention_layernorm.weight": "model.safetensors",
|
| 588 |
+
"language_model.model.layers.28.post_feedforward_layernorm.weight": "model.safetensors",
|
| 589 |
+
"language_model.model.layers.28.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 590 |
+
"language_model.model.layers.28.self_attn.k_norm.weight": "model.safetensors",
|
| 591 |
+
"language_model.model.layers.28.self_attn.k_proj.biases": "model.safetensors",
|
| 592 |
+
"language_model.model.layers.28.self_attn.k_proj.scales": "model.safetensors",
|
| 593 |
+
"language_model.model.layers.28.self_attn.k_proj.weight": "model.safetensors",
|
| 594 |
+
"language_model.model.layers.28.self_attn.o_proj.biases": "model.safetensors",
|
| 595 |
+
"language_model.model.layers.28.self_attn.o_proj.scales": "model.safetensors",
|
| 596 |
+
"language_model.model.layers.28.self_attn.o_proj.weight": "model.safetensors",
|
| 597 |
+
"language_model.model.layers.28.self_attn.q_norm.weight": "model.safetensors",
|
| 598 |
+
"language_model.model.layers.28.self_attn.q_proj.biases": "model.safetensors",
|
| 599 |
+
"language_model.model.layers.28.self_attn.q_proj.scales": "model.safetensors",
|
| 600 |
+
"language_model.model.layers.28.self_attn.q_proj.weight": "model.safetensors",
|
| 601 |
+
"language_model.model.layers.28.self_attn.v_proj.biases": "model.safetensors",
|
| 602 |
+
"language_model.model.layers.28.self_attn.v_proj.scales": "model.safetensors",
|
| 603 |
+
"language_model.model.layers.28.self_attn.v_proj.weight": "model.safetensors",
|
| 604 |
+
"language_model.model.layers.29.input_layernorm.weight": "model.safetensors",
|
| 605 |
+
"language_model.model.layers.29.mlp.down_proj.biases": "model.safetensors",
|
| 606 |
+
"language_model.model.layers.29.mlp.down_proj.scales": "model.safetensors",
|
| 607 |
+
"language_model.model.layers.29.mlp.down_proj.weight": "model.safetensors",
|
| 608 |
+
"language_model.model.layers.29.mlp.gate_proj.biases": "model.safetensors",
|
| 609 |
+
"language_model.model.layers.29.mlp.gate_proj.scales": "model.safetensors",
|
| 610 |
+
"language_model.model.layers.29.mlp.gate_proj.weight": "model.safetensors",
|
| 611 |
+
"language_model.model.layers.29.mlp.up_proj.biases": "model.safetensors",
|
| 612 |
+
"language_model.model.layers.29.mlp.up_proj.scales": "model.safetensors",
|
| 613 |
+
"language_model.model.layers.29.mlp.up_proj.weight": "model.safetensors",
|
| 614 |
+
"language_model.model.layers.29.post_attention_layernorm.weight": "model.safetensors",
|
| 615 |
+
"language_model.model.layers.29.post_feedforward_layernorm.weight": "model.safetensors",
|
| 616 |
+
"language_model.model.layers.29.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 617 |
+
"language_model.model.layers.29.self_attn.k_norm.weight": "model.safetensors",
|
| 618 |
+
"language_model.model.layers.29.self_attn.k_proj.biases": "model.safetensors",
|
| 619 |
+
"language_model.model.layers.29.self_attn.k_proj.scales": "model.safetensors",
|
| 620 |
+
"language_model.model.layers.29.self_attn.k_proj.weight": "model.safetensors",
|
| 621 |
+
"language_model.model.layers.29.self_attn.o_proj.biases": "model.safetensors",
|
| 622 |
+
"language_model.model.layers.29.self_attn.o_proj.scales": "model.safetensors",
|
| 623 |
+
"language_model.model.layers.29.self_attn.o_proj.weight": "model.safetensors",
|
| 624 |
+
"language_model.model.layers.29.self_attn.q_norm.weight": "model.safetensors",
|
| 625 |
+
"language_model.model.layers.29.self_attn.q_proj.biases": "model.safetensors",
|
| 626 |
+
"language_model.model.layers.29.self_attn.q_proj.scales": "model.safetensors",
|
| 627 |
+
"language_model.model.layers.29.self_attn.q_proj.weight": "model.safetensors",
|
| 628 |
+
"language_model.model.layers.29.self_attn.v_proj.biases": "model.safetensors",
|
| 629 |
+
"language_model.model.layers.29.self_attn.v_proj.scales": "model.safetensors",
|
| 630 |
+
"language_model.model.layers.29.self_attn.v_proj.weight": "model.safetensors",
|
| 631 |
+
"language_model.model.layers.3.input_layernorm.weight": "model.safetensors",
|
| 632 |
+
"language_model.model.layers.3.mlp.down_proj.biases": "model.safetensors",
|
| 633 |
+
"language_model.model.layers.3.mlp.down_proj.scales": "model.safetensors",
|
| 634 |
+
"language_model.model.layers.3.mlp.down_proj.weight": "model.safetensors",
|
| 635 |
+
"language_model.model.layers.3.mlp.gate_proj.biases": "model.safetensors",
|
| 636 |
+
"language_model.model.layers.3.mlp.gate_proj.scales": "model.safetensors",
|
| 637 |
+
"language_model.model.layers.3.mlp.gate_proj.weight": "model.safetensors",
|
| 638 |
+
"language_model.model.layers.3.mlp.up_proj.biases": "model.safetensors",
|
| 639 |
+
"language_model.model.layers.3.mlp.up_proj.scales": "model.safetensors",
|
| 640 |
+
"language_model.model.layers.3.mlp.up_proj.weight": "model.safetensors",
|
| 641 |
+
"language_model.model.layers.3.post_attention_layernorm.weight": "model.safetensors",
|
| 642 |
+
"language_model.model.layers.3.post_feedforward_layernorm.weight": "model.safetensors",
|
| 643 |
+
"language_model.model.layers.3.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 644 |
+
"language_model.model.layers.3.self_attn.k_norm.weight": "model.safetensors",
|
| 645 |
+
"language_model.model.layers.3.self_attn.k_proj.biases": "model.safetensors",
|
| 646 |
+
"language_model.model.layers.3.self_attn.k_proj.scales": "model.safetensors",
|
| 647 |
+
"language_model.model.layers.3.self_attn.k_proj.weight": "model.safetensors",
|
| 648 |
+
"language_model.model.layers.3.self_attn.o_proj.biases": "model.safetensors",
|
| 649 |
+
"language_model.model.layers.3.self_attn.o_proj.scales": "model.safetensors",
|
| 650 |
+
"language_model.model.layers.3.self_attn.o_proj.weight": "model.safetensors",
|
| 651 |
+
"language_model.model.layers.3.self_attn.q_norm.weight": "model.safetensors",
|
| 652 |
+
"language_model.model.layers.3.self_attn.q_proj.biases": "model.safetensors",
|
| 653 |
+
"language_model.model.layers.3.self_attn.q_proj.scales": "model.safetensors",
|
| 654 |
+
"language_model.model.layers.3.self_attn.q_proj.weight": "model.safetensors",
|
| 655 |
+
"language_model.model.layers.3.self_attn.v_proj.biases": "model.safetensors",
|
| 656 |
+
"language_model.model.layers.3.self_attn.v_proj.scales": "model.safetensors",
|
| 657 |
+
"language_model.model.layers.3.self_attn.v_proj.weight": "model.safetensors",
|
| 658 |
+
"language_model.model.layers.30.input_layernorm.weight": "model.safetensors",
|
| 659 |
+
"language_model.model.layers.30.mlp.down_proj.biases": "model.safetensors",
|
| 660 |
+
"language_model.model.layers.30.mlp.down_proj.scales": "model.safetensors",
|
| 661 |
+
"language_model.model.layers.30.mlp.down_proj.weight": "model.safetensors",
|
| 662 |
+
"language_model.model.layers.30.mlp.gate_proj.biases": "model.safetensors",
|
| 663 |
+
"language_model.model.layers.30.mlp.gate_proj.scales": "model.safetensors",
|
| 664 |
+
"language_model.model.layers.30.mlp.gate_proj.weight": "model.safetensors",
|
| 665 |
+
"language_model.model.layers.30.mlp.up_proj.biases": "model.safetensors",
|
| 666 |
+
"language_model.model.layers.30.mlp.up_proj.scales": "model.safetensors",
|
| 667 |
+
"language_model.model.layers.30.mlp.up_proj.weight": "model.safetensors",
|
| 668 |
+
"language_model.model.layers.30.post_attention_layernorm.weight": "model.safetensors",
|
| 669 |
+
"language_model.model.layers.30.post_feedforward_layernorm.weight": "model.safetensors",
|
| 670 |
+
"language_model.model.layers.30.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 671 |
+
"language_model.model.layers.30.self_attn.k_norm.weight": "model.safetensors",
|
| 672 |
+
"language_model.model.layers.30.self_attn.k_proj.biases": "model.safetensors",
|
| 673 |
+
"language_model.model.layers.30.self_attn.k_proj.scales": "model.safetensors",
|
| 674 |
+
"language_model.model.layers.30.self_attn.k_proj.weight": "model.safetensors",
|
| 675 |
+
"language_model.model.layers.30.self_attn.o_proj.biases": "model.safetensors",
|
| 676 |
+
"language_model.model.layers.30.self_attn.o_proj.scales": "model.safetensors",
|
| 677 |
+
"language_model.model.layers.30.self_attn.o_proj.weight": "model.safetensors",
|
| 678 |
+
"language_model.model.layers.30.self_attn.q_norm.weight": "model.safetensors",
|
| 679 |
+
"language_model.model.layers.30.self_attn.q_proj.biases": "model.safetensors",
|
| 680 |
+
"language_model.model.layers.30.self_attn.q_proj.scales": "model.safetensors",
|
| 681 |
+
"language_model.model.layers.30.self_attn.q_proj.weight": "model.safetensors",
|
| 682 |
+
"language_model.model.layers.30.self_attn.v_proj.biases": "model.safetensors",
|
| 683 |
+
"language_model.model.layers.30.self_attn.v_proj.scales": "model.safetensors",
|
| 684 |
+
"language_model.model.layers.30.self_attn.v_proj.weight": "model.safetensors",
|
| 685 |
+
"language_model.model.layers.31.input_layernorm.weight": "model.safetensors",
|
| 686 |
+
"language_model.model.layers.31.mlp.down_proj.biases": "model.safetensors",
|
| 687 |
+
"language_model.model.layers.31.mlp.down_proj.scales": "model.safetensors",
|
| 688 |
+
"language_model.model.layers.31.mlp.down_proj.weight": "model.safetensors",
|
| 689 |
+
"language_model.model.layers.31.mlp.gate_proj.biases": "model.safetensors",
|
| 690 |
+
"language_model.model.layers.31.mlp.gate_proj.scales": "model.safetensors",
|
| 691 |
+
"language_model.model.layers.31.mlp.gate_proj.weight": "model.safetensors",
|
| 692 |
+
"language_model.model.layers.31.mlp.up_proj.biases": "model.safetensors",
|
| 693 |
+
"language_model.model.layers.31.mlp.up_proj.scales": "model.safetensors",
|
| 694 |
+
"language_model.model.layers.31.mlp.up_proj.weight": "model.safetensors",
|
| 695 |
+
"language_model.model.layers.31.post_attention_layernorm.weight": "model.safetensors",
|
| 696 |
+
"language_model.model.layers.31.post_feedforward_layernorm.weight": "model.safetensors",
|
| 697 |
+
"language_model.model.layers.31.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 698 |
+
"language_model.model.layers.31.self_attn.k_norm.weight": "model.safetensors",
|
| 699 |
+
"language_model.model.layers.31.self_attn.k_proj.biases": "model.safetensors",
|
| 700 |
+
"language_model.model.layers.31.self_attn.k_proj.scales": "model.safetensors",
|
| 701 |
+
"language_model.model.layers.31.self_attn.k_proj.weight": "model.safetensors",
|
| 702 |
+
"language_model.model.layers.31.self_attn.o_proj.biases": "model.safetensors",
|
| 703 |
+
"language_model.model.layers.31.self_attn.o_proj.scales": "model.safetensors",
|
| 704 |
+
"language_model.model.layers.31.self_attn.o_proj.weight": "model.safetensors",
|
| 705 |
+
"language_model.model.layers.31.self_attn.q_norm.weight": "model.safetensors",
|
| 706 |
+
"language_model.model.layers.31.self_attn.q_proj.biases": "model.safetensors",
|
| 707 |
+
"language_model.model.layers.31.self_attn.q_proj.scales": "model.safetensors",
|
| 708 |
+
"language_model.model.layers.31.self_attn.q_proj.weight": "model.safetensors",
|
| 709 |
+
"language_model.model.layers.31.self_attn.v_proj.biases": "model.safetensors",
|
| 710 |
+
"language_model.model.layers.31.self_attn.v_proj.scales": "model.safetensors",
|
| 711 |
+
"language_model.model.layers.31.self_attn.v_proj.weight": "model.safetensors",
|
| 712 |
+
"language_model.model.layers.32.input_layernorm.weight": "model.safetensors",
|
| 713 |
+
"language_model.model.layers.32.mlp.down_proj.biases": "model.safetensors",
|
| 714 |
+
"language_model.model.layers.32.mlp.down_proj.scales": "model.safetensors",
|
| 715 |
+
"language_model.model.layers.32.mlp.down_proj.weight": "model.safetensors",
|
| 716 |
+
"language_model.model.layers.32.mlp.gate_proj.biases": "model.safetensors",
|
| 717 |
+
"language_model.model.layers.32.mlp.gate_proj.scales": "model.safetensors",
|
| 718 |
+
"language_model.model.layers.32.mlp.gate_proj.weight": "model.safetensors",
|
| 719 |
+
"language_model.model.layers.32.mlp.up_proj.biases": "model.safetensors",
|
| 720 |
+
"language_model.model.layers.32.mlp.up_proj.scales": "model.safetensors",
|
| 721 |
+
"language_model.model.layers.32.mlp.up_proj.weight": "model.safetensors",
|
| 722 |
+
"language_model.model.layers.32.post_attention_layernorm.weight": "model.safetensors",
|
| 723 |
+
"language_model.model.layers.32.post_feedforward_layernorm.weight": "model.safetensors",
|
| 724 |
+
"language_model.model.layers.32.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 725 |
+
"language_model.model.layers.32.self_attn.k_norm.weight": "model.safetensors",
|
| 726 |
+
"language_model.model.layers.32.self_attn.k_proj.biases": "model.safetensors",
|
| 727 |
+
"language_model.model.layers.32.self_attn.k_proj.scales": "model.safetensors",
|
| 728 |
+
"language_model.model.layers.32.self_attn.k_proj.weight": "model.safetensors",
|
| 729 |
+
"language_model.model.layers.32.self_attn.o_proj.biases": "model.safetensors",
|
| 730 |
+
"language_model.model.layers.32.self_attn.o_proj.scales": "model.safetensors",
|
| 731 |
+
"language_model.model.layers.32.self_attn.o_proj.weight": "model.safetensors",
|
| 732 |
+
"language_model.model.layers.32.self_attn.q_norm.weight": "model.safetensors",
|
| 733 |
+
"language_model.model.layers.32.self_attn.q_proj.biases": "model.safetensors",
|
| 734 |
+
"language_model.model.layers.32.self_attn.q_proj.scales": "model.safetensors",
|
| 735 |
+
"language_model.model.layers.32.self_attn.q_proj.weight": "model.safetensors",
|
| 736 |
+
"language_model.model.layers.32.self_attn.v_proj.biases": "model.safetensors",
|
| 737 |
+
"language_model.model.layers.32.self_attn.v_proj.scales": "model.safetensors",
|
| 738 |
+
"language_model.model.layers.32.self_attn.v_proj.weight": "model.safetensors",
|
| 739 |
+
"language_model.model.layers.33.input_layernorm.weight": "model.safetensors",
|
| 740 |
+
"language_model.model.layers.33.mlp.down_proj.biases": "model.safetensors",
|
| 741 |
+
"language_model.model.layers.33.mlp.down_proj.scales": "model.safetensors",
|
| 742 |
+
"language_model.model.layers.33.mlp.down_proj.weight": "model.safetensors",
|
| 743 |
+
"language_model.model.layers.33.mlp.gate_proj.biases": "model.safetensors",
|
| 744 |
+
"language_model.model.layers.33.mlp.gate_proj.scales": "model.safetensors",
|
| 745 |
+
"language_model.model.layers.33.mlp.gate_proj.weight": "model.safetensors",
|
| 746 |
+
"language_model.model.layers.33.mlp.up_proj.biases": "model.safetensors",
|
| 747 |
+
"language_model.model.layers.33.mlp.up_proj.scales": "model.safetensors",
|
| 748 |
+
"language_model.model.layers.33.mlp.up_proj.weight": "model.safetensors",
|
| 749 |
+
"language_model.model.layers.33.post_attention_layernorm.weight": "model.safetensors",
|
| 750 |
+
"language_model.model.layers.33.post_feedforward_layernorm.weight": "model.safetensors",
|
| 751 |
+
"language_model.model.layers.33.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 752 |
+
"language_model.model.layers.33.self_attn.k_norm.weight": "model.safetensors",
|
| 753 |
+
"language_model.model.layers.33.self_attn.k_proj.biases": "model.safetensors",
|
| 754 |
+
"language_model.model.layers.33.self_attn.k_proj.scales": "model.safetensors",
|
| 755 |
+
"language_model.model.layers.33.self_attn.k_proj.weight": "model.safetensors",
|
| 756 |
+
"language_model.model.layers.33.self_attn.o_proj.biases": "model.safetensors",
|
| 757 |
+
"language_model.model.layers.33.self_attn.o_proj.scales": "model.safetensors",
|
| 758 |
+
"language_model.model.layers.33.self_attn.o_proj.weight": "model.safetensors",
|
| 759 |
+
"language_model.model.layers.33.self_attn.q_norm.weight": "model.safetensors",
|
| 760 |
+
"language_model.model.layers.33.self_attn.q_proj.biases": "model.safetensors",
|
| 761 |
+
"language_model.model.layers.33.self_attn.q_proj.scales": "model.safetensors",
|
| 762 |
+
"language_model.model.layers.33.self_attn.q_proj.weight": "model.safetensors",
|
| 763 |
+
"language_model.model.layers.33.self_attn.v_proj.biases": "model.safetensors",
|
| 764 |
+
"language_model.model.layers.33.self_attn.v_proj.scales": "model.safetensors",
|
| 765 |
+
"language_model.model.layers.33.self_attn.v_proj.weight": "model.safetensors",
|
| 766 |
+
"language_model.model.layers.4.input_layernorm.weight": "model.safetensors",
|
| 767 |
+
"language_model.model.layers.4.mlp.down_proj.biases": "model.safetensors",
|
| 768 |
+
"language_model.model.layers.4.mlp.down_proj.scales": "model.safetensors",
|
| 769 |
+
"language_model.model.layers.4.mlp.down_proj.weight": "model.safetensors",
|
| 770 |
+
"language_model.model.layers.4.mlp.gate_proj.biases": "model.safetensors",
|
| 771 |
+
"language_model.model.layers.4.mlp.gate_proj.scales": "model.safetensors",
|
| 772 |
+
"language_model.model.layers.4.mlp.gate_proj.weight": "model.safetensors",
|
| 773 |
+
"language_model.model.layers.4.mlp.up_proj.biases": "model.safetensors",
|
| 774 |
+
"language_model.model.layers.4.mlp.up_proj.scales": "model.safetensors",
|
| 775 |
+
"language_model.model.layers.4.mlp.up_proj.weight": "model.safetensors",
|
| 776 |
+
"language_model.model.layers.4.post_attention_layernorm.weight": "model.safetensors",
|
| 777 |
+
"language_model.model.layers.4.post_feedforward_layernorm.weight": "model.safetensors",
|
| 778 |
+
"language_model.model.layers.4.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 779 |
+
"language_model.model.layers.4.self_attn.k_norm.weight": "model.safetensors",
|
| 780 |
+
"language_model.model.layers.4.self_attn.k_proj.biases": "model.safetensors",
|
| 781 |
+
"language_model.model.layers.4.self_attn.k_proj.scales": "model.safetensors",
|
| 782 |
+
"language_model.model.layers.4.self_attn.k_proj.weight": "model.safetensors",
|
| 783 |
+
"language_model.model.layers.4.self_attn.o_proj.biases": "model.safetensors",
|
| 784 |
+
"language_model.model.layers.4.self_attn.o_proj.scales": "model.safetensors",
|
| 785 |
+
"language_model.model.layers.4.self_attn.o_proj.weight": "model.safetensors",
|
| 786 |
+
"language_model.model.layers.4.self_attn.q_norm.weight": "model.safetensors",
|
| 787 |
+
"language_model.model.layers.4.self_attn.q_proj.biases": "model.safetensors",
|
| 788 |
+
"language_model.model.layers.4.self_attn.q_proj.scales": "model.safetensors",
|
| 789 |
+
"language_model.model.layers.4.self_attn.q_proj.weight": "model.safetensors",
|
| 790 |
+
"language_model.model.layers.4.self_attn.v_proj.biases": "model.safetensors",
|
| 791 |
+
"language_model.model.layers.4.self_attn.v_proj.scales": "model.safetensors",
|
| 792 |
+
"language_model.model.layers.4.self_attn.v_proj.weight": "model.safetensors",
|
| 793 |
+
"language_model.model.layers.5.input_layernorm.weight": "model.safetensors",
|
| 794 |
+
"language_model.model.layers.5.mlp.down_proj.biases": "model.safetensors",
|
| 795 |
+
"language_model.model.layers.5.mlp.down_proj.scales": "model.safetensors",
|
| 796 |
+
"language_model.model.layers.5.mlp.down_proj.weight": "model.safetensors",
|
| 797 |
+
"language_model.model.layers.5.mlp.gate_proj.biases": "model.safetensors",
|
| 798 |
+
"language_model.model.layers.5.mlp.gate_proj.scales": "model.safetensors",
|
| 799 |
+
"language_model.model.layers.5.mlp.gate_proj.weight": "model.safetensors",
|
| 800 |
+
"language_model.model.layers.5.mlp.up_proj.biases": "model.safetensors",
|
| 801 |
+
"language_model.model.layers.5.mlp.up_proj.scales": "model.safetensors",
|
| 802 |
+
"language_model.model.layers.5.mlp.up_proj.weight": "model.safetensors",
|
| 803 |
+
"language_model.model.layers.5.post_attention_layernorm.weight": "model.safetensors",
|
| 804 |
+
"language_model.model.layers.5.post_feedforward_layernorm.weight": "model.safetensors",
|
| 805 |
+
"language_model.model.layers.5.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 806 |
+
"language_model.model.layers.5.self_attn.k_norm.weight": "model.safetensors",
|
| 807 |
+
"language_model.model.layers.5.self_attn.k_proj.biases": "model.safetensors",
|
| 808 |
+
"language_model.model.layers.5.self_attn.k_proj.scales": "model.safetensors",
|
| 809 |
+
"language_model.model.layers.5.self_attn.k_proj.weight": "model.safetensors",
|
| 810 |
+
"language_model.model.layers.5.self_attn.o_proj.biases": "model.safetensors",
|
| 811 |
+
"language_model.model.layers.5.self_attn.o_proj.scales": "model.safetensors",
|
| 812 |
+
"language_model.model.layers.5.self_attn.o_proj.weight": "model.safetensors",
|
| 813 |
+
"language_model.model.layers.5.self_attn.q_norm.weight": "model.safetensors",
|
| 814 |
+
"language_model.model.layers.5.self_attn.q_proj.biases": "model.safetensors",
|
| 815 |
+
"language_model.model.layers.5.self_attn.q_proj.scales": "model.safetensors",
|
| 816 |
+
"language_model.model.layers.5.self_attn.q_proj.weight": "model.safetensors",
|
| 817 |
+
"language_model.model.layers.5.self_attn.v_proj.biases": "model.safetensors",
|
| 818 |
+
"language_model.model.layers.5.self_attn.v_proj.scales": "model.safetensors",
|
| 819 |
+
"language_model.model.layers.5.self_attn.v_proj.weight": "model.safetensors",
|
| 820 |
+
"language_model.model.layers.6.input_layernorm.weight": "model.safetensors",
|
| 821 |
+
"language_model.model.layers.6.mlp.down_proj.biases": "model.safetensors",
|
| 822 |
+
"language_model.model.layers.6.mlp.down_proj.scales": "model.safetensors",
|
| 823 |
+
"language_model.model.layers.6.mlp.down_proj.weight": "model.safetensors",
|
| 824 |
+
"language_model.model.layers.6.mlp.gate_proj.biases": "model.safetensors",
|
| 825 |
+
"language_model.model.layers.6.mlp.gate_proj.scales": "model.safetensors",
|
| 826 |
+
"language_model.model.layers.6.mlp.gate_proj.weight": "model.safetensors",
|
| 827 |
+
"language_model.model.layers.6.mlp.up_proj.biases": "model.safetensors",
|
| 828 |
+
"language_model.model.layers.6.mlp.up_proj.scales": "model.safetensors",
|
| 829 |
+
"language_model.model.layers.6.mlp.up_proj.weight": "model.safetensors",
|
| 830 |
+
"language_model.model.layers.6.post_attention_layernorm.weight": "model.safetensors",
|
| 831 |
+
"language_model.model.layers.6.post_feedforward_layernorm.weight": "model.safetensors",
|
| 832 |
+
"language_model.model.layers.6.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 833 |
+
"language_model.model.layers.6.self_attn.k_norm.weight": "model.safetensors",
|
| 834 |
+
"language_model.model.layers.6.self_attn.k_proj.biases": "model.safetensors",
|
| 835 |
+
"language_model.model.layers.6.self_attn.k_proj.scales": "model.safetensors",
|
| 836 |
+
"language_model.model.layers.6.self_attn.k_proj.weight": "model.safetensors",
|
| 837 |
+
"language_model.model.layers.6.self_attn.o_proj.biases": "model.safetensors",
|
| 838 |
+
"language_model.model.layers.6.self_attn.o_proj.scales": "model.safetensors",
|
| 839 |
+
"language_model.model.layers.6.self_attn.o_proj.weight": "model.safetensors",
|
| 840 |
+
"language_model.model.layers.6.self_attn.q_norm.weight": "model.safetensors",
|
| 841 |
+
"language_model.model.layers.6.self_attn.q_proj.biases": "model.safetensors",
|
| 842 |
+
"language_model.model.layers.6.self_attn.q_proj.scales": "model.safetensors",
|
| 843 |
+
"language_model.model.layers.6.self_attn.q_proj.weight": "model.safetensors",
|
| 844 |
+
"language_model.model.layers.6.self_attn.v_proj.biases": "model.safetensors",
|
| 845 |
+
"language_model.model.layers.6.self_attn.v_proj.scales": "model.safetensors",
|
| 846 |
+
"language_model.model.layers.6.self_attn.v_proj.weight": "model.safetensors",
|
| 847 |
+
"language_model.model.layers.7.input_layernorm.weight": "model.safetensors",
|
| 848 |
+
"language_model.model.layers.7.mlp.down_proj.biases": "model.safetensors",
|
| 849 |
+
"language_model.model.layers.7.mlp.down_proj.scales": "model.safetensors",
|
| 850 |
+
"language_model.model.layers.7.mlp.down_proj.weight": "model.safetensors",
|
| 851 |
+
"language_model.model.layers.7.mlp.gate_proj.biases": "model.safetensors",
|
| 852 |
+
"language_model.model.layers.7.mlp.gate_proj.scales": "model.safetensors",
|
| 853 |
+
"language_model.model.layers.7.mlp.gate_proj.weight": "model.safetensors",
|
| 854 |
+
"language_model.model.layers.7.mlp.up_proj.biases": "model.safetensors",
|
| 855 |
+
"language_model.model.layers.7.mlp.up_proj.scales": "model.safetensors",
|
| 856 |
+
"language_model.model.layers.7.mlp.up_proj.weight": "model.safetensors",
|
| 857 |
+
"language_model.model.layers.7.post_attention_layernorm.weight": "model.safetensors",
|
| 858 |
+
"language_model.model.layers.7.post_feedforward_layernorm.weight": "model.safetensors",
|
| 859 |
+
"language_model.model.layers.7.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 860 |
+
"language_model.model.layers.7.self_attn.k_norm.weight": "model.safetensors",
|
| 861 |
+
"language_model.model.layers.7.self_attn.k_proj.biases": "model.safetensors",
|
| 862 |
+
"language_model.model.layers.7.self_attn.k_proj.scales": "model.safetensors",
|
| 863 |
+
"language_model.model.layers.7.self_attn.k_proj.weight": "model.safetensors",
|
| 864 |
+
"language_model.model.layers.7.self_attn.o_proj.biases": "model.safetensors",
|
| 865 |
+
"language_model.model.layers.7.self_attn.o_proj.scales": "model.safetensors",
|
| 866 |
+
"language_model.model.layers.7.self_attn.o_proj.weight": "model.safetensors",
|
| 867 |
+
"language_model.model.layers.7.self_attn.q_norm.weight": "model.safetensors",
|
| 868 |
+
"language_model.model.layers.7.self_attn.q_proj.biases": "model.safetensors",
|
| 869 |
+
"language_model.model.layers.7.self_attn.q_proj.scales": "model.safetensors",
|
| 870 |
+
"language_model.model.layers.7.self_attn.q_proj.weight": "model.safetensors",
|
| 871 |
+
"language_model.model.layers.7.self_attn.v_proj.biases": "model.safetensors",
|
| 872 |
+
"language_model.model.layers.7.self_attn.v_proj.scales": "model.safetensors",
|
| 873 |
+
"language_model.model.layers.7.self_attn.v_proj.weight": "model.safetensors",
|
| 874 |
+
"language_model.model.layers.8.input_layernorm.weight": "model.safetensors",
|
| 875 |
+
"language_model.model.layers.8.mlp.down_proj.biases": "model.safetensors",
|
| 876 |
+
"language_model.model.layers.8.mlp.down_proj.scales": "model.safetensors",
|
| 877 |
+
"language_model.model.layers.8.mlp.down_proj.weight": "model.safetensors",
|
| 878 |
+
"language_model.model.layers.8.mlp.gate_proj.biases": "model.safetensors",
|
| 879 |
+
"language_model.model.layers.8.mlp.gate_proj.scales": "model.safetensors",
|
| 880 |
+
"language_model.model.layers.8.mlp.gate_proj.weight": "model.safetensors",
|
| 881 |
+
"language_model.model.layers.8.mlp.up_proj.biases": "model.safetensors",
|
| 882 |
+
"language_model.model.layers.8.mlp.up_proj.scales": "model.safetensors",
|
| 883 |
+
"language_model.model.layers.8.mlp.up_proj.weight": "model.safetensors",
|
| 884 |
+
"language_model.model.layers.8.post_attention_layernorm.weight": "model.safetensors",
|
| 885 |
+
"language_model.model.layers.8.post_feedforward_layernorm.weight": "model.safetensors",
|
| 886 |
+
"language_model.model.layers.8.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 887 |
+
"language_model.model.layers.8.self_attn.k_norm.weight": "model.safetensors",
|
| 888 |
+
"language_model.model.layers.8.self_attn.k_proj.biases": "model.safetensors",
|
| 889 |
+
"language_model.model.layers.8.self_attn.k_proj.scales": "model.safetensors",
|
| 890 |
+
"language_model.model.layers.8.self_attn.k_proj.weight": "model.safetensors",
|
| 891 |
+
"language_model.model.layers.8.self_attn.o_proj.biases": "model.safetensors",
|
| 892 |
+
"language_model.model.layers.8.self_attn.o_proj.scales": "model.safetensors",
|
| 893 |
+
"language_model.model.layers.8.self_attn.o_proj.weight": "model.safetensors",
|
| 894 |
+
"language_model.model.layers.8.self_attn.q_norm.weight": "model.safetensors",
|
| 895 |
+
"language_model.model.layers.8.self_attn.q_proj.biases": "model.safetensors",
|
| 896 |
+
"language_model.model.layers.8.self_attn.q_proj.scales": "model.safetensors",
