初始化项目，由ModelHub XC社区提供模型
Model: pankajmathur/model_101 Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
344
README.md
Normal file
344
README.md
Normal file
@@ -0,0 +1,344 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
license: llama2
|
||||
library_name: transformers
|
||||
datasets:
|
||||
- pankajmathur/orca_mini_v1_dataset
|
||||
- pankajmathur/lima_unchained_v1
|
||||
- pankajmathur/WizardLM_Orca
|
||||
- pankajmathur/alpaca_orca
|
||||
- pankajmathur/dolly-v2_orca
|
||||
- garage-bAInd/Open-Platypus
|
||||
- ehartford/dolphin
|
||||
model-index:
|
||||
- name: model_101
|
||||
results:
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: AI2 Reasoning Challenge (25-Shot)
|
||||
type: ai2_arc
|
||||
config: ARC-Challenge
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 25
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 68.69
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/model_101
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: HellaSwag (10-Shot)
|
||||
type: hellaswag
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 10
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 86.42
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/model_101
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: MMLU (5-Shot)
|
||||
type: cais/mmlu
|
||||
config: all
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 69.92
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/model_101
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: TruthfulQA (0-shot)
|
||||
type: truthful_qa
|
||||
config: multiple_choice
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 0
|
||||
metrics:
|
||||
- type: mc2
|
||||
value: 58.85
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/model_101
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: Winogrande (5-shot)
|
||||
type: winogrande
|
||||
config: winogrande_xl
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 82.08
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/model_101
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: GSM8k (5-shot)
|
||||
type: gsm8k
|
||||
config: main
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 44.81
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/model_101
|
||||
name: Open LLM Leaderboard
|
||||
---
|
||||
|
||||
# model_101
|
||||
|
||||
A hybrid (explain + instruct) style Llama2-70b model, Pleae check examples below for both style prompts, Here is the list of datasets used:
|
||||
|
||||
* Open-Platypus
|
||||
* Alpaca
|
||||
* WizardLM
|
||||
* Dolly-V2
|
||||
* Dolphin Samples (~200K)
|
||||
* Orca_minis_v1
|
||||
* Alpaca_orca
|
||||
* WizardLM_orca
|
||||
* Dolly-V2_orca
|
||||
* Plus more datasets which I am planning to release as open source dataset sometime in future.
|
||||
|
||||
<br>
|
||||
|
||||
<strong>
|
||||
"Obsessed with GenAI's potential? So am I ! Let's create together 🚀 <a href="https://www.linkedin.com/in/pankajam" target="_blank">https://www.linkedin.com/in/pankajam</a>"
|
||||
</strong>
|
||||
|
||||
<br>
|
||||
|
||||
<br>
|
||||
|
||||
### Evaluation
|
||||
|
||||
We evaluated model_001 on a wide range of tasks using [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) from EleutherAI.
|
||||
|
||||
Here are the results on metrics used by [HuggingFaceH4 Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
||||
|
||||
|||
|
||||
|:------:|:-------:|
|
||||
|**Task**|**Value**|
|
||||
|*ARC*|0.6869|
|
||||
|*HellaSwag*|0.8642|
|
||||
|*MMLU*|0.6992|
|
||||
|*TruthfulQA*|0.5885|
|
||||
|*Winogrande*|0.8208|
|
||||
|*GSM8k*|0.4481|
|
||||
|*DROP*|0.5510|
|
||||
|**Total Average**|**0.6655**|
|
||||
|
||||
|
||||
<br>
|
||||
|
||||
### Prompt Format
|
||||
|
||||
Here is the Orca prompt format
|
||||
|
||||
```
|
||||
### System:
|
||||
You are an AI assistant that follows instruction extremely well. Help as much as you can.
|
||||
|
||||
### User:
|
||||
Tell me about Orcas.
|
||||
|
||||
### Assistant:
|
||||
|
||||
```
|
||||
|
||||
Here is the Alpaca prompt format
|
||||
|
||||
```
|
||||
|
||||
### User:
|
||||
Tell me about Alpacas.
|
||||
|
||||
### Assistant:
|
||||
|
||||
```
|
||||
|
||||
#### OobaBooga Instructions:
|
||||
|
||||
This model required upto 45GB GPU VRAM in 4bit so it can be loaded directly on Single RTX 6000/L40/A40/A100/H100 GPU or Double RTX 4090/L4/A10/RTX 3090/RTX A5000
|
||||
So, if you have access to Machine with 45GB GPU VRAM and have installed [OobaBooga Web UI](https://github.com/oobabooga/text-generation-webui) on it.
|
||||
You can just download this model by using HF repo link directly on OobaBooga Web UI "Model" Tab/Page & Just use **load-in-4bit** option in it.
|
||||
|
||||
|
||||
|
||||
|
||||
After that go to Default Tab/Page on OobaBooga Web UI and **copy paste above prompt format into Input** and Enjoy!
|
||||
|
||||
|
||||
|
||||
<br>
|
||||
|
||||
#### Code Instructions:
|
||||
|
||||
Below shows a code example on how to use this model via Orca prompt
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained("pankajmathur/model_101")
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
"pankajmathur/model_101",
|
||||
torch_dtype=torch.float16,
|
||||
load_in_4bit=True,
|
||||
low_cpu_mem_usage=True,
|
||||
device_map="auto"
|
||||
)
|
||||
system_prompt = "### System:\nYou are an AI assistant that follows instruction extremely well. Help as much as you can.\n\n"
|
||||
|
||||
#generate text steps
|
||||
instruction = "Tell me about Orcas."
|
||||
prompt = f"{system_prompt}### User: {instruction}\n\n### Assistant:\n"
|
||||
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
|
||||
output = model.generate(**inputs, do_sample=True, top_p=0.95, top_k=0, max_new_tokens=4096)
|
||||
|
||||
print(tokenizer.decode(output[0], skip_special_tokens=True))
|
||||
|
||||
```
|
||||
|
||||
|
||||
Below shows a code example on how to use this model via Alpaca prompt
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained("pankajmathur/model_101")
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
"pankajmathur/model_101",
|
||||
torch_dtype=torch.float16,
|
||||
load_in_4bit=True,
|
||||
low_cpu_mem_usage=True,
|
||||
device_map="auto"
|
||||
)
|
||||
#generate text steps
|
||||
instruction = "Tell me about Alpacas."
|
||||
prompt = f"### User: {instruction}\n\n### Assistant:\n"
|
||||
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
|
||||
output = model.generate(**inputs, do_sample=True, top_p=0.95, top_k=0, max_new_tokens=4096)
|
||||
|
||||
print(tokenizer.decode(output[0], skip_special_tokens=True))
|
||||
|
||||
```
|
||||
|
||||
<br>
|
||||
|
||||
#### license disclaimer:
|
||||
|
||||
This model is bound by the license & usage restrictions of the original Llama-2 model. And comes with no warranty or gurantees of any kind.
|
||||
|
||||
<br>
|
||||
|
||||
#### Limitations & Biases:
|
||||
|
||||
While this model aims for accuracy, it can occasionally produce inaccurate or misleading results.
|
||||
|
||||
Despite diligent efforts in refining the pretraining data, there remains a possibility for the generation of inappropriate, biased, or offensive content.
|
||||
|
||||
Exercise caution and cross-check information when necessary.
|
||||
|
||||
|
||||
<br>
|
||||
|
||||
### Citiation:
|
||||
|
||||
Please kindly cite using the following BibTeX:
|
||||
|
||||
```
|
||||
@misc{model_101,
|
||||
author = {Pankaj Mathur},
|
||||
title = {model_101: A hybrid (explain + instruct) style Llama2-70b model},
|
||||
month = {August},
|
||||
year = {2023},
|
||||
publisher = {HuggingFace},
|
||||
journal = {HuggingFace repository},
|
||||
howpublished = {\url{https://https://huggingface.co/pankajmathur/model_101},
|
||||
}
|
||||
```
|
||||
|
||||
```
|
||||
@misc{mukherjee2023orca,
|
||||
title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4},
|
||||
author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
|
||||
year={2023},
|
||||
eprint={2306.02707},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.CL}
|
||||
}
|
||||
```
|
||||
|
||||
```
|
||||
@software{touvron2023llama2,
|
||||
title={Llama 2: Open Foundation and Fine-Tuned Chat Models},
|
||||
author={Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava,
|
||||
Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fuller,
|
||||
Cynthia Gao, Vedanuj Goswami, Naman Goyal, Anthony Hartshorn, Saghar Hosseini, Rui Hou, Hakan Inan, Marcin Kardas, Viktor Kerkez Madian Khabsa, Isabel Kloumann,
|
||||
Artem Korenev, Punit Singh Koura, Marie-Anne Lachaux, Thibaut Lavril, Jenya Lee, Diana Liskovich, Yinghai Lu, Yuning Mao, Xavier Martinet, Todor Mihaylov,
|
||||
Pushkar Mishra, Igor Molybog, Yixin Nie, Andrew Poulton, Jeremy Reizenstein, Rashi Rungta, Kalyan Saladi, Alan Schelten, Ