Commit
•
d1c7f63
1
Parent(s):
2f32505
79aeca2c297a66d5fe4a620f3f51155579cd84352e14aa96d80adb8a776d652c
Browse files- README.md +271 -0
- added_tokens.json +5 -0
- config.json +39 -0
- generation_config.json +11 -0
- huggingface-metadata.txt +22 -0
- merges.txt +0 -0
- model.safetensors.index.json +1042 -0
- output-00008-of-00008.safetensors +3 -0
- special_tokens_map.json +20 -0
- tokenizer.json +0 -0
- tokenizer_config.json +43 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,271 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
model-index:
|
| 4 |
+
- name: RYS-XLarge
|
| 5 |
+
results:
|
| 6 |
+
- task:
|
| 7 |
+
type: text-generation
|
| 8 |
+
name: Text Generation
|
| 9 |
+
dataset:
|
| 10 |
+
name: IFEval (0-Shot)
|
| 11 |
+
type: HuggingFaceH4/ifeval
|
| 12 |
+
args:
|
| 13 |
+
num_few_shot: 0
|
| 14 |
+
metrics:
|
| 15 |
+
- type: inst_level_strict_acc and prompt_level_strict_acc
|
| 16 |
+
value: 79.96
|
| 17 |
+
name: strict accuracy
|
| 18 |
+
source:
|
| 19 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dnhkng/RYS-XLarge
|
| 20 |
+
name: Open LLM Leaderboard
|
| 21 |
+
- task:
|
| 22 |
+
type: text-generation
|
| 23 |
+
name: Text Generation
|
| 24 |
+
dataset:
|
| 25 |
+
name: BBH (3-Shot)
|
| 26 |
+
type: BBH
|
| 27 |
+
args:
|
| 28 |
+
num_few_shot: 3
|
| 29 |
+
metrics:
|
| 30 |
+
- type: acc_norm
|
| 31 |
+
value: 58.77
|
| 32 |
+
name: normalized accuracy
|
| 33 |
+
source:
|
| 34 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dnhkng/RYS-XLarge
|
| 35 |
+
name: Open LLM Leaderboard
|
| 36 |
+
- task:
|
| 37 |
+
type: text-generation
|
| 38 |
+
name: Text Generation
|
| 39 |
+
dataset:
|
| 40 |
+
name: MATH Lvl 5 (4-Shot)
|
| 41 |
+
type: hendrycks/competition_math
|
| 42 |
+
args:
|
| 43 |
+
num_few_shot: 4
|
| 44 |
+
metrics:
|
| 45 |
+
- type: exact_match
|
| 46 |
+
value: 38.97
|
| 47 |
+
name: exact match
|
| 48 |
+
source:
|
| 49 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dnhkng/RYS-XLarge
|
| 50 |
+
name: Open LLM Leaderboard
|
| 51 |
+
- task:
|
| 52 |
+
type: text-generation
|
| 53 |
+
name: Text Generation
|
| 54 |
+
dataset:
|
| 55 |
+
name: GPQA (0-shot)
|
| 56 |
+
type: Idavidrein/gpqa
|
| 57 |
+
args:
|
| 58 |
+
num_few_shot: 0
|
| 59 |
+
metrics:
|
| 60 |
+
- type: acc_norm
|
| 61 |
+
value: 17.9
|
| 62 |
+
name: acc_norm
|
| 63 |
+
source:
|
| 64 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dnhkng/RYS-XLarge
|
| 65 |
+
name: Open LLM Leaderboard
|
| 66 |
+
- task:
|
| 67 |
+
type: text-generation
|
| 68 |
+
name: Text Generation
|
| 69 |
+
dataset:
|
| 70 |
+
name: MuSR (0-shot)
|
| 71 |
+
type: TAUR-Lab/MuSR
|
| 72 |
+
args:
|
| 73 |
+
num_few_shot: 0
|
| 74 |
+
metrics:
|
| 75 |
+
- type: acc_norm
|
| 76 |
+
value: 23.72
|
| 77 |
+
name: acc_norm
|
| 78 |
+
source:
|
| 79 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dnhkng/RYS-XLarge
|
| 80 |
+
name: Open LLM Leaderboard
|
| 81 |
+
- task:
|
| 82 |
+
type: text-generation
|
| 83 |
+
name: Text Generation
|
| 84 |
+
dataset:
|
| 85 |
+
name: MMLU-PRO (5-shot)
|
| 86 |
+
type: TIGER-Lab/MMLU-Pro
|
| 87 |
+
config: main
|
| 88 |
+
split: test
|
| 89 |
+
args:
|
| 90 |
+
num_few_shot: 5
|
| 91 |
+
metrics:
|
| 92 |
+
- type: acc
|
| 93 |
+
value: 49.2
|
| 94 |
+
name: accuracy
|
| 95 |
+
source:
|
| 96 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dnhkng/RYS-XLarge
|
| 97 |
+
name: Open LLM Leaderboard
|
| 98 |
+
---
|
| 99 |
+
|
| 100 |
+
This is a new kind of model optimization.
|
| 101 |
+
This model is based on MaziyarPanahi/calme-2.1-qwen2-72b, which was tuned from Qwen2-72B.
|
| 102 |
+
|
| 103 |
+
A paper is currently being written on the technique. Special thanks to my wife, for putting up with me coding in the basement for too many evenings and weekends for months!
|
| 104 |
+
|
| 105 |
+
## Quickstart
|
| 106 |
+
|
| 107 |
+
Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.
|
| 108 |
+
|
| 109 |
+
```python
|
| 110 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 111 |
+
device = "cuda" # the device to load the model onto
|
| 112 |
+
|
| 113 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 114 |
+
"dnhkng/RYS-XLarge",
|
| 115 |
+
torch_dtype="auto",
|
| 116 |
+
device_map="auto"
|
| 117 |
+
)
|
| 118 |
+
tokenizer = AutoTokenizer.from_pretrained("dnhkng/RYS-XLarge")
|
| 119 |
+
|
| 120 |
+
prompt = "Give me a short introduction to large language model."
|
| 121 |
+
messages = [
|
| 122 |
+
{"role": "system", "content": "You are a helpful assistant."},
|
| 123 |
+
{"role": "user", "content": prompt}
|
| 124 |
+
]
|
| 125 |
+
text = tokenizer.apply_chat_template(
|
| 126 |
+
messages,
|
| 127 |
+
tokenize=False,
|
| 128 |
+
add_generation_prompt=True
|
| 129 |
+
)
|
| 130 |
+
model_inputs = tokenizer([text], return_tensors="pt").to(device)
|
| 131 |
+
|
| 132 |
+
generated_ids = model.generate(
|
| 133 |
+
model_inputs.input_ids,
|
| 134 |
+
max_new_tokens=512
|
| 135 |
+
)
|
| 136 |
+
generated_ids = [
|
| 137 |
+
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
| 138 |
+
]
|
| 139 |
+
|
| 140 |
+
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
| 141 |
+
```
|
| 142 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
| 143 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_dnhkng__RYS-XLarge)
|
| 144 |
+
|
| 145 |
+
| Metric |Value|
|
| 146 |
+
|-------------------|----:|
|
| 147 |
+
|Avg. |44.75|
|
| 148 |
+
|IFEval (0-Shot) |79.96|
|
| 149 |
+
|BBH (3-Shot) |58.77|
|
| 150 |
+
|MATH Lvl 5 (4-Shot)|38.97|
|
| 151 |
+
|GPQA (0-shot) |17.90|
|
| 152 |
+
|MuSR (0-shot) |23.72|
|
| 153 |
+
|MMLU-PRO (5-shot) |49.20|
|
| 154 |
+
|
| 155 |
+
___________________________________
|
| 156 |
+
# *ADVERTISING BREAK*
|
| 157 |
+
|
| 158 |
+
I’m on the hunt for new challenges and a chance to dive into some exciting research opportunities. Oh, and did I mention I just snagged a top spot on the Open LLM leaderboard? 🎉
|
| 159 |
+
|
| 160 |
+
|
| 161 |
+
|
| 162 |
+
## CV - Dr David Noel Ng
|
| 163 |
+
|
| 164 |
+
|
| 165 |
+
#### Profile
|
| 166 |
+
Innovation enthusiast, AI-strategist, and interdisciplinary-tech nerd – that's me in a nutshell. With over a decade of experience in research and project management, my professional journey has been largely shaped by my passion for artificial intelligence and its potential to transform various industries. With a solid background in artificial intelligence and machine learning, coupled with a knack for innovation and problem-solving (and a healthy dose of curiosity), I'm excited to bring my skills to a new team.
|
| 167 |
+
|
| 168 |
+
Originally from Australia, where I earned my degrees in Organic Chemistry and Biochemistry, I moved to Germany in 2004. My academic pursuit continued with a Ph.D. in Chemistry at the Max Planck Institute of Biochemistry. Today, I leverage my robust educational background and diverse industry experience to drive AI innovations in a wide range of applications. Hobbies? Lots: I've also built the world's most powerful espresso machine and am working to bring [GLaDOS to life](https://github.com/dnhkng/GlaDOS).
|
| 169 |
+
|
| 170 |
+
|
| 171 |
+
___________________________________
|
| 172 |
+
### PROFESSIONAL EXPERIENCE
|
| 173 |
+
#### SENIOR GLOBAL INNOVATION STRATEGIST - ARTIFICIAL INTELLIGENCE
|
| 174 |
+
#### Munich Re | Munich | 05/2023 - Now
|
| 175 |
+
|
| 176 |
+
As a Senior Global Innovation Strategist at Munich Re, my passion is in steering AI/ML strategies, maximizing project impact, and advancing the use of cutting-edge technology. I built the AI Accelerator, which drives the rapid and structured development of AI use-case Implementations.
|
| 177 |
+
#### AI CONSULTANT - LEAD AI ENGINEER
|
| 178 |
+
#### appliedAI UTUM | Munich | 04/2019 - 04/2023
|
| 179 |
+
|
| 180 |
+
In my tenure at appliedAI, I held a leadership role where I spearheaded the successful development and execution of various AI/ML proof-of-concept (POC) and minimum viable product (MVP) projects. I utilized a hands-on approach to drive ideation, planning, and delivery of these solutions for our clients.
|
| 181 |
+
|
| 182 |
+
- AI-Controlled Imaging: Directed a PoC of an AI-Controlled Electron Microscope using Reinforcement Learning for a premier imaging company.
|
| 183 |
+
- Anomaly Detection: Oversaw development of security systems utilizing anomaly detection, integrating diverse technologies to boost client security at the Munich Security Conference..
|
| 184 |
+
- Project Optimization: Implemented AlphaZero-based Graph Optimization for project management in the Nuclear Energy sector.
|
| 185 |
+
- Food Safety: Delivered a PoC for industrial food safety equipment, significantly improving detection sensitivity.
|
| 186 |
+
- NLP Consulting: Consulted on automated document analysis and risk assessment for the European Central Bank, leveraging NLP technologies.
|
| 187 |
+
- Aerospace Anomaly Detection: Developed a PoC for Aerospace manufacturing, using generative diffusion models to create synthetic data for training anomaly detection models.
|
| 188 |
+
- Retail Automation: Applied Vision and Skeletal Tracking for supermarket automation, modernizing retail operations.
|
| 189 |
+
- Public Speaking and Training: Regularly presented talks and training sessions on topics such as KI-Transfer Plus for the Bayerischen Staatsministeriums für Digitales, and KI in Biotech for the BioEntrepreneurship Summit, spreading AI knowledge and fostering digital transformation in the Health/Pharma sector..
|
| 190 |
+
|
| 191 |
+
|
| 192 |
+
#### PROJECT LEAD - INNOVATIVE TECHNOLOGIES
|
| 193 |
+
#### Nanotemper Technologies GmbH | Munich | 5/2016 - 3/2019
|
| 194 |
+
|
| 195 |
+
Project Lead in the Future Technologies Department, Scientist Bioanalytics and all-rounder in bioanalytics/data/optoelectronics. Contributions and successes:
|
| 196 |
+
- Created and applied Deep Learning models for interpreting biophysical data for pharmaceutical stability in antibody development
|
| 197 |
+
- Designed, built, and programmed prototype optoelectronic apparatus for the rapid analysis of biosimilar pharmaceutical molecules
|
| 198 |
+
- Introduced FPGA technology for high-speed data collection and analysis, now used in the key products at Nanotemper
|
| 199 |
+
|
| 200 |
+
#### RESEARCH SCIENTIST
|
| 201 |
+
#### Max Planck Institute Of Neurobiology | Martinsried | 02/2016 - 04/2019
|
| 202 |
+
|
| 203 |
+
Driven by an interest in Biotech, I found a role in research working on biosensors, particularly on optical probes of neural activity (Optogenetics). Contribution and success:
|
| 204 |
+
- Designed, built and utilized a robotic screening platform for the high-throughput engineering of biosensors.
|
| 205 |
+
- Utilised image-processing and machine-learning techniques to collect and analyse biosensor data.
|
| 206 |
+
- Automated the development of large molecules by FACS-based directed protein evolution.
|
| 207 |
+
- Patented new CRISPR/Cas9 technology for high-throughput protein engineering.
|
| 208 |
+
|
| 209 |
+
#### CONSULTANT FOR THE NETFLIX SERIES 'BIOHACKERS'
|
| 210 |
+
#### Netflix | Munich | 01/2019 - 12/2019
|
| 211 |
+
|
| 212 |
+
In this role, I advised on the scientific concepts, storylines and film set for this popular Netflix series. Contribution and success:
|
| 213 |
+
- Helped design and build the Laboratory and ‘Biohacking’ labs
|
| 214 |
+
- Modified the scripts to keep scientific accuracy
|
| 215 |
+
- Location scouting and liaison with the LMU to organise research labs for filming
|
| 216 |
+
|
| 217 |
+
#### Doctoral Candidate
|
| 218 |
+
#### Max Planck Institute for Biochemistry
|
| 219 |
+
|
| 220 |
+
My PhD thesis was all about Optical brain-computer interfaces, and synthesizing molecular sensors for optically imaging brain activity. I devised a new biomolecular targeting technique and developed compounds for high-speed optical analysis of neuron activity.
|
| 221 |
+
- Molecular Sensor Development: Designed, synthesized, and tested molecular sensors to optically image brain activity, advancing neuroimaging capabilities.
|
| 222 |
+
- Biomolecular Targeting Technique: Developed a novel technique for labelling live cells with organic dye, utilizing pro-drug techniques used in pharmaceutical development, enhancing the precision of cell tracking and analysis.
|
| 223 |
+
- Neuronal Activity Analysis: Designed a high-speed optical analysis setup for cultured neurons and developed specialized compounds for this purpose, improving our understanding of neuron activity.
|
| 224 |
+
|
| 225 |
+
## SKILLS
|
| 226 |
+
- Strong interest in customer experience and Machine Learning transformations (e.g. expectation management, stakeholder alignment, team reorganization etc.)
|
| 227 |
+
- Ability to work autonomously in the completion of deliverables
|
| 228 |
+
- Ability to provide technical and analytic direction, guidance and roadmaps for ML projects
|
| 229 |
+
- Excellent communication and presentation skills: able to explain Analytics in non-technical terms to business users (C-level, investors, public presentations etc.)
|
| 230 |
+
- Deep technical expertise and strong problem-solving and data-analysis skills
|
| 231 |
+
|
| 232 |
+
|
| 233 |
+
|
| 234 |
+
## AWARDS
|
| 235 |
+
|
| 236 |
+
#### The United Nations COVID-19 Detect & Protect Challenge
|
| 237 |
+
- The United Nations Development Programme Centre for Technology, Innovation and Sustainable Development · Aug 2020
|
| 238 |
+
|
| 239 |
+
#### AI at the Edge Challenge with NVIDIA - Artificial Intelligence of Things (AIoT)
|
| 240 |
+
- Issued by Nvidia · Mar 2020
|
| 241 |
+
|
| 242 |
+
#### Create Intelligence at the Edge - Artificial Intelligence on FPGA
|
| 243 |
+
- Avnet and Xilinx · Dec 2018
|
| 244 |
+
|
| 245 |
+
#### PATENTS
|
| 246 |
+
- WO2018020050A1 - Targeted in situ protein diversification by site-directed DNA cleavage and repair
|
| 247 |
+
|
| 248 |
+
|
| 249 |
+
## EDUCATION
|
| 250 |
+
|
| 251 |
+
#### PhD in Organic Chemistry
|
| 252 |
+
- Max Planck Institute of Biochemistry
|
| 253 |
+
|
| 254 |
+
#### Honours Degree - Biochemistry
|
| 255 |
+
- Monash University Melbourne
|
| 256 |
+
|
| 257 |
+
#### Bachelor of Science - Double Major -
|
| 258 |
+
- Chemistry / Molecular Biology
|
| 259 |
+
- University of Tasmania
|
| 260 |
+
|
| 261 |
+
#### Nanodegree - Deep Reinforcement Learning
|
| 262 |
+
- Udacity Online
|
| 263 |
+
|
| 264 |
+
#### Nanodegree - Deep Learning
|
| 265 |
+
- Udacity Online
|
| 266 |
+
|
| 267 |
+
|
| 268 |
+
___________________________________
|
| 269 |
+
I'm based out of Munich, Germany, but I would be interested in working remotely for a team with more compute than my 2x 4090s 🚀
|
| 270 |
+
|
| 271 |
+
#### Reach out via [LinkedIn](https://www.linkedin.com/in/dnhkng)
|
added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endoftext|>": 151643,
|
| 3 |
+
"<|im_end|>": 151645,
|
| 4 |
+
"<|im_start|>": 151644
|
| 5 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Qwen/Qwen2-72B-Instruct",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 8192,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 29568,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"max_window_layers": 80,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 64,
|
| 17 |
+
"num_hidden_layers": 86,
|
| 18 |
+
"num_key_value_heads": 8,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_theta": 1000000.0,
|
| 21 |
+
"sliding_window": 131072,
|
| 22 |
+
"tie_word_embeddings": false,
|
| 23 |
+
"torch_dtype": "bfloat16",
|
| 24 |
+
"transformers_version": "4.41.0",
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"use_sliding_window": false,
|
| 27 |
+
"vocab_size": 151646,
|
| 28 |
+
"quantization_config": {
|
| 29 |
+
"quant_method": "exl2",
|
| 30 |
+
"version": "0.1.8",
|
| 31 |
+
"bits": 6.0,
|
| 32 |
+
"head_bits": 6,
|
| 33 |
+
"calibration": {
|
| 34 |
+
"rows": 115,
|
| 35 |
+
"length": 2048,
|
| 36 |
+
"dataset": "(default)"
|
| 37 |
+
}
|
| 38 |
+
}
|
| 39 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": 151645,
|
| 5 |
+
"pad_token_id": 151643,
|
| 6 |
+
"repetition_penalty": 1.05,
|
| 7 |
+
"temperature": 0.7,
|
| 8 |
+
"top_k": 20,
|
| 9 |
+
"top_p": 0.8,
|
| 10 |
+
"transformers_version": "4.41.0"
|
| 11 |
+
}
|
huggingface-metadata.txt
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
url: https://huggingface.co/dnhkng/RYS-XLarge
|
| 2 |
+
branch: main
|
| 3 |
+
download date: 2024-08-07 03:20:52
|
| 4 |
+
sha256sum:
|
| 5 |
+
7378924216101627f0f72ef3ee0193bed21a971cf296d94b5351ba9bccc1c187 model-00001-of-00018.safetensors
|
| 6 |
+
ad41e9524962bb7714c7fd2003db946a0f589b16d131868dcea28b8caec70181 model-00002-of-00018.safetensors
|
| 7 |
+
dca052fa730fa6090a0bfa940b5bf0d0adea69ff8982d35d7f5f0b31a9713bcc model-00003-of-00018.safetensors
|
| 8 |
+
82de046be64b4eb1823db50135374f53af7d76695a3de6303251a9e1cc1994f4 model-00004-of-00018.safetensors
|
| 9 |
+
e363e5588da122516e6b6414dc3245c6b6ecda3a4d225da2a5401a8439b9598e model-00005-of-00018.safetensors
|
| 10 |
+
95aa0840f60dfb60c330e5dffdb581d421925b5913578782214167ce56204ded model-00006-of-00018.safetensors
|
| 11 |
+
23393d5adf5db589452a09c8be1577f3371ccf2a72ef594730d45e9141d37c1f model-00007-of-00018.safetensors
|
| 12 |
+
0586e5043a501aae89bf5919d6ea80797b2980614b1e70d0b61023b84ca99537 model-00008-of-00018.safetensors
|
| 13 |
+
be7fab3e4feeb0e0dd286764134f1f4761a1fed4f68529d61a33612e224efffa model-00009-of-00018.safetensors
|
| 14 |
+
2841a820dcf32c176eac0baf77a0b26b2712247c3c2cdb7f99947760d5482e98 model-00010-of-00018.safetensors
|
| 15 |
+
036da171cda513926755523f2c65a3a137298383eebac2aa3786baeda6c34a84 model-00011-of-00018.safetensors
|
| 16 |
+
4a02f4af6c63dd2f98595176a9b7403c4dd8ed62aef091a739019f44359175c7 model-00012-of-00018.safetensors
|
| 17 |
+
153728fdeddb223a2671f94f84576fadd7a597c6b3df08acb3ca0d86b0923678 model-00013-of-00018.safetensors
|
| 18 |
+
fceedec3f634206be2d9768fda14afcbf9c7f92242e5ade3edd8dc77cb4d9731 model-00014-of-00018.safetensors
|
| 19 |
+
a15fa30f3210bf8c27303b917780dbbbe913ec666c5229cdc7f62e2e7bac992a model-00015-of-00018.safetensors
|
| 20 |
+
da7b7f6517ca2e8663ac548b546d29b9aae27c2e3786741a6777a65ed233562f model-00016-of-00018.safetensors
|
| 21 |
+
29a0838eab6c1edb3317088ad90d8b97248e8c86d44874e0fa2d6789b614d4af model-00017-of-00018.safetensors
|
| 22 |
+
7b4cb032dbb21a84c35a9991e011db2628ea318ecf8eaf09e95f747ea274bc27 model-00018-of-00018.safetensors
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,1042 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"weight_map": {
|
| 3 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00018.safetensors",
|
| 4 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
|
| 5 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
|
| 6 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
|
| 7 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00018.safetensors",
|
| 8 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00018.safetensors",
|
| 9 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00018.safetensors",
|
| 10 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00018.safetensors",
|
| 11 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00018.safetensors",
|
| 12 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00018.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00018.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00018.safetensors",
|
| 15 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00018.safetensors",
|
| 16 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
|
| 17 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
|
| 18 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
|
| 19 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00018.safetensors",
|
| 20 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00018.safetensors",
|
| 21 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00018.safetensors",
|
| 22 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00018.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00018.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00018.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00018.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00018.safetensors",
|
| 27 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00018.safetensors",
|
| 28 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
|
| 29 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
|
| 30 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
|
| 31 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00018.safetensors",
|
| 32 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00018.safetensors",
|
| 33 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00018.safetensors",
|
| 34 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00018.safetensors",
|
| 35 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00018.safetensors",
|
| 36 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00018.safetensors",
|
| 37 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00018.safetensors",
|
| 38 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00018.safetensors",
|
| 39 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00018.safetensors",
|
| 40 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
|
| 41 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
|
| 42 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
|
| 43 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00018.safetensors",
|
| 44 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00018.safetensors",
|
| 45 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00018.safetensors",
|
| 46 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00018.safetensors",
|
| 47 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00018.safetensors",
|
| 48 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00018.safetensors",
|
| 49 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00018.safetensors",
|
| 50 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00018.safetensors",
|
| 51 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00018.safetensors",
|
| 52 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
|
| 53 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
|
| 54 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
|
| 55 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00018.safetensors",
|
| 56 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00018.safetensors",
|
| 57 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00018.safetensors",
|
| 58 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00018.safetensors",
|
| 59 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00018.safetensors",
|
| 60 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00018.safetensors",
|
| 61 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00018.safetensors",
|
| 62 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00018.safetensors",
|
| 63 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00018.safetensors",
|
| 64 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00018.safetensors",
|
| 65 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00018.safetensors",
|
| 66 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00018.safetensors",
|
| 67 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00018.safetensors",
|
| 68 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00018.safetensors",
|
| 69 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00018.safetensors",
|
| 70 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
|
| 71 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00018.safetensors",
|
| 72 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00018.safetensors",
|
| 73 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00018.safetensors",
|
| 74 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00018.safetensors",
|
| 75 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00018.safetensors",
|
| 76 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00018.safetensors",
|
| 77 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00018.safetensors",
|
| 78 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00018.safetensors",
|
| 79 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00018.safetensors",
|
| 80 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00018.safetensors",
|
| 81 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00018.safetensors",
|
| 82 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
|
| 83 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00018.safetensors",
|
| 84 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00018.safetensors",
|
| 85 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00018.safetensors",
|
| 86 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00018.safetensors",
|
| 87 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00018.safetensors",
|
| 88 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00018.safetensors",
|
| 89 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00018.safetensors",
|
| 90 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00018.safetensors",
|
| 91 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00018.safetensors",
|
| 92 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00018.safetensors",
|
| 93 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00018.safetensors",
|
| 94 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
|
| 95 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00018.safetensors",
|
| 96 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00018.safetensors",
|
| 97 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00018.safetensors",
|
| 98 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00018.safetensors",
|
| 99 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00018.safetensors",
|
| 100 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00018.safetensors",
|
| 101 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00018.safetensors",
|
| 102 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00018.safetensors",
|
| 103 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00018.safetensors",
|
| 104 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00018.safetensors",
|
| 105 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00018.safetensors",
|
| 106 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
|
| 107 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00018.safetensors",
|
| 108 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00018.safetensors",
|
| 109 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00018.safetensors",
|
| 110 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00018.safetensors",
|
| 111 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00018.safetensors",
|
| 112 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00018.safetensors",
|
| 113 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00018.safetensors",
|
| 114 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00018.safetensors",
|
| 115 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00018.safetensors",
|
| 116 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00018.safetensors",
|
| 117 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00018.safetensors",
|
| 118 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
|
| 119 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00018.safetensors",
|
| 120 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00018.safetensors",
|
| 121 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00018.safetensors",
|
| 122 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00018.safetensors",
|
| 123 |
+
"model.layers.10.input_layernorm.weight": "model-00003-of-00018.safetensors",
|
| 124 |
+
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00018.safetensors",
|
| 125 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00018.safetensors",
|
| 126 |
+
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00018.safetensors",
|
| 127 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00018.safetensors",
|
| 128 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00003-of-00018.safetensors",
|
| 129 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00018.safetensors",
|
| 130 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00018.safetensors",
|
| 131 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00003-of-00018.safetensors",
|
| 132 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00018.safetensors",
|
| 133 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00003-of-00018.safetensors",
|
| 134 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00018.safetensors",
|
| 135 |
+
"model.layers.11.input_layernorm.weight": "model-00003-of-00018.safetensors",
|
| 136 |
+
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00018.safetensors",
|
| 137 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00018.safetensors",
|
| 138 |
+
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00018.safetensors",
|
| 139 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00018.safetensors",
|
| 140 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00003-of-00018.safetensors",
|
| 141 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00018.safetensors",
|
| 142 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00018.safetensors",
|
| 143 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00003-of-00018.safetensors",
|
| 144 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00018.safetensors",
|
| 145 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00003-of-00018.safetensors",
|
| 146 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00018.safetensors",
|
| 147 |
+
"model.layers.12.input_layernorm.weight": "model-00003-of-00018.safetensors",
|
| 148 |
+
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00018.safetensors",
|
| 149 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00018.safetensors",
|
| 150 |
+
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00018.safetensors",
|
| 151 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00018.safetensors",
|
| 152 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00003-of-00018.safetensors",
|
| 153 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00018.safetensors",
|
| 154 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00018.safetensors",
|
| 155 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00003-of-00018.safetensors",
|
| 156 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00018.safetensors",
|
| 157 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00003-of-00018.safetensors",
|
| 158 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00018.safetensors",
|
| 159 |
+
"model.layers.13.input_layernorm.weight": "model-00003-of-00018.safetensors",
|
| 160 |
+
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00018.safetensors",
|
| 161 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00018.safetensors",
|
| 162 |
+
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00018.safetensors",
|
| 163 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00018.safetensors",
|
| 164 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00003-of-00018.safetensors",
|
| 165 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00018.safetensors",
|
| 166 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00018.safetensors",
|
| 167 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00003-of-00018.safetensors",
|
| 168 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00018.safetensors",
|
| 169 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00003-of-00018.safetensors",
|
| 170 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00018.safetensors",
|
| 171 |
+
"model.layers.14.input_layernorm.weight": "model-00003-of-00018.safetensors",
|
| 172 |
+
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00018.safetensors",
|
| 173 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00018.safetensors",
|
| 174 |
+
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00018.safetensors",
|
| 175 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00018.safetensors",
|
| 176 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00003-of-00018.safetensors",
|
| 177 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00018.safetensors",
|
| 178 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00018.safetensors",
|
| 179 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00003-of-00018.safetensors",
|
| 180 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00018.safetensors",
|
| 181 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00003-of-00018.safetensors",
|
| 182 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00018.safetensors",
|
| 183 |
+
"model.layers.15.input_layernorm.weight": "model-00004-of-00018.safetensors",
|
| 184 |
+
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00018.safetensors",
|
| 185 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00018.safetensors",
|
| 186 |
+
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00018.safetensors",
|
| 187 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00018.safetensors",
|
| 188 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00004-of-00018.safetensors",
|
| 189 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00018.safetensors",
|
| 190 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00018.safetensors",
|
| 191 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00004-of-00018.safetensors",
|
| 192 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00018.safetensors",
|
| 193 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00004-of-00018.safetensors",
|
| 194 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00018.safetensors",
|
| 195 |
+
"model.layers.16.input_layernorm.weight": "model-00004-of-00018.safetensors",
|
| 196 |
+
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00018.safetensors",
|
| 197 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00018.safetensors",
|
| 198 |
+
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00018.safetensors",
|
| 199 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00018.safetensors",
|
| 200 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00004-of-00018.safetensors",
|
| 201 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00018.safetensors",
|
| 202 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00018.safetensors",
|
| 203 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00004-of-00018.safetensors",
|
| 204 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00018.safetensors",
|
| 205 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00004-of-00018.safetensors",
|
| 206 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00018.safetensors",
|
| 207 |
+
"model.layers.17.input_layernorm.weight": "model-00004-of-00018.safetensors",
|
| 208 |
+
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00018.safetensors",
|
| 209 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00018.safetensors",
|
| 210 |
+
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00018.safetensors",
|
| 211 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00018.safetensors",
|
| 212 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00004-of-00018.safetensors",
|
| 213 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00018.safetensors",
|
| 214 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00018.safetensors",
|
| 215 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00004-of-00018.safetensors",
|
| 216 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00018.safetensors",
|
| 217 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00004-of-00018.safetensors",
|
| 218 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00018.safetensors",
|
| 219 |
+
"model.layers.18.input_layernorm.weight": "model-00004-of-00018.safetensors",
|
| 220 |
+
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00018.safetensors",
|
| 221 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00018.safetensors",
|
| 222 |
+
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00018.safetensors",
|
| 223 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00018.safetensors",
|
| 224 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00004-of-00018.safetensors",
|
| 225 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00018.safetensors",
|
| 226 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00018.safetensors",
|
| 227 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00004-of-00018.safetensors",
|
| 228 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00018.safetensors",
|
| 229 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00004-of-00018.safetensors",
|
| 230 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00018.safetensors",
|
| 231 |
+
"model.layers.19.input_layernorm.weight": "model-00004-of-00018.safetensors",
|
| 232 |
+
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00018.safetensors",
|
| 233 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00018.safetensors",
|
| 234 |
+
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00018.safetensors",
|
| 235 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00018.safetensors",
|
| 236 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00004-of-00018.safetensors",
|
| 237 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00018.safetensors",
|
| 238 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00018.safetensors",
|
| 239 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00004-of-00018.safetensors",
|
| 240 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00018.safetensors",
|
| 241 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00004-of-00018.safetensors",
|
| 242 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00018.safetensors",
|
| 243 |
+
"model.layers.20.input_layernorm.weight": "model-00005-of-00018.safetensors",
|
| 244 |
+
"model.layers.20.mlp.down_proj.weight": "model-00005-of-00018.safetensors",
|
| 245 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00018.safetensors",
|
| 246 |
+
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00018.safetensors",
|
| 247 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00005-of-00018.safetensors",
|
| 248 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00005-of-00018.safetensors",
|
| 249 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00018.safetensors",
|
| 250 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00018.safetensors",
|
| 251 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00005-of-00018.safetensors",
|
| 252 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00018.safetensors",
|
| 253 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00005-of-00018.safetensors",
|
| 254 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00018.safetensors",
|
| 255 |
+
"model.layers.21.input_layernorm.weight": "model-00005-of-00018.safetensors",
|
| 256 |
+
"model.layers.21.mlp.down_proj.weight": "model-00005-of-00018.safetensors",
|
| 257 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00005-of-00018.safetensors",
|
| 258 |
+
"model.layers.21.mlp.up_proj.weight": "model-00005-of-00018.safetensors",
|
| 259 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00005-of-00018.safetensors",
|
| 260 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00005-of-00018.safetensors",
|
| 261 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00018.safetensors",
|
| 262 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00018.safetensors",
|
| 263 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00005-of-00018.safetensors",
|
| 264 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00018.safetensors",
|
| 265 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00005-of-00018.safetensors",
|
| 266 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00018.safetensors",
|
| 267 |
+
"model.layers.22.input_layernorm.weight": "model-00005-of-00018.safetensors",
|
| 268 |
+
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00018.safetensors",
|
| 269 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00018.safetensors",
|
| 270 |
+
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00018.safetensors",
|
| 271 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00018.safetensors",
|
| 272 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00005-of-00018.safetensors",
|
| 273 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00005-of-00018.safetensors",
|
| 274 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00005-of-00018.safetensors",
|
| 275 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00005-of-00018.safetensors",
|
| 276 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00005-of-00018.safetensors",
|
| 277 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00005-of-00018.safetensors",
|
| 278 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00005-of-00018.safetensors",
|
| 279 |
+
"model.layers.23.input_layernorm.weight": "model-00005-of-00018.safetensors",
|
| 280 |
+
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00018.safetensors",
|
| 281 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00018.safetensors",
|
| 282 |
+
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00018.safetensors",
|
| 283 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00018.safetensors",
|
| 284 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00005-of-00018.safetensors",
|
| 285 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00018.safetensors",
|
| 286 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00018.safetensors",
|
| 287 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00005-of-00018.safetensors",
|
| 288 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00018.safetensors",
|
| 289 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00005-of-00018.safetensors",
|
| 290 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00018.safetensors",
|
| 291 |
+
"model.layers.24.input_layernorm.weight": "model-00005-of-00018.safetensors",
|
| 292 |
+
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00018.safetensors",
|
| 293 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00018.safetensors",
|
| 294 |
+
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00018.safetensors",
|
| 295 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00018.safetensors",
|
| 296 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00005-of-00018.safetensors",
|
| 297 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00018.safetensors",
|
| 298 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00018.safetensors",
|
| 299 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00005-of-00018.safetensors",
|
| 300 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00018.safetensors",
|
| 301 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00005-of-00018.safetensors",
|
| 302 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00018.safetensors",
|
| 303 |
+
"model.layers.25.input_layernorm.weight": "model-00006-of-00018.safetensors",
|
| 304 |
+
"model.layers.25.mlp.down_proj.weight": "model-00006-of-00018.safetensors",
|
| 305 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00006-of-00018.safetensors",
|
| 306 |
+
"model.layers.25.mlp.up_proj.weight": "model-00006-of-00018.safetensors",
|
| 307 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00006-of-00018.safetensors",
|
| 308 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00006-of-00018.safetensors",
|
| 309 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00018.safetensors",
|
| 310 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00018.safetensors",
|
| 311 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00006-of-00018.safetensors",
|
| 312 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00018.safetensors",
|
| 313 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00006-of-00018.safetensors",
|
| 314 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00018.safetensors",
|
| 315 |
+
"model.layers.26.input_layernorm.weight": "model-00006-of-00018.safetensors",
|
| 316 |
+
"model.layers.26.mlp.down_proj.weight": "model-00006-of-00018.safetensors",
|
| 317 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00006-of-00018.safetensors",
|
| 318 |
+
"model.layers.26.mlp.up_proj.weight": "model-00006-of-00018.safetensors",
|
| 319 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00006-of-00018.safetensors",
|
| 320 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00006-of-00018.safetensors",
|
| 321 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00006-of-00018.safetensors",
|
| 322 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00006-of-00018.safetensors",
|
| 323 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00006-of-00018.safetensors",
|
| 324 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00006-of-00018.safetensors",
|
| 325 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00006-of-00018.safetensors",
|
| 326 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00006-of-00018.safetensors",
|
| 327 |
+
"model.layers.27.input_layernorm.weight": "model-00006-of-00018.safetensors",
|
| 328 |
+
"model.layers.27.mlp.down_proj.weight": "model-00006-of-00018.safetensors",
|
| 329 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00006-of-00018.safetensors",
|
| 330 |
+
"model.layers.27.mlp.up_proj.weight": "model-00006-of-00018.safetensors",
|
| 331 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00018.safetensors",
|
| 332 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00006-of-00018.safetensors",
|
| 333 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00006-of-00018.safetensors",
|
| 334 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00006-of-00018.safetensors",
|
| 335 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00006-of-00018.safetensors",
|
| 336 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00006-of-00018.safetensors",
|
| 337 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00006-of-00018.safetensors",
|
| 338 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00006-of-00018.safetensors",
|
| 339 |
+
"model.layers.28.input_layernorm.weight": "model-00006-of-00018.safetensors",
|
| 340 |
+
"model.layers.28.mlp.down_proj.weight": "model-00006-of-00018.safetensors",
|
| 341 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00006-of-00018.safetensors",
|
| 342 |
+
"model.layers.28.mlp.up_proj.weight": "model-00006-of-00018.safetensors",
|
| 343 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00006-of-00018.safetensors",
|
| 344 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00006-of-00018.safetensors",
|
| 345 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00006-of-00018.safetensors",
|
| 346 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00006-of-00018.safetensors",
|
| 347 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00006-of-00018.safetensors",
|
| 348 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00006-of-00018.safetensors",
|
| 349 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00006-of-00018.safetensors",
|
| 350 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00006-of-00018.safetensors",
|
| 351 |
+
"model.layers.29.input_layernorm.weight": "model-00006-of-00018.safetensors",
|
| 352 |
+
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00018.safetensors",
|
| 353 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00018.safetensors",
|
| 354 |
+
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00018.safetensors",
|
| 355 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00018.safetensors",
|
| 356 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00006-of-00018.safetensors",
|
| 357 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00018.safetensors",
|
| 358 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00018.safetensors",
|
| 359 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00006-of-00018.safetensors",
|
| 360 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00018.safetensors",
|
| 361 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00006-of-00018.safetensors",
|
| 362 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00018.safetensors",
|
| 363 |
+
"model.layers.30.input_layernorm.weight": "model-00007-of-00018.safetensors",
|
| 364 |
+
"model.layers.30.mlp.down_proj.weight": "model-00007-of-00018.safetensors",
|
| 365 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00007-of-00018.safetensors",
|
| 366 |
+
"model.layers.30.mlp.up_proj.weight": "model-00007-of-00018.safetensors",
|
| 367 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00007-of-00018.safetensors",
|
| 368 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00007-of-00018.safetensors",
|
| 369 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00007-of-00018.safetensors",
|
| 370 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00007-of-00018.safetensors",
|
| 371 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00007-of-00018.safetensors",
|
| 372 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00007-of-00018.safetensors",
|
| 373 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00007-of-00018.safetensors",
|
| 374 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00007-of-00018.safetensors",
|
| 375 |
+
"model.layers.31.input_layernorm.weight": "model-00007-of-00018.safetensors",
|
| 376 |
+
"model.layers.31.mlp.down_proj.weight": "model-00007-of-00018.safetensors",
|
| 377 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00007-of-00018.safetensors",
|
| 378 |
+
"model.layers.31.mlp.up_proj.weight": "model-00007-of-00018.safetensors",
|
| 379 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00007-of-00018.safetensors",
|
| 380 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00007-of-00018.safetensors",
|
| 381 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00007-of-00018.safetensors",
|
| 382 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00007-of-00018.safetensors",
|
| 383 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00007-of-00018.safetensors",
|
| 384 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00007-of-00018.safetensors",
|
| 385 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00007-of-00018.safetensors",
|
| 386 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00007-of-00018.safetensors",
|
| 387 |
+
"model.layers.32.input_layernorm.weight": "model-00007-of-00018.safetensors",
|
| 388 |
+
"model.layers.32.mlp.down_proj.weight": "model-00007-of-00018.safetensors",
|
| 389 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00007-of-00018.safetensors",
|
| 390 |
+
"model.layers.32.mlp.up_proj.weight": "model-00007-of-00018.safetensors",
|
| 391 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00007-of-00018.safetensors",
|
| 392 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00007-of-00018.safetensors",
|
| 393 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00007-of-00018.safetensors",
|
| 394 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00007-of-00018.safetensors",
|
| 395 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00007-of-00018.safetensors",
|
| 396 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00007-of-00018.safetensors",
|
| 397 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00007-of-00018.safetensors",
|
| 398 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00007-of-00018.safetensors",
|
| 399 |
+
"model.layers.33.input_layernorm.weight": "model-00007-of-00018.safetensors",
|
| 400 |
+
"model.layers.33.mlp.down_proj.weight": "model-00007-of-00018.safetensors",
|
| 401 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00007-of-00018.safetensors",
|
| 402 |
+
"model.layers.33.mlp.up_proj.weight": "model-00007-of-00018.safetensors",
|
| 403 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00007-of-00018.safetensors",
|
| 404 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00007-of-00018.safetensors",
|
| 405 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00007-of-00018.safetensors",
|
| 406 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00007-of-00018.safetensors",
|
| 407 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00007-of-00018.safetensors",
|
| 408 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00007-of-00018.safetensors",
|
| 409 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00007-of-00018.safetensors",
|
| 410 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00007-of-00018.safetensors",
|
| 411 |
+
"model.layers.34.input_layernorm.weight": "model-00007-of-00018.safetensors",
|
| 412 |
+
"model.layers.34.mlp.down_proj.weight": "model-00007-of-00018.safetensors",
|
| 413 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00007-of-00018.safetensors",
|
| 414 |
+
"model.layers.34.mlp.up_proj.weight": "model-00007-of-00018.safetensors",
|
| 415 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00007-of-00018.safetensors",
|
| 416 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00007-of-00018.safetensors",
|
| 417 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00007-of-00018.safetensors",
|
| 418 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00007-of-00018.safetensors",
|
| 419 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00007-of-00018.safetensors",
|
| 420 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00007-of-00018.safetensors",
|
| 421 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00007-of-00018.safetensors",
|
| 422 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00007-of-00018.safetensors",
|
| 423 |
+
"model.layers.35.input_layernorm.weight": "model-00008-of-00018.safetensors",
|
| 424 |
+
"model.layers.35.mlp.down_proj.weight": "model-00008-of-00018.safetensors",
|
| 425 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00008-of-00018.safetensors",
|
| 426 |
+
"model.layers.35.mlp.up_proj.weight": "model-00008-of-00018.safetensors",
|
| 427 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00008-of-00018.safetensors",
|
| 428 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00008-of-00018.safetensors",
|
| 429 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00008-of-00018.safetensors",
|
| 430 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00008-of-00018.safetensors",
|
| 431 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00008-of-00018.safetensors",
|
| 432 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00008-of-00018.safetensors",
|
| 433 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00008-of-00018.safetensors",
|
| 434 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00008-of-00018.safetensors",
|
| 435 |
+
"model.layers.36.input_layernorm.weight": "model-00008-of-00018.safetensors",
|
| 436 |
+
"model.layers.36.mlp.down_proj.weight": "model-00008-of-00018.safetensors",
|
| 437 |
+
"model.layers.36.mlp.gate_proj.weight": "model-00008-of-00018.safetensors",
|
| 438 |
+
"model.layers.36.mlp.up_proj.weight": "model-00008-of-00018.safetensors",
|
| 439 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00008-of-00018.safetensors",
|
| 440 |
+
"model.layers.36.self_attn.k_proj.bias": "model-00008-of-00018.safetensors",
|
| 441 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00008-of-00018.safetensors",
|
| 442 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00008-of-00018.safetensors",
|
| 443 |
+
"model.layers.36.self_attn.q_proj.bias": "model-00008-of-00018.safetensors",
|
| 444 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00008-of-00018.safetensors",
|
| 445 |
+
"model.layers.36.self_attn.v_proj.bias": "model-00008-of-00018.safetensors",
|
| 446 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00008-of-00018.safetensors",
|
| 447 |
+
"model.layers.37.input_layernorm.weight": "model-00008-of-00018.safetensors",
|
| 448 |
+
"model.layers.37.mlp.down_proj.weight": "model-00008-of-00018.safetensors",
|
| 449 |
+
"model.layers.37.mlp.gate_proj.weight": "model-00008-of-00018.safetensors",
|
| 450 |
+
"model.layers.37.mlp.up_proj.weight": "model-00008-of-00018.safetensors",
|
| 451 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00008-of-00018.safetensors",
|
| 452 |
+
"model.layers.37.self_attn.k_proj.bias": "model-00008-of-00018.safetensors",
|
| 453 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00008-of-00018.safetensors",
|
| 454 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00008-of-00018.safetensors",
|
| 455 |
+
"model.layers.37.self_attn.q_proj.bias": "model-00008-of-00018.safetensors",
|
| 456 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00008-of-00018.safetensors",
|
| 457 |
+
"model.layers.37.self_attn.v_proj.bias": "model-00008-of-00018.safetensors",
|
| 458 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00008-of-00018.safetensors",
|
| 459 |
+
"model.layers.38.input_layernorm.weight": "model-00008-of-00018.safetensors",
|
| 460 |
+
"model.layers.38.mlp.down_proj.weight": "model-00008-of-00018.safetensors",
|
| 461 |
+
"model.layers.38.mlp.gate_proj.weight": "model-00008-of-00018.safetensors",
|
| 462 |
+
"model.layers.38.mlp.up_proj.weight": "model-00008-of-00018.safetensors",
|
| 463 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00008-of-00018.safetensors",
|
| 464 |
+
"model.layers.38.self_attn.k_proj.bias": "model-00008-of-00018.safetensors",
|
| 465 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00008-of-00018.safetensors",
|
| 466 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00008-of-00018.safetensors",
|
| 467 |
+
"model.layers.38.self_attn.q_proj.bias": "model-00008-of-00018.safetensors",
|
| 468 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00008-of-00018.safetensors",
|
| 469 |
+
"model.layers.38.self_attn.v_proj.bias": "model-00008-of-00018.safetensors",
|
| 470 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00008-of-00018.safetensors",
|
| 471 |
+
"model.layers.39.input_layernorm.weight": "model-00008-of-00018.safetensors",
|
| 472 |
+
"model.layers.39.mlp.down_proj.weight": "model-00008-of-00018.safetensors",
|
| 473 |
+
"model.layers.39.mlp.gate_proj.weight": "model-00008-of-00018.safetensors",
|
| 474 |
+
"model.layers.39.mlp.up_proj.weight": "model-00008-of-00018.safetensors",
|
| 475 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00008-of-00018.safetensors",
|
| 476 |
+
"model.layers.39.self_attn.k_proj.bias": "model-00008-of-00018.safetensors",
|
| 477 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00008-of-00018.safetensors",
|
| 478 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00008-of-00018.safetensors",
|
| 479 |
+
"model.layers.39.self_attn.q_proj.bias": "model-00008-of-00018.safetensors",
|
| 480 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00008-of-00018.safetensors",
|
| 481 |
+
"model.layers.39.self_attn.v_proj.bias": "model-00008-of-00018.safetensors",
|
| 482 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00008-of-00018.safetensors",
|
| 483 |
+
"model.layers.40.input_layernorm.weight": "model-00009-of-00018.safetensors",
|
| 484 |
+
"model.layers.40.mlp.down_proj.weight": "model-00009-of-00018.safetensors",
|
| 485 |
+
"model.layers.40.mlp.gate_proj.weight": "model-00009-of-00018.safetensors",
|
| 486 |
+
"model.layers.40.mlp.up_proj.weight": "model-00009-of-00018.safetensors",
|
| 487 |
+
"model.layers.40.post_attention_layernorm.weight": "model-00009-of-00018.safetensors",
|
| 488 |
+
"model.layers.40.self_attn.k_proj.bias": "model-00009-of-00018.safetensors",
|
| 489 |
+
"model.layers.40.self_attn.k_proj.weight": "model-00009-of-00018.safetensors",
|
| 490 |
+
"model.layers.40.self_attn.o_proj.weight": "model-00009-of-00018.safetensors",
|
| 491 |
+
"model.layers.40.self_attn.q_proj.bias": "model-00009-of-00018.safetensors",
|
| 492 |
+
"model.layers.40.self_attn.q_proj.weight": "model-00009-of-00018.safetensors",
|
| 493 |
+
"model.layers.40.self_attn.v_proj.bias": "model-00009-of-00018.safetensors",
|
| 494 |
+
"model.layers.40.self_attn.v_proj.weight": "model-00009-of-00018.safetensors",
|
| 495 |
+
"model.layers.41.input_layernorm.weight": "model-00009-of-00018.safetensors",
|
| 496 |
+
"model.layers.41.mlp.down_proj.weight": "model-00009-of-00018.safetensors",
|
| 497 |
+
"model.layers.41.mlp.gate_proj.weight": "model-00009-of-00018.safetensors",
|
| 498 |
+
"model.layers.41.mlp.up_proj.weight": "model-00009-of-00018.safetensors",
|
| 499 |
+
"model.layers.41.post_attention_layernorm.weight": "model-00009-of-00018.safetensors",
|
| 500 |
+
"model.layers.41.self_attn.k_proj.bias": "model-00009-of-00018.safetensors",
|
| 501 |
+
"model.layers.41.self_attn.k_proj.weight": "model-00009-of-00018.safetensors",
|
| 502 |
+
"model.layers.41.self_attn.o_proj.weight": "model-00009-of-00018.safetensors",
|
| 503 |
+
"model.layers.41.self_attn.q_proj.bias": "model-00009-of-00018.safetensors",
|
| 504 |
+
"model.layers.41.self_attn.q_proj.weight": "model-00009-of-00018.safetensors",
|
| 505 |
+
"model.layers.41.self_attn.v_proj.bias": "model-00009-of-00018.safetensors",
|
| 506 |
+
"model.layers.41.self_attn.v_proj.weight": "model-00009-of-00018.safetensors",
|
| 507 |
+
"model.layers.42.input_layernorm.weight": "model-00009-of-00018.safetensors",
|
| 508 |
+
"model.layers.42.mlp.down_proj.weight": "model-00009-of-00018.safetensors",
|
| 509 |
+
"model.layers.42.mlp.gate_proj.weight": "model-00009-of-00018.safetensors",
|
| 510 |
+
"model.layers.42.mlp.up_proj.weight": "model-00009-of-00018.safetensors",
|
| 511 |
+
"model.layers.42.post_attention_layernorm.weight": "model-00009-of-00018.safetensors",
|
| 512 |
+
"model.layers.42.self_attn.k_proj.bias": "model-00009-of-00018.safetensors",
|
| 513 |
+
"model.layers.42.self_attn.k_proj.weight": "model-00009-of-00018.safetensors",
|
| 514 |
+
"model.layers.42.self_attn.o_proj.weight": "model-00009-of-00018.safetensors",
|
| 515 |
+
"model.layers.42.self_attn.q_proj.bias": "model-00009-of-00018.safetensors",
|
| 516 |
+
"model.layers.42.self_attn.q_proj.weight": "model-00009-of-00018.safetensors",
|
| 517 |
+
"model.layers.42.self_attn.v_proj.bias": "model-00009-of-00018.safetensors",
|
| 518 |
+
"model.layers.42.self_attn.v_proj.weight": "model-00009-of-00018.safetensors",
|
| 519 |
+
"model.layers.43.input_layernorm.weight": "model-00009-of-00018.safetensors",
|
| 520 |
+
"model.layers.43.mlp.down_proj.weight": "model-00009-of-00018.safetensors",
|
| 521 |
+
"model.layers.43.mlp.gate_proj.weight": "model-00009-of-00018.safetensors",
|
| 522 |
+
"model.layers.43.mlp.up_proj.weight": "model-00009-of-00018.safetensors",
|
| 523 |
+
"model.layers.43.post_attention_layernorm.weight": "model-00009-of-00018.safetensors",
|
| 524 |
+
"model.layers.43.self_attn.k_proj.bias": "model-00009-of-00018.safetensors",
|
| 525 |
+
"model.layers.43.self_attn.k_proj.weight": "model-00009-of-00018.safetensors",
|
| 526 |
+
"model.layers.43.self_attn.o_proj.weight": "model-00009-of-00018.safetensors",
|
| 527 |
+
"model.layers.43.self_attn.q_proj.bias": "model-00009-of-00018.safetensors",
|
| 528 |
+
"model.layers.43.self_attn.q_proj.weight": "model-00009-of-00018.safetensors",
|
| 529 |
+
"model.layers.43.self_attn.v_proj.bias": "model-00009-of-00018.safetensors",
|
| 530 |
+
"model.layers.43.self_attn.v_proj.weight": "model-00009-of-00018.safetensors",
|
| 531 |
+
"model.layers.44.input_layernorm.weight": "model-00009-of-00018.safetensors",
|
| 532 |
+
"model.layers.44.mlp.down_proj.weight": "model-00009-of-00018.safetensors",
|
| 533 |
+
"model.layers.44.mlp.gate_proj.weight": "model-00009-of-00018.safetensors",
|
| 534 |
+
"model.layers.44.mlp.up_proj.weight": "model-00009-of-00018.safetensors",
|
| 535 |
+
"model.layers.44.post_attention_layernorm.weight": "model-00009-of-00018.safetensors",
|
| 536 |
+
"model.layers.44.self_attn.k_proj.bias": "model-00009-of-00018.safetensors",
|
| 537 |
+
"model.layers.44.self_attn.k_proj.weight": "model-00009-of-00018.safetensors",
|
| 538 |
+
"model.layers.44.self_attn.o_proj.weight": "model-00009-of-00018.safetensors",
|
| 539 |
+
"model.layers.44.self_attn.q_proj.bias": "model-00009-of-00018.safetensors",
|
| 540 |
+
"model.layers.44.self_attn.q_proj.weight": "model-00009-of-00018.safetensors",
|
| 541 |
+
"model.layers.44.self_attn.v_proj.bias": "model-00009-of-00018.safetensors",
|
| 542 |
+
"model.layers.44.self_attn.v_proj.weight": "model-00009-of-00018.safetensors",
|
| 543 |
+
"model.layers.45.input_layernorm.weight": "model-00010-of-00018.safetensors",
|
| 544 |
+
"model.layers.45.mlp.down_proj.weight": "model-00010-of-00018.safetensors",
|
| 545 |
+
"model.layers.45.mlp.gate_proj.weight": "model-00010-of-00018.safetensors",
|
| 546 |
+
"model.layers.45.mlp.up_proj.weight": "model-00010-of-00018.safetensors",
|
| 547 |
+
"model.layers.45.post_attention_layernorm.weight": "model-00010-of-00018.safetensors",
|
| 548 |
+
"model.layers.45.self_attn.k_proj.bias": "model-00010-of-00018.safetensors",
|
| 549 |
+
"model.layers.45.self_attn.k_proj.weight": "model-00010-of-00018.safetensors",
|
| 550 |
+
"model.layers.45.self_attn.o_proj.weight": "model-00010-of-00018.safetensors",
|
| 551 |
+
"model.layers.45.self_attn.q_proj.bias": "model-00010-of-00018.safetensors",
|
| 552 |
+
"model.layers.45.self_attn.q_proj.weight": "model-00010-of-00018.safetensors",
|
| 553 |
+
"model.layers.45.self_attn.v_proj.bias": "model-00010-of-00018.safetensors",
|
| 554 |
+
"model.layers.45.self_attn.v_proj.weight": "model-00010-of-00018.safetensors",
|
| 555 |
+
"model.layers.46.input_layernorm.weight": "model-00010-of-00018.safetensors",
|
| 556 |
+
"model.layers.46.mlp.down_proj.weight": "model-00010-of-00018.safetensors",
|
| 557 |
+
"model.layers.46.mlp.gate_proj.weight": "model-00010-of-00018.safetensors",
|
| 558 |
+
"model.layers.46.mlp.up_proj.weight": "model-00010-of-00018.safetensors",
|
| 559 |
+
"model.layers.46.post_attention_layernorm.weight": "model-00010-of-00018.safetensors",
|
| 560 |
+
"model.layers.46.self_attn.k_proj.bias": "model-00010-of-00018.safetensors",
|
| 561 |
+
"model.layers.46.self_attn.k_proj.weight": "model-00010-of-00018.safetensors",
|
| 562 |
+
"model.layers.46.self_attn.o_proj.weight": "model-00010-of-00018.safetensors",
|
| 563 |
+
"model.layers.46.self_attn.q_proj.bias": "model-00010-of-00018.safetensors",
|
| 564 |
+
"model.layers.46.self_attn.q_proj.weight": "model-00010-of-00018.safetensors",
|
| 565 |
+
"model.layers.46.self_attn.v_proj.bias": "model-00010-of-00018.safetensors",
|
| 566 |
+
"model.layers.46.self_attn.v_proj.weight": "model-00010-of-00018.safetensors",
|
| 567 |
+
"model.layers.47.input_layernorm.weight": "model-00010-of-00018.safetensors",
|
| 568 |
+
"model.layers.47.mlp.down_proj.weight": "model-00010-of-00018.safetensors",
|
| 569 |
+
"model.layers.47.mlp.gate_proj.weight": "model-00010-of-00018.safetensors",
|
| 570 |
+
"model.layers.47.mlp.up_proj.weight": "model-00010-of-00018.safetensors",
|
| 571 |
+
"model.layers.47.post_attention_layernorm.weight": "model-00010-of-00018.safetensors",
|
| 572 |
+
"model.layers.47.self_attn.k_proj.bias": "model-00010-of-00018.safetensors",
|
| 573 |
+
"model.layers.47.self_attn.k_proj.weight": "model-00010-of-00018.safetensors",
|
| 574 |
+
"model.layers.47.self_attn.o_proj.weight": "model-00010-of-00018.safetensors",
|
| 575 |
+
"model.layers.47.self_attn.q_proj.bias": "model-00010-of-00018.safetensors",
|
| 576 |
+
"model.layers.47.self_attn.q_proj.weight": "model-00010-of-00018.safetensors",
|
| 577 |
+
"model.layers.47.self_attn.v_proj.bias": "model-00010-of-00018.safetensors",
|
| 578 |
+
"model.layers.47.self_attn.v_proj.weight": "model-00010-of-00018.safetensors",
|
| 579 |
+
"model.layers.48.input_layernorm.weight": "model-00010-of-00018.safetensors",
|
| 580 |
+
"model.layers.48.mlp.down_proj.weight": "model-00010-of-00018.safetensors",
|
| 581 |
+
"model.layers.48.mlp.gate_proj.weight": "model-00010-of-00018.safetensors",
|
| 582 |
+
"model.layers.48.mlp.up_proj.weight": "model-00010-of-00018.safetensors",
|
| 583 |
+
"model.layers.48.post_attention_layernorm.weight": "model-00010-of-00018.safetensors",
|
| 584 |
+
"model.layers.48.self_attn.k_proj.bias": "model-00010-of-00018.safetensors",
|
| 585 |
+
"model.layers.48.self_attn.k_proj.weight": "model-00010-of-00018.safetensors",
|
| 586 |
+
"model.layers.48.self_attn.o_proj.weight": "model-00010-of-00018.safetensors",
|
| 587 |
+
"model.layers.48.self_attn.q_proj.bias": "model-00010-of-00018.safetensors",
|
| 588 |
+
"model.layers.48.self_attn.q_proj.weight": "model-00010-of-00018.safetensors",
|
| 589 |
+
"model.layers.48.self_attn.v_proj.bias": "model-00010-of-00018.safetensors",
|
| 590 |
+
"model.layers.48.self_attn.v_proj.weight": "model-00010-of-00018.safetensors",
|
| 591 |
+
"model.layers.49.input_layernorm.weight": "model-00010-of-00018.safetensors",
|
| 592 |
+
"model.layers.49.mlp.down_proj.weight": "model-00010-of-00018.safetensors",
|
| 593 |
+
"model.layers.49.mlp.gate_proj.weight": "model-00010-of-00018.safetensors",
|
| 594 |
+
"model.layers.49.mlp.up_proj.weight": "model-00010-of-00018.safetensors",
|
| 595 |
+
"model.layers.49.post_attention_layernorm.weight": "model-00010-of-00018.safetensors",
|
| 596 |
+
"model.layers.49.self_attn.k_proj.bias": "model-00010-of-00018.safetensors",
|
| 597 |
+
"model.layers.49.self_attn.k_proj.weight": "model-00010-of-00018.safetensors",
|
| 598 |
+
"model.layers.49.self_attn.o_proj.weight": "model-00010-of-00018.safetensors",
|
| 599 |
+
"model.layers.49.self_attn.q_proj.bias": "model-00010-of-00018.safetensors",
|
| 600 |
+
"model.layers.49.self_attn.q_proj.weight": "model-00010-of-00018.safetensors",
|
| 601 |
+
"model.layers.49.self_attn.v_proj.bias": "model-00010-of-00018.safetensors",
|
| 602 |
+
"model.layers.49.self_attn.v_proj.weight": "model-00010-of-00018.safetensors",
|
| 603 |
+
"model.layers.50.input_layernorm.weight": "model-00011-of-00018.safetensors",
|
| 604 |
+
"model.layers.50.mlp.down_proj.weight": "model-00011-of-00018.safetensors",
|
| 605 |
+
"model.layers.50.mlp.gate_proj.weight": "model-00011-of-00018.safetensors",
|
| 606 |
+
"model.layers.50.mlp.up_proj.weight": "model-00011-of-00018.safetensors",
|
| 607 |
+
"model.layers.50.post_attention_layernorm.weight": "model-00011-of-00018.safetensors",
|
| 608 |
+
"model.layers.50.self_attn.k_proj.bias": "model-00011-of-00018.safetensors",
|
| 609 |
+
"model.layers.50.self_attn.k_proj.weight": "model-00011-of-00018.safetensors",
|
| 610 |
+
"model.layers.50.self_attn.o_proj.weight": "model-00011-of-00018.safetensors",
|
| 611 |
+
"model.layers.50.self_attn.q_proj.bias": "model-00011-of-00018.safetensors",
|
| 612 |
+
"model.layers.50.self_attn.q_proj.weight": "model-00011-of-00018.safetensors",
|
| 613 |
+
"model.layers.50.self_attn.v_proj.bias": "model-00011-of-00018.safetensors",
|
| 614 |
+
"model.layers.50.self_attn.v_proj.weight": "model-00011-of-00018.safetensors",
|
| 615 |
+
"model.layers.51.input_layernorm.weight": "model-00011-of-00018.safetensors",
|
| 616 |
+
"model.layers.51.mlp.down_proj.weight": "model-00011-of-00018.safetensors",
|
| 617 |
+
"model.layers.51.mlp.gate_proj.weight": "model-00011-of-00018.safetensors",
|
| 618 |
+
"model.layers.51.mlp.up_proj.weight": "model-00011-of-00018.safetensors",
|
| 619 |
+
"model.layers.51.post_attention_layernorm.weight": "model-00011-of-00018.safetensors",
|
| 620 |
+
"model.layers.51.self_attn.k_proj.bias": "model-00011-of-00018.safetensors",
|
| 621 |
+
"model.layers.51.self_attn.k_proj.weight": "model-00011-of-00018.safetensors",
|
| 622 |
+
"model.layers.51.self_attn.o_proj.weight": "model-00011-of-00018.safetensors",
|
| 623 |
+
"model.layers.51.self_attn.q_proj.bias": "model-00011-of-00018.safetensors",
|
| 624 |
+
"model.layers.51.self_attn.q_proj.weight": "model-00011-of-00018.safetensors",
|
| 625 |
+
"model.layers.51.self_attn.v_proj.bias": "model-00011-of-00018.safetensors",
|
| 626 |
+
"model.layers.51.self_attn.v_proj.weight": "model-00011-of-00018.safetensors",
|
| 627 |
+
"model.layers.52.input_layernorm.weight": "model-00011-of-00018.safetensors",
|
| 628 |
+
"model.layers.52.mlp.down_proj.weight": "model-00011-of-00018.safetensors",
|
| 629 |
+
"model.layers.52.mlp.gate_proj.weight": "model-00011-of-00018.safetensors",
|
| 630 |
+
"model.layers.52.mlp.up_proj.weight": "model-00011-of-00018.safetensors",
|
| 631 |
+
"model.layers.52.post_attention_layernorm.weight": "model-00011-of-00018.safetensors",
|
| 632 |
+
"model.layers.52.self_attn.k_proj.bias": "model-00011-of-00018.safetensors",
|
| 633 |
+
"model.layers.52.self_attn.k_proj.weight": "model-00011-of-00018.safetensors",
|
| 634 |
+
"model.layers.52.self_attn.o_proj.weight": "model-00011-of-00018.safetensors",
|
| 635 |
+
"model.layers.52.self_attn.q_proj.bias": "model-00011-of-00018.safetensors",
|
| 636 |
+
"model.layers.52.self_attn.q_proj.weight": "model-00011-of-00018.safetensors",
|
| 637 |
+
"model.layers.52.self_attn.v_proj.bias": "model-00011-of-00018.safetensors",
|
| 638 |
+
"model.layers.52.self_attn.v_proj.weight": "model-00011-of-00018.safetensors",
|
| 639 |
+
"model.layers.53.input_layernorm.weight": "model-00011-of-00018.safetensors",
|
| 640 |
+
"model.layers.53.mlp.down_proj.weight": "model-00011-of-00018.safetensors",
|
| 641 |
+
"model.layers.53.mlp.gate_proj.weight": "model-00011-of-00018.safetensors",
|
| 642 |
+
"model.layers.53.mlp.up_proj.weight": "model-00011-of-00018.safetensors",
|
| 643 |
+
"model.layers.53.post_attention_layernorm.weight": "model-00011-of-00018.safetensors",
|
| 644 |
+
"model.layers.53.self_attn.k_proj.bias": "model-00011-of-00018.safetensors",
|
| 645 |
+
"model.layers.53.self_attn.k_proj.weight": "model-00011-of-00018.safetensors",
|
| 646 |
+
"model.layers.53.self_attn.o_proj.weight": "model-00011-of-00018.safetensors",
|
| 647 |
+
"model.layers.53.self_attn.q_proj.bias": "model-00011-of-00018.safetensors",
|
| 648 |
+
"model.layers.53.self_attn.q_proj.weight": "model-00011-of-00018.safetensors",
|
| 649 |
+
"model.layers.53.self_attn.v_proj.bias": "model-00011-of-00018.safetensors",
|
| 650 |
+
"model.layers.53.self_attn.v_proj.weight": "model-00011-of-00018.safetensors",
|
| 651 |
+
"model.layers.54.input_layernorm.weight": "model-00011-of-00018.safetensors",
|
| 652 |
+
"model.layers.54.mlp.down_proj.weight": "model-00011-of-00018.safetensors",
|
| 653 |
+
"model.layers.54.mlp.gate_proj.weight": "model-00011-of-00018.safetensors",
|
| 654 |
+
"model.layers.54.mlp.up_proj.weight": "model-00011-of-00018.safetensors",
|
| 655 |
+
"model.layers.54.post_attention_layernorm.weight": "model-00011-of-00018.safetensors",
|
| 656 |
+
"model.layers.54.self_attn.k_proj.bias": "model-00011-of-00018.safetensors",
|
| 657 |
+
"model.layers.54.self_attn.k_proj.weight": "model-00011-of-00018.safetensors",
|
| 658 |
+
"model.layers.54.self_attn.o_proj.weight": "model-00011-of-00018.safetensors",
|
| 659 |
+
"model.layers.54.self_attn.q_proj.bias": "model-00011-of-00018.safetensors",
|
| 660 |
+
"model.layers.54.self_attn.q_proj.weight": "model-00011-of-00018.safetensors",
|
| 661 |
+
"model.layers.54.self_attn.v_proj.bias": "model-00011-of-00018.safetensors",
|
| 662 |
+
"model.layers.54.self_attn.v_proj.weight": "model-00011-of-00018.safetensors",
|
| 663 |
+
"model.layers.55.input_layernorm.weight": "model-00012-of-00018.safetensors",
|
| 664 |
+
"model.layers.55.mlp.down_proj.weight": "model-00012-of-00018.safetensors",
|
| 665 |
+
"model.layers.55.mlp.gate_proj.weight": "model-00012-of-00018.safetensors",
|
| 666 |
+
"model.layers.55.mlp.up_proj.weight": "model-00012-of-00018.safetensors",
|
| 667 |
+
"model.layers.55.post_attention_layernorm.weight": "model-00012-of-00018.safetensors",
|
| 668 |
+
"model.layers.55.self_attn.k_proj.bias": "model-00012-of-00018.safetensors",
|
| 669 |
+
"model.layers.55.self_attn.k_proj.weight": "model-00012-of-00018.safetensors",
|
| 670 |
+
"model.layers.55.self_attn.o_proj.weight": "model-00012-of-00018.safetensors",
|
| 671 |
+
"model.layers.55.self_attn.q_proj.bias": "model-00012-of-00018.safetensors",
|
| 672 |
+
"model.layers.55.self_attn.q_proj.weight": "model-00012-of-00018.safetensors",
|
| 673 |
+
"model.layers.55.self_attn.v_proj.bias": "model-00012-of-00018.safetensors",
|
| 674 |
+
"model.layers.55.self_attn.v_proj.weight": "model-00012-of-00018.safetensors",
|
| 675 |
+
"model.layers.56.input_layernorm.weight": "model-00012-of-00018.safetensors",
|
| 676 |
+
"model.layers.56.mlp.down_proj.weight": "model-00012-of-00018.safetensors",
|
| 677 |
+
"model.layers.56.mlp.gate_proj.weight": "model-00012-of-00018.safetensors",
|
| 678 |
+
"model.layers.56.mlp.up_proj.weight": "model-00012-of-00018.safetensors",
|
| 679 |
+
"model.layers.56.post_attention_layernorm.weight": "model-00012-of-00018.safetensors",
|
| 680 |
+
"model.layers.56.self_attn.k_proj.bias": "model-00012-of-00018.safetensors",
|
| 681 |
+
"model.layers.56.self_attn.k_proj.weight": "model-00012-of-00018.safetensors",
|
| 682 |
+
"model.layers.56.self_attn.o_proj.weight": "model-00012-of-00018.safetensors",
|
| 683 |
+
"model.layers.56.self_attn.q_proj.bias": "model-00012-of-00018.safetensors",
|
| 684 |
+
"model.layers.56.self_attn.q_proj.weight": "model-00012-of-00018.safetensors",
|
| 685 |
+
"model.layers.56.self_attn.v_proj.bias": "model-00012-of-00018.safetensors",
|
| 686 |
+
"model.layers.56.self_attn.v_proj.weight": "model-00012-of-00018.safetensors",
|
| 687 |
+
"model.layers.57.input_layernorm.weight": "model-00012-of-00018.safetensors",
|
| 688 |
+
"model.layers.57.mlp.down_proj.weight": "model-00012-of-00018.safetensors",
|
| 689 |
+
"model.layers.57.mlp.gate_proj.weight": "model-00012-of-00018.safetensors",
|
| 690 |
+
"model.layers.57.mlp.up_proj.weight": "model-00012-of-00018.safetensors",
|
| 691 |
+
"model.layers.57.post_attention_layernorm.weight": "model-00012-of-00018.safetensors",
|
| 692 |
+
"model.layers.57.self_attn.k_proj.bias": "model-00012-of-00018.safetensors",
|
| 693 |
+
"model.layers.57.self_attn.k_proj.weight": "model-00012-of-00018.safetensors",
|
| 694 |
+
"model.layers.57.self_attn.o_proj.weight": "model-00012-of-00018.safetensors",
|
| 695 |
+
"model.layers.57.self_attn.q_proj.bias": "model-00012-of-00018.safetensors",
|
| 696 |
+
"model.layers.57.self_attn.q_proj.weight": "model-00012-of-00018.safetensors",
|
| 697 |
+
"model.layers.57.self_attn.v_proj.bias": "model-00012-of-00018.safetensors",
|
| 698 |
+
"model.layers.57.self_attn.v_proj.weight": "model-00012-of-00018.safetensors",
|
| 699 |
+
"model.layers.58.input_layernorm.weight": "model-00012-of-00018.safetensors",
|
| 700 |
+
"model.layers.58.mlp.down_proj.weight": "model-00012-of-00018.safetensors",
|
| 701 |
+
"model.layers.58.mlp.gate_proj.weight": "model-00012-of-00018.safetensors",
|
| 702 |
+
"model.layers.58.mlp.up_proj.weight": "model-00012-of-00018.safetensors",
|
| 703 |
+
"model.layers.58.post_attention_layernorm.weight": "model-00012-of-00018.safetensors",
|
| 704 |
+
"model.layers.58.self_attn.k_proj.bias": "model-00012-of-00018.safetensors",
|
| 705 |
+
"model.layers.58.self_attn.k_proj.weight": "model-00012-of-00018.safetensors",
|
| 706 |
+
"model.layers.58.self_attn.o_proj.weight": "model-00012-of-00018.safetensors",
|
| 707 |
+
"model.layers.58.self_attn.q_proj.bias": "model-00012-of-00018.safetensors",
|
| 708 |
+
"model.layers.58.self_attn.q_proj.weight": "model-00012-of-00018.safetensors",
|
| 709 |
+
"model.layers.58.self_attn.v_proj.bias": "model-00012-of-00018.safetensors",
|
| 710 |
+
"model.layers.58.self_attn.v_proj.weight": "model-00012-of-00018.safetensors",
|
| 711 |
+
"model.layers.59.input_layernorm.weight": "model-00012-of-00018.safetensors",
|
| 712 |
+
"model.layers.59.mlp.down_proj.weight": "model-00012-of-00018.safetensors",
|
| 713 |
+
"model.layers.59.mlp.gate_proj.weight": "model-00012-of-00018.safetensors",
|
| 714 |
+
"model.layers.59.mlp.up_proj.weight": "model-00012-of-00018.safetensors",
|
| 715 |
+
"model.layers.59.post_attention_layernorm.weight": "model-00012-of-00018.safetensors",
|
| 716 |
+
"model.layers.59.self_attn.k_proj.bias": "model-00012-of-00018.safetensors",
|
| 717 |
+
"model.layers.59.self_attn.k_proj.weight": "model-00012-of-00018.safetensors",
|
| 718 |
+
"model.layers.59.self_attn.o_proj.weight": "model-00012-of-00018.safetensors",
|
| 719 |
+
"model.layers.59.self_attn.q_proj.bias": "model-00012-of-00018.safetensors",
|
| 720 |
+
"model.layers.59.self_attn.q_proj.weight": "model-00012-of-00018.safetensors",
|
| 721 |
+
"model.layers.59.self_attn.v_proj.bias": "model-00012-of-00018.safetensors",
|
| 722 |
+
"model.layers.59.self_attn.v_proj.weight": "model-00012-of-00018.safetensors",
|
| 723 |
+
"model.layers.60.input_layernorm.weight": "model-00013-of-00018.safetensors",
|
| 724 |
+
"model.layers.60.mlp.down_proj.weight": "model-00013-of-00018.safetensors",
|
| 725 |
+
"model.layers.60.mlp.gate_proj.weight": "model-00013-of-00018.safetensors",
|
| 726 |
+
"model.layers.60.mlp.up_proj.weight": "model-00013-of-00018.safetensors",
|
| 727 |
+
"model.layers.60.post_attention_layernorm.weight": "model-00013-of-00018.safetensors",
|
| 728 |
+
"model.layers.60.self_attn.k_proj.bias": "model-00013-of-00018.safetensors",
|
| 729 |
+
"model.layers.60.self_attn.k_proj.weight": "model-00013-of-00018.safetensors",
|
| 730 |
+
"model.layers.60.self_attn.o_proj.weight": "model-00013-of-00018.safetensors",
|
| 731 |
+
"model.layers.60.self_attn.q_proj.bias": "model-00013-of-00018.safetensors",
|
| 732 |
+
"model.layers.60.self_attn.q_proj.weight": "model-00013-of-00018.safetensors",
|
| 733 |
+
"model.layers.60.self_attn.v_proj.bias": "model-00013-of-00018.safetensors",
|
| 734 |
+
"model.layers.60.self_attn.v_proj.weight": "model-00013-of-00018.safetensors",
|
| 735 |
+
"model.layers.61.input_layernorm.weight": "model-00013-of-00018.safetensors",
|
| 736 |
+
"model.layers.61.mlp.down_proj.weight": "model-00013-of-00018.safetensors",
|
| 737 |
+
"model.layers.61.mlp.gate_proj.weight": "model-00013-of-00018.safetensors",
|
| 738 |
+
"model.layers.61.mlp.up_proj.weight": "model-00013-of-00018.safetensors",
|
| 739 |
+
"model.layers.61.post_attention_layernorm.weight": "model-00013-of-00018.safetensors",
|
| 740 |
+
"model.layers.61.self_attn.k_proj.bias": "model-00013-of-00018.safetensors",
|
| 741 |
+
"model.layers.61.self_attn.k_proj.weight": "model-00013-of-00018.safetensors",
|
| 742 |
+
"model.layers.61.self_attn.o_proj.weight": "model-00013-of-00018.safetensors",
|
| 743 |
+
"model.layers.61.self_attn.q_proj.bias": "model-00013-of-00018.safetensors",
|
| 744 |
+
"model.layers.61.self_attn.q_proj.weight": "model-00013-of-00018.safetensors",
|
| 745 |
+
"model.layers.61.self_attn.v_proj.bias": "model-00013-of-00018.safetensors",
|
| 746 |
+
"model.layers.61.self_attn.v_proj.weight": "model-00013-of-00018.safetensors",
|
| 747 |
+
"model.layers.62.input_layernorm.weight": "model-00013-of-00018.safetensors",
|
| 748 |
+
"model.layers.62.mlp.down_proj.weight": "model-00013-of-00018.safetensors",
|
| 749 |
+
"model.layers.62.mlp.gate_proj.weight": "model-00013-of-00018.safetensors",
|
| 750 |
+
"model.layers.62.mlp.up_proj.weight": "model-00013-of-00018.safetensors",
|
| 751 |
+
"model.layers.62.post_attention_layernorm.weight": "model-00013-of-00018.safetensors",
|
| 752 |
+
"model.layers.62.self_attn.k_proj.bias": "model-00013-of-00018.safetensors",
|
| 753 |
+
"model.layers.62.self_attn.k_proj.weight": "model-00013-of-00018.safetensors",
|
| 754 |
+
"model.layers.62.self_attn.o_proj.weight": "model-00013-of-00018.safetensors",
|
| 755 |
+
"model.layers.62.self_attn.q_proj.bias": "model-00013-of-00018.safetensors",
|
| 756 |
+
"model.layers.62.self_attn.q_proj.weight": "model-00013-of-00018.safetensors",
|
| 757 |
+
"model.layers.62.self_attn.v_proj.bias": "model-00013-of-00018.safetensors",
|
| 758 |
+
"model.layers.62.self_attn.v_proj.weight": "model-00013-of-00018.safetensors",
|
| 759 |
+
"model.layers.63.input_layernorm.weight": "model-00013-of-00018.safetensors",
|
| 760 |
+
"model.layers.63.mlp.down_proj.weight": "model-00013-of-00018.safetensors",
|
| 761 |
+
"model.layers.63.mlp.gate_proj.weight": "model-00013-of-00018.safetensors",
|
| 762 |
+
"model.layers.63.mlp.up_proj.weight": "model-00013-of-00018.safetensors",
|
| 763 |
+
"model.layers.63.post_attention_layernorm.weight": "model-00013-of-00018.safetensors",
|
| 764 |
+
"model.layers.63.self_attn.k_proj.bias": "model-00013-of-00018.safetensors",
|
| 765 |
+
"model.layers.63.self_attn.k_proj.weight": "model-00013-of-00018.safetensors",
|
| 766 |
+
"model.layers.63.self_attn.o_proj.weight": "model-00013-of-00018.safetensors",
|
| 767 |
+
"model.layers.63.self_attn.q_proj.bias": "model-00013-of-00018.safetensors",
|
| 768 |
+
"model.layers.63.self_attn.q_proj.weight": "model-00013-of-00018.safetensors",
|
| 769 |
+
"model.layers.63.self_attn.v_proj.bias": "model-00013-of-00018.safetensors",
|
| 770 |
+
"model.layers.63.self_attn.v_proj.weight": "model-00013-of-00018.safetensors",
|
| 771 |
+
"model.layers.64.input_layernorm.weight": "model-00013-of-00018.safetensors",
|
| 772 |
+
"model.layers.64.mlp.down_proj.weight": "model-00013-of-00018.safetensors",
|
| 773 |
+
"model.layers.64.mlp.gate_proj.weight": "model-00013-of-00018.safetensors",
|
| 774 |
+
"model.layers.64.mlp.up_proj.weight": "model-00013-of-00018.safetensors",
|
| 775 |
+
"model.layers.64.post_attention_layernorm.weight": "model-00013-of-00018.safetensors",
|
| 776 |
+
"model.layers.64.self_attn.k_proj.bias": "model-00013-of-00018.safetensors",
|
| 777 |
+
"model.layers.64.self_attn.k_proj.weight": "model-00013-of-00018.safetensors",
|
| 778 |
+
"model.layers.64.self_attn.o_proj.weight": "model-00013-of-00018.safetensors",
|
| 779 |
+
"model.layers.64.self_attn.q_proj.bias": "model-00013-of-00018.safetensors",
|
| 780 |
+
"model.layers.64.self_attn.q_proj.weight": "model-00013-of-00018.safetensors",
|
| 781 |
+
"model.layers.64.self_attn.v_proj.bias": "model-00013-of-00018.safetensors",
|
| 782 |
+
"model.layers.64.self_attn.v_proj.weight": "model-00013-of-00018.safetensors",
|
| 783 |
+
"model.layers.65.input_layernorm.weight": "model-00014-of-00018.safetensors",
|
| 784 |
+
"model.layers.65.mlp.down_proj.weight": "model-00014-of-00018.safetensors",
|
| 785 |
+
"model.layers.65.mlp.gate_proj.weight": "model-00014-of-00018.safetensors",
|
| 786 |
+
"model.layers.65.mlp.up_proj.weight": "model-00014-of-00018.safetensors",
|
| 787 |
+
"model.layers.65.post_attention_layernorm.weight": "model-00014-of-00018.safetensors",
|
| 788 |
+
"model.layers.65.self_attn.k_proj.bias": "model-00014-of-00018.safetensors",
|
| 789 |
+
"model.layers.65.self_attn.k_proj.weight": "model-00014-of-00018.safetensors",
|
| 790 |
+
"model.layers.65.self_attn.o_proj.weight": "model-00014-of-00018.safetensors",
|
| 791 |
+
"model.layers.65.self_attn.q_proj.bias": "model-00014-of-00018.safetensors",
|
| 792 |
+
"model.layers.65.self_attn.q_proj.weight": "model-00014-of-00018.safetensors",
|
| 793 |
+
"model.layers.65.self_attn.v_proj.bias": "model-00014-of-00018.safetensors",
|
| 794 |
+
"model.layers.65.self_attn.v_proj.weight": "model-00014-of-00018.safetensors",
|
| 795 |
+
"model.layers.66.input_layernorm.weight": "model-00014-of-00018.safetensors",
|
| 796 |
+
"model.layers.66.mlp.down_proj.weight": "model-00014-of-00018.safetensors",
|
| 797 |
+
"model.layers.66.mlp.gate_proj.weight": "model-00014-of-00018.safetensors",
|
| 798 |
+
"model.layers.66.mlp.up_proj.weight": "model-00014-of-00018.safetensors",
|
| 799 |
+
"model.layers.66.post_attention_layernorm.weight": "model-00014-of-00018.safetensors",
|
| 800 |
+
"model.layers.66.self_attn.k_proj.bias": "model-00014-of-00018.safetensors",
|
| 801 |
+
"model.layers.66.self_attn.k_proj.weight": "model-00014-of-00018.safetensors",
|
| 802 |
+
"model.layers.66.self_attn.o_proj.weight": "model-00014-of-00018.safetensors",
|
| 803 |
+
"model.layers.66.self_attn.q_proj.bias": "model-00014-of-00018.safetensors",
|
| 804 |
+
"model.layers.66.self_attn.q_proj.weight": "model-00014-of-00018.safetensors",
|
| 805 |
+
"model.layers.66.self_attn.v_proj.bias": "model-00014-of-00018.safetensors",
|
| 806 |
+
"model.layers.66.self_attn.v_proj.weight": "model-00014-of-00018.safetensors",
|
| 807 |
+
"model.layers.67.input_layernorm.weight": "model-00014-of-00018.safetensors",
|
| 808 |
+
"model.layers.67.mlp.down_proj.weight": "model-00014-of-00018.safetensors",
|
| 809 |
+
"model.layers.67.mlp.gate_proj.weight": "model-00014-of-00018.safetensors",
|
| 810 |
+
"model.layers.67.mlp.up_proj.weight": "model-00014-of-00018.safetensors",
|
| 811 |
+
"model.layers.67.post_attention_layernorm.weight": "model-00014-of-00018.safetensors",
|
| 812 |
+
"model.layers.67.self_attn.k_proj.bias": "model-00014-of-00018.safetensors",
|
| 813 |
+
"model.layers.67.self_attn.k_proj.weight": "model-00014-of-00018.safetensors",
|
| 814 |
+
"model.layers.67.self_attn.o_proj.weight": "model-00014-of-00018.safetensors",
|
| 815 |
+
"model.layers.67.self_attn.q_proj.bias": "model-00014-of-00018.safetensors",
|
| 816 |
+
"model.layers.67.self_attn.q_proj.weight": "model-00014-of-00018.safetensors",
|
| 817 |
+
"model.layers.67.self_attn.v_proj.bias": "model-00014-of-00018.safetensors",
|
| 818 |
+
"model.layers.67.self_attn.v_proj.weight": "model-00014-of-00018.safetensors",
|
| 819 |
+
"model.layers.68.input_layernorm.weight": "model-00014-of-00018.safetensors",
|
| 820 |
+
"model.layers.68.mlp.down_proj.weight": "model-00014-of-00018.safetensors",
|
| 821 |
+
"model.layers.68.mlp.gate_proj.weight": "model-00014-of-00018.safetensors",
|
| 822 |
+
"model.layers.68.mlp.up_proj.weight": "model-00014-of-00018.safetensors",
|
| 823 |
+
"model.layers.68.post_attention_layernorm.weight": "model-00014-of-00018.safetensors",
|
| 824 |
+
"model.layers.68.self_attn.k_proj.bias": "model-00014-of-00018.safetensors",
|
| 825 |
+
"model.layers.68.self_attn.k_proj.weight": "model-00014-of-00018.safetensors",
|
| 826 |
+
"model.layers.68.self_attn.o_proj.weight": "model-00014-of-00018.safetensors",
|
| 827 |
+
"model.layers.68.self_attn.q_proj.bias": "model-00014-of-00018.safetensors",
|
| 828 |
+
"model.layers.68.self_attn.q_proj.weight": "model-00014-of-00018.safetensors",
|
| 829 |
+
"model.layers.68.self_attn.v_proj.bias": "model-00014-of-00018.safetensors",
|
| 830 |
+
"model.layers.68.self_attn.v_proj.weight": "model-00014-of-00018.safetensors",
|
| 831 |
+
"model.layers.69.input_layernorm.weight": "model-00014-of-00018.safetensors",
|
| 832 |
+
"model.layers.69.mlp.down_proj.weight": "model-00014-of-00018.safetensors",
|
| 833 |
+
"model.layers.69.mlp.gate_proj.weight": "model-00014-of-00018.safetensors",
|
| 834 |
+
"model.layers.69.mlp.up_proj.weight": "model-00014-of-00018.safetensors",
|
| 835 |
+
"model.layers.69.post_attention_layernorm.weight": "model-00014-of-00018.safetensors",
|
| 836 |
+
"model.layers.69.self_attn.k_proj.bias": "model-00014-of-00018.safetensors",
|
| 837 |
+
"model.layers.69.self_attn.k_proj.weight": "model-00014-of-00018.safetensors",
|
| 838 |
+
"model.layers.69.self_attn.o_proj.weight": "model-00014-of-00018.safetensors",
|
| 839 |
+
"model.layers.69.self_attn.q_proj.bias": "model-00014-of-00018.safetensors",
|
| 840 |
+
"model.layers.69.self_attn.q_proj.weight": "model-00014-of-00018.safetensors",
|
| 841 |
+
"model.layers.69.self_attn.v_proj.bias": "model-00014-of-00018.safetensors",
|
| 842 |
+
"model.layers.69.self_attn.v_proj.weight": "model-00014-of-00018.safetensors",
|
| 843 |
+
"model.layers.70.input_layernorm.weight": "model-00015-of-00018.safetensors",
|
| 844 |
+
"model.layers.70.mlp.down_proj.weight": "model-00015-of-00018.safetensors",
|
| 845 |
+
"model.layers.70.mlp.gate_proj.weight": "model-00015-of-00018.safetensors",
|
| 846 |
+
"model.layers.70.mlp.up_proj.weight": "model-00015-of-00018.safetensors",
|
| 847 |
+
"model.layers.70.post_attention_layernorm.weight": "model-00015-of-00018.safetensors",
|
| 848 |
+
"model.layers.70.self_attn.k_proj.bias": "model-00015-of-00018.safetensors",
|
| 849 |
+
"model.layers.70.self_attn.k_proj.weight": "model-00015-of-00018.safetensors",
|
| 850 |
+
"model.layers.70.self_attn.o_proj.weight": "model-00015-of-00018.safetensors",
|
| 851 |
+
"model.layers.70.self_attn.q_proj.bias": "model-00015-of-00018.safetensors",
|
| 852 |
+
"model.layers.70.self_attn.q_proj.weight": "model-00015-of-00018.safetensors",
|
| 853 |
+
"model.layers.70.self_attn.v_proj.bias": "model-00015-of-00018.safetensors",
|
| 854 |
+
"model.layers.70.self_attn.v_proj.weight": "model-00015-of-00018.safetensors",
|
| 855 |
+
"model.layers.71.input_layernorm.weight": "model-00015-of-00018.safetensors",
|
| 856 |
+
"model.layers.71.mlp.down_proj.weight": "model-00015-of-00018.safetensors",
|
| 857 |
+
"model.layers.71.mlp.gate_proj.weight": "model-00015-of-00018.safetensors",
|
| 858 |
+
"model.layers.71.mlp.up_proj.weight": "model-00015-of-00018.safetensors",
|
| 859 |
+
"model.layers.71.post_attention_layernorm.weight": "model-00015-of-00018.safetensors",
|
| 860 |
+
"model.layers.71.self_attn.k_proj.bias": "model-00015-of-00018.safetensors",
|
| 861 |
+
"model.layers.71.self_attn.k_proj.weight": "model-00015-of-00018.safetensors",
|
| 862 |
+
"model.layers.71.self_attn.o_proj.weight": "model-00015-of-00018.safetensors",
|
| 863 |
+
"model.layers.71.self_attn.q_proj.bias": "model-00015-of-00018.safetensors",
|
| 864 |
+
"model.layers.71.self_attn.q_proj.weight": "model-00015-of-00018.safetensors",
|
| 865 |
+
"model.layers.71.self_attn.v_proj.bias": "model-00015-of-00018.safetensors",
|
| 866 |
+
"model.layers.71.self_attn.v_proj.weight": "model-00015-of-00018.safetensors",
|
| 867 |
+
"model.layers.72.input_layernorm.weight": "model-00015-of-00018.safetensors",
|
| 868 |
+
"model.layers.72.mlp.down_proj.weight": "model-00015-of-00018.safetensors",
|
| 869 |
+
"model.layers.72.mlp.gate_proj.weight": "model-00015-of-00018.safetensors",
|
| 870 |
+
"model.layers.72.mlp.up_proj.weight": "model-00015-of-00018.safetensors",
|
| 871 |
+
"model.layers.72.post_attention_layernorm.weight": "model-00015-of-00018.safetensors",
|
| 872 |
+
"model.layers.72.self_attn.k_proj.bias": "model-00015-of-00018.safetensors",
|
| 873 |
+
"model.layers.72.self_attn.k_proj.weight": "model-00015-of-00018.safetensors",
|
| 874 |
+
"model.layers.72.self_attn.o_proj.weight": "model-00015-of-00018.safetensors",
|
| 875 |
+
"model.layers.72.self_attn.q_proj.bias": "model-00015-of-00018.safetensors",
|
| 876 |
+
"model.layers.72.self_attn.q_proj.weight": "model-00015-of-00018.safetensors",
|
| 877 |
+
"model.layers.72.self_attn.v_proj.bias": "model-00015-of-00018.safetensors",
|
| 878 |
+
"model.layers.72.self_attn.v_proj.weight": "model-00015-of-00018.safetensors",
|
| 879 |
+
"model.layers.73.input_layernorm.weight": "model-00015-of-00018.safetensors",
|
| 880 |
+
"model.layers.73.mlp.down_proj.weight": "model-00015-of-00018.safetensors",
|
| 881 |
+
"model.layers.73.mlp.gate_proj.weight": "model-00015-of-00018.safetensors",
|
| 882 |
+
"model.layers.73.mlp.up_proj.weight": "model-00015-of-00018.safetensors",
|
| 883 |
+
"model.layers.73.post_attention_layernorm.weight": "model-00015-of-00018.safetensors",
|
| 884 |
+
"model.layers.73.self_attn.k_proj.bias": "model-00015-of-00018.safetensors",
|
| 885 |
+
"model.layers.73.self_attn.k_proj.weight": "model-00015-of-00018.safetensors",
|
| 886 |
+
"model.layers.73.self_attn.o_proj.weight": "model-00015-of-00018.safetensors",
|
| 887 |
+
"model.layers.73.self_attn.q_proj.bias": "model-00015-of-00018.safetensors",
|
| 888 |
+
"model.layers.73.self_attn.q_proj.weight": "model-00015-of-00018.safetensors",
|
| 889 |
+
"model.layers.73.self_attn.v_proj.bias": "model-00015-of-00018.safetensors",
|
| 890 |
+
"model.layers.73.self_attn.v_proj.weight": "model-00015-of-00018.safetensors",
|
| 891 |
+
"model.layers.74.input_layernorm.weight": "model-00015-of-00018.safetensors",
|
| 892 |
+
"model.layers.74.mlp.down_proj.weight": "model-00015-of-00018.safetensors",
|
| 893 |
+
"model.layers.74.mlp.gate_proj.weight": "model-00015-of-00018.safetensors",
|
| 894 |
+
"model.layers.74.mlp.up_proj.weight": "model-00015-of-00018.safetensors",
|
| 895 |
+
"model.layers.74.post_attention_layernorm.weight": "model-00015-of-00018.safetensors",
|
| 896 |
+
"model.layers.74.self_attn.k_proj.bias": "model-00015-of-00018.safetensors",
|
| 897 |
+
"model.layers.74.self_attn.k_proj.weight": "model-00015-of-00018.safetensors",
|
| 898 |
+
"model.layers.74.self_attn.o_proj.weight": "model-00015-of-00018.safetensors",
|
| 899 |
+
"model.layers.74.self_attn.q_proj.bias": "model-00015-of-00018.safetensors",
|
| 900 |
+
"model.layers.74.self_attn.q_proj.weight": "model-00015-of-00018.safetensors",
|
| 901 |
+
"model.layers.74.self_attn.v_proj.bias": "model-00015-of-00018.safetensors",
|
| 902 |
+
"model.layers.74.self_attn.v_proj.weight": "model-00015-of-00018.safetensors",
|
| 903 |
+
"model.layers.75.input_layernorm.weight": "model-00016-of-00018.safetensors",
|
| 904 |
+
"model.layers.75.mlp.down_proj.weight": "model-00016-of-00018.safetensors",
|
| 905 |
+
"model.layers.75.mlp.gate_proj.weight": "model-00016-of-00018.safetensors",
|
| 906 |
+
"model.layers.75.mlp.up_proj.weight": "model-00016-of-00018.safetensors",
|
| 907 |
+
"model.layers.75.post_attention_layernorm.weight": "model-00016-of-00018.safetensors",
|
| 908 |
+
"model.layers.75.self_attn.k_proj.bias": "model-00016-of-00018.safetensors",
|
| 909 |
+
"model.layers.75.self_attn.k_proj.weight": "model-00016-of-00018.safetensors",
|
| 910 |
+
"model.layers.75.self_attn.o_proj.weight": "model-00016-of-00018.safetensors",
|
| 911 |
+
"model.layers.75.self_attn.q_proj.bias": "model-00016-of-00018.safetensors",
|
| 912 |
+
"model.layers.75.self_attn.q_proj.weight": "model-00016-of-00018.safetensors",
|
| 913 |
+
"model.layers.75.self_attn.v_proj.bias": "model-00016-of-00018.safetensors",
|
| 914 |
+
"model.layers.75.self_attn.v_proj.weight": "model-00016-of-00018.safetensors",
|
| 915 |
+
"model.layers.76.input_layernorm.weight": "model-00016-of-00018.safetensors",
|
| 916 |
+
"model.layers.76.mlp.down_proj.weight": "model-00016-of-00018.safetensors",
|
| 917 |
+
"model.layers.76.mlp.gate_proj.weight": "model-00016-of-00018.safetensors",
|
| 918 |
+
"model.layers.76.mlp.up_proj.weight": "model-00016-of-00018.safetensors",
|
| 919 |
+
"model.layers.76.post_attention_layernorm.weight": "model-00016-of-00018.safetensors",
|
| 920 |
+
"model.layers.76.self_attn.k_proj.bias": "model-00016-of-00018.safetensors",
|
| 921 |
+
"model.layers.76.self_attn.k_proj.weight": "model-00016-of-00018.safetensors",
|
| 922 |
+
"model.layers.76.self_attn.o_proj.weight": "model-00016-of-00018.safetensors",
|
| 923 |
+
"model.layers.76.self_attn.q_proj.bias": "model-00016-of-00018.safetensors",
|
| 924 |
+
"model.layers.76.self_attn.q_proj.weight": "model-00016-of-00018.safetensors",
|
| 925 |
+
"model.layers.76.self_attn.v_proj.bias": "model-00016-of-00018.safetensors",
|
| 926 |
+
"model.layers.76.self_attn.v_proj.weight": "model-00016-of-00018.safetensors",
|
| 927 |
+
"model.layers.77.input_layernorm.weight": "model-00016-of-00018.safetensors",
|
| 928 |
+
"model.layers.77.mlp.down_proj.weight": "model-00016-of-00018.safetensors",
|
| 929 |
+
"model.layers.77.mlp.gate_proj.weight": "model-00016-of-00018.safetensors",
|
| 930 |
+
"model.layers.77.mlp.up_proj.weight": "model-00016-of-00018.safetensors",
|
| 931 |
+
"model.layers.77.post_attention_layernorm.weight": "model-00016-of-00018.safetensors",
|
| 932 |
+
"model.layers.77.self_attn.k_proj.bias": "model-00016-of-00018.safetensors",
|
| 933 |
+
"model.layers.77.self_attn.k_proj.weight": "model-00016-of-00018.safetensors",
|
| 934 |
+
"model.layers.77.self_attn.o_proj.weight": "model-00016-of-00018.safetensors",
|
| 935 |
+
"model.layers.77.self_attn.q_proj.bias": "model-00016-of-00018.safetensors",
|
| 936 |
+
"model.layers.77.self_attn.q_proj.weight": "model-00016-of-00018.safetensors",
|
| 937 |
+
"model.layers.77.self_attn.v_proj.bias": "model-00016-of-00018.safetensors",
|
| 938 |
+
"model.layers.77.self_attn.v_proj.weight": "model-00016-of-00018.safetensors",
|
| 939 |
+
"model.layers.78.input_layernorm.weight": "model-00016-of-00018.safetensors",
|
| 940 |
+
"model.layers.78.mlp.down_proj.weight": "model-00016-of-00018.safetensors",
|
| 941 |
+
"model.layers.78.mlp.gate_proj.weight": "model-00016-of-00018.safetensors",
|
| 942 |
+
"model.layers.78.mlp.up_proj.weight": "model-00016-of-00018.safetensors",
|
| 943 |
+
"model.layers.78.post_attention_layernorm.weight": "model-00016-of-00018.safetensors",
|
| 944 |
+
"model.layers.78.self_attn.k_proj.bias": "model-00016-of-00018.safetensors",
|
| 945 |
+
"model.layers.78.self_attn.k_proj.weight": "model-00016-of-00018.safetensors",
|
| 946 |
+
"model.layers.78.self_attn.o_proj.weight": "model-00016-of-00018.safetensors",
|
| 947 |
+
"model.layers.78.self_attn.q_proj.bias": "model-00016-of-00018.safetensors",
|
| 948 |
+
"model.layers.78.self_attn.q_proj.weight": "model-00016-of-00018.safetensors",
|
| 949 |
+
"model.layers.78.self_attn.v_proj.bias": "model-00016-of-00018.safetensors",
|
| 950 |
+
"model.layers.78.self_attn.v_proj.weight": "model-00016-of-00018.safetensors",
|
| 951 |
+
"model.layers.79.input_layernorm.weight": "model-00016-of-00018.safetensors",
|
| 952 |
+
"model.layers.79.mlp.down_proj.weight": "model-00016-of-00018.safetensors",
|
| 953 |
+
"model.layers.79.mlp.gate_proj.weight": "model-00016-of-00018.safetensors",
|
| 954 |
+
"model.layers.79.mlp.up_proj.weight": "model-00016-of-00018.safetensors",
|
| 955 |
+
"model.layers.79.post_attention_layernorm.weight": "model-00016-of-00018.safetensors",
|
| 956 |
+
"model.layers.79.self_attn.k_proj.bias": "model-00016-of-00018.safetensors",
|
| 957 |
+
"model.layers.79.self_attn.k_proj.weight": "model-00016-of-00018.safetensors",
|
| 958 |
+
"model.layers.79.self_attn.o_proj.weight": "model-00016-of-00018.safetensors",
|
| 959 |
+
"model.layers.79.self_attn.q_proj.bias": "model-00016-of-00018.safetensors",
|
| 960 |
+
"model.layers.79.self_attn.q_proj.weight": "model-00016-of-00018.safetensors",
|
| 961 |
+
"model.layers.79.self_attn.v_proj.bias": "model-00016-of-00018.safetensors",
|
| 962 |
+
"model.layers.79.self_attn.v_proj.weight": "model-00016-of-00018.safetensors",
|
| 963 |
+
"model.layers.80.input_layernorm.weight": "model-00017-of-00018.safetensors",
|
| 964 |
+
"model.layers.80.mlp.down_proj.weight": "model-00017-of-00018.safetensors",
|
| 965 |
+
"model.layers.80.mlp.gate_proj.weight": "model-00017-of-00018.safetensors",
|
| 966 |
+
"model.layers.80.mlp.up_proj.weight": "model-00017-of-00018.safetensors",
|
| 967 |
+
"model.layers.80.post_attention_layernorm.weight": "model-00017-of-00018.safetensors",
|
| 968 |
+
"model.layers.80.self_attn.k_proj.bias": "model-00017-of-00018.safetensors",
|
| 969 |
+
"model.layers.80.self_attn.k_proj.weight": "model-00017-of-00018.safetensors",
|
| 970 |
+
"model.layers.80.self_attn.o_proj.weight": "model-00017-of-00018.safetensors",
|
| 971 |
+
"model.layers.80.self_attn.q_proj.bias": "model-00017-of-00018.safetensors",
|
| 972 |
+
"model.layers.80.self_attn.q_proj.weight": "model-00017-of-00018.safetensors",
|
| 973 |
+
"model.layers.80.self_attn.v_proj.bias": "model-00017-of-00018.safetensors",
|
| 974 |
+
"model.layers.80.self_attn.v_proj.weight": "model-00017-of-00018.safetensors",
|
| 975 |
+
"model.layers.81.input_layernorm.weight": "model-00017-of-00018.safetensors",
|
| 976 |
+
"model.layers.81.mlp.down_proj.weight": "model-00017-of-00018.safetensors",
|
| 977 |
+
"model.layers.81.mlp.gate_proj.weight": "model-00017-of-00018.safetensors",
|
| 978 |
+
"model.layers.81.mlp.up_proj.weight": "model-00017-of-00018.safetensors",
|
| 979 |
+
"model.layers.81.post_attention_layernorm.weight": "model-00017-of-00018.safetensors",
|
| 980 |
+
"model.layers.81.self_attn.k_proj.bias": "model-00017-of-00018.safetensors",
|
| 981 |
+
"model.layers.81.self_attn.k_proj.weight": "model-00017-of-00018.safetensors",
|
| 982 |
+
"model.layers.81.self_attn.o_proj.weight": "model-00017-of-00018.safetensors",
|
| 983 |
+
"model.layers.81.self_attn.q_proj.bias": "model-00017-of-00018.safetensors",
|
| 984 |
+
"model.layers.81.self_attn.q_proj.weight": "model-00017-of-00018.safetensors",
|
| 985 |
+
"model.layers.81.self_attn.v_proj.bias": "model-00017-of-00018.safetensors",
|
| 986 |
+
"model.layers.81.self_attn.v_proj.weight": "model-00017-of-00018.safetensors",
|
| 987 |
+
"model.layers.82.input_layernorm.weight": "model-00017-of-00018.safetensors",
|
| 988 |
+
"model.layers.82.mlp.down_proj.weight": "model-00017-of-00018.safetensors",
|
| 989 |
+
"model.layers.82.mlp.gate_proj.weight": "model-00017-of-00018.safetensors",
|
| 990 |
+
"model.layers.82.mlp.up_proj.weight": "model-00017-of-00018.safetensors",
|
| 991 |
+
"model.layers.82.post_attention_layernorm.weight": "model-00017-of-00018.safetensors",
|
| 992 |
+
"model.layers.82.self_attn.k_proj.bias": "model-00017-of-00018.safetensors",
|
| 993 |
+
"model.layers.82.self_attn.k_proj.weight": "model-00017-of-00018.safetensors",
|
| 994 |
+
"model.layers.82.self_attn.o_proj.weight": "model-00017-of-00018.safetensors",
|
| 995 |
+
"model.layers.82.self_attn.q_proj.bias": "model-00017-of-00018.safetensors",
|
| 996 |
+
"model.layers.82.self_attn.q_proj.weight": "model-00017-of-00018.safetensors",
|
| 997 |
+
"model.layers.82.self_attn.v_proj.bias": "model-00017-of-00018.safetensors",
|
| 998 |
+
"model.layers.82.self_attn.v_proj.weight": "model-00017-of-00018.safetensors",
|
| 999 |
+
"model.layers.83.input_layernorm.weight": "model-00017-of-00018.safetensors",
|
| 1000 |
+
"model.layers.83.mlp.down_proj.weight": "model-00017-of-00018.safetensors",
|
| 1001 |
+
"model.layers.83.mlp.gate_proj.weight": "model-00017-of-00018.safetensors",
|
| 1002 |
+
"model.layers.83.mlp.up_proj.weight": "model-00017-of-00018.safetensors",
|
| 1003 |
+
"model.layers.83.post_attention_layernorm.weight": "model-00017-of-00018.safetensors",
|
| 1004 |
+
"model.layers.83.self_attn.k_proj.bias": "model-00017-of-00018.safetensors",
|
| 1005 |
+
"model.layers.83.self_attn.k_proj.weight": "model-00017-of-00018.safetensors",
|
| 1006 |
+
"model.layers.83.self_attn.o_proj.weight": "model-00017-of-00018.safetensors",
|
| 1007 |
+
"model.layers.83.self_attn.q_proj.bias": "model-00017-of-00018.safetensors",
|
| 1008 |
+
"model.layers.83.self_attn.q_proj.weight": "model-00017-of-00018.safetensors",
|
| 1009 |
+
"model.layers.83.self_attn.v_proj.bias": "model-00017-of-00018.safetensors",
|
| 1010 |
+
"model.layers.83.self_attn.v_proj.weight": "model-00017-of-00018.safetensors",
|
| 1011 |
+
"model.layers.84.input_layernorm.weight": "model-00017-of-00018.safetensors",
|
| 1012 |
+
"model.layers.84.mlp.down_proj.weight": "model-00017-of-00018.safetensors",
|
| 1013 |
+
"model.layers.84.mlp.gate_proj.weight": "model-00017-of-00018.safetensors",
|
| 1014 |
+
"model.layers.84.mlp.up_proj.weight": "model-00017-of-00018.safetensors",
|
| 1015 |
+
"model.layers.84.post_attention_layernorm.weight": "model-00017-of-00018.safetensors",
|
| 1016 |
+
"model.layers.84.self_attn.k_proj.bias": "model-00017-of-00018.safetensors",
|
| 1017 |
+
"model.layers.84.self_attn.k_proj.weight": "model-00017-of-00018.safetensors",
|
| 1018 |
+
"model.layers.84.self_attn.o_proj.weight": "model-00017-of-00018.safetensors",
|
| 1019 |
+
"model.layers.84.self_attn.q_proj.bias": "model-00017-of-00018.safetensors",
|
| 1020 |
+
"model.layers.84.self_attn.q_proj.weight": "model-00017-of-00018.safetensors",
|
| 1021 |
+
"model.layers.84.self_attn.v_proj.bias": "model-00017-of-00018.safetensors",
|
| 1022 |
+
"model.layers.84.self_attn.v_proj.weight": "model-00017-of-00018.safetensors",
|
| 1023 |
+
"model.layers.85.input_layernorm.weight": "model-00018-of-00018.safetensors",
|
| 1024 |
+
"model.layers.85.mlp.down_proj.weight": "model-00018-of-00018.safetensors",
|
| 1025 |
+
"model.layers.85.mlp.gate_proj.weight": "model-00018-of-00018.safetensors",
|
| 1026 |
+
"model.layers.85.mlp.up_proj.weight": "model-00018-of-00018.safetensors",
|
| 1027 |
+
"model.layers.85.post_attention_layernorm.weight": "model-00018-of-00018.safetensors",
|
| 1028 |
+
"model.layers.85.self_attn.k_proj.bias": "model-00018-of-00018.safetensors",
|
| 1029 |
+
"model.layers.85.self_attn.k_proj.weight": "model-00018-of-00018.safetensors",
|
| 1030 |
+
"model.layers.85.self_attn.o_proj.weight": "model-00018-of-00018.safetensors",
|
| 1031 |
+
"model.layers.85.self_attn.q_proj.bias": "model-00018-of-00018.safetensors",
|
| 1032 |
+
"model.layers.85.self_attn.q_proj.weight": "model-00018-of-00018.safetensors",
|
| 1033 |
+
"model.layers.85.self_attn.v_proj.bias": "model-00018-of-00018.safetensors",
|
| 1034 |
+
"model.layers.85.self_attn.v_proj.weight": "model-00018-of-00018.safetensors",
|
| 1035 |
+
"lm_head.weight": "model-00018-of-00018.safetensors",
|
| 1036 |
+
"model.embed_tokens.weight": "model-00018-of-00018.safetensors",
|
| 1037 |
+
"model.norm.weight": "model-00018-of-00018.safetensors"
|
| 1038 |
+
},
|
| 1039 |
+
"metadata": {
|
| 1040 |
+
"total_size": 145398710272
|
| 1041 |
+
}
|
| 1042 |
+
}
|
output-00008-of-00008.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:061e1a703e7f3ebb439c0df50322281b8b3901c63b1c362ee9b01c03e41f3098
|
| 3 |
+
size 980252768
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"eos_token": {
|
| 7 |
+
"content": "<|im_end|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"pad_token": {
|
| 14 |
+
"content": "<|endoftext|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
}
|
| 20 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
"additional_special_tokens": [
|
| 30 |
+
"<|im_start|>",
|
| 31 |
+
"<|im_end|>"
|
| 32 |
+
],
|
| 33 |
+
"bos_token": null,
|
| 34 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 35 |
+
"clean_up_tokenization_spaces": false,
|
| 36 |
+
"eos_token": "<|im_end|>",
|
| 37 |
+
"errors": "replace",
|
| 38 |
+
"model_max_length": 131072,
|
| 39 |
+
"pad_token": "<|endoftext|>",
|
| 40 |
+
"split_special_tokens": false,
|
| 41 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 42 |
+
"unk_token": null
|
| 43 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|