|
| 897 |
+
"language_model.model.layers.8.self_attn.q_proj.weight": "model.safetensors",
|
| 898 |
+
"language_model.model.layers.8.self_attn.v_proj.biases": "model.safetensors",
|
| 899 |
+
"language_model.model.layers.8.self_attn.v_proj.scales": "model.safetensors",
|
| 900 |
+
"language_model.model.layers.8.self_attn.v_proj.weight": "model.safetensors",
|
| 901 |
+
"language_model.model.layers.9.input_layernorm.weight": "model.safetensors",
|
| 902 |
+
"language_model.model.layers.9.mlp.down_proj.biases": "model.safetensors",
|
| 903 |
+
"language_model.model.layers.9.mlp.down_proj.scales": "model.safetensors",
|
| 904 |
+
"language_model.model.layers.9.mlp.down_proj.weight": "model.safetensors",
|
| 905 |
+
"language_model.model.layers.9.mlp.gate_proj.biases": "model.safetensors",
|
| 906 |
+
"language_model.model.layers.9.mlp.gate_proj.scales": "model.safetensors",
|
| 907 |
+
"language_model.model.layers.9.mlp.gate_proj.weight": "model.safetensors",
|
| 908 |
+
"language_model.model.layers.9.mlp.up_proj.biases": "model.safetensors",
|
| 909 |
+
"language_model.model.layers.9.mlp.up_proj.scales": "model.safetensors",
|
| 910 |
+
"language_model.model.layers.9.mlp.up_proj.weight": "model.safetensors",
|
| 911 |
+
"language_model.model.layers.9.post_attention_layernorm.weight": "model.safetensors",
|
| 912 |
+
"language_model.model.layers.9.post_feedforward_layernorm.weight": "model.safetensors",
|
| 913 |
+
"language_model.model.layers.9.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 914 |
+
"language_model.model.layers.9.self_attn.k_norm.weight": "model.safetensors",
|
| 915 |
+
"language_model.model.layers.9.self_attn.k_proj.biases": "model.safetensors",
|
| 916 |
+
"language_model.model.layers.9.self_attn.k_proj.scales": "model.safetensors",
|
| 917 |
+
"language_model.model.layers.9.self_attn.k_proj.weight": "model.safetensors",
|
| 918 |
+
"language_model.model.layers.9.self_attn.o_proj.biases": "model.safetensors",
|
| 919 |
+
"language_model.model.layers.9.self_attn.o_proj.scales": "model.safetensors",
|
| 920 |
+
"language_model.model.layers.9.self_attn.o_proj.weight": "model.safetensors",
|
| 921 |
+
"language_model.model.layers.9.self_attn.q_norm.weight": "model.safetensors",
|
| 922 |
+
"language_model.model.layers.9.self_attn.q_proj.biases": "model.safetensors",
|
| 923 |
+
"language_model.model.layers.9.self_attn.q_proj.scales": "model.safetensors",
|
| 924 |
+
"language_model.model.layers.9.self_attn.q_proj.weight": "model.safetensors",
|
| 925 |
+
"language_model.model.layers.9.self_attn.v_proj.biases": "model.safetensors",
|
| 926 |
+
"language_model.model.layers.9.self_attn.v_proj.scales": "model.safetensors",
|
| 927 |
+
"language_model.model.layers.9.self_attn.v_proj.weight": "model.safetensors",
|
| 928 |
+
"language_model.model.norm.weight": "model.safetensors"
|
| 929 |
+
}
|
| 930 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a74aefb1dc1340a25f29ab8370384b9ed24b2d921d7749ece7bbcfcfdf00d497
|
| 3 |
+
size 33384443
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"boi_token": "<start_of_image>",
|
| 4 |
+
"bos_token": "<bos>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eoi_token": "<end_of_image>",
|
| 7 |
+
"eos_token": "<eos>",
|
| 8 |
+
"image_token": "<image_soft_token>",
|
| 9 |
+
"is_local": true,
|
| 10 |
+
"mask_token": "<mask>",
|
| 11 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 12 |
+
"model_specific_special_tokens": {
|
| 13 |
+
"boi_token": "<start_of_image>",
|
| 14 |
+
"eoi_token": "<end_of_image>",
|
| 15 |
+
"image_token": "<image_soft_token>"
|
| 16 |
+
},
|
| 17 |
+
"pad_token": "<pad>",
|
| 18 |
+
"padding_side": "left",
|
| 19 |
+
"processor_class": "Gemma3Processor",
|
| 20 |
+
"sp_model_kwargs": null,
|
| 21 |
+
"spaces_between_special_tokens": false,
|
| 22 |
+
"tokenizer_class": "GemmaTokenizer",
|
| 23 |
+
"unk_token": "<unk>",
|
| 24 |
+
"use_default_system_prompt": false
|
| 25 |
+
}
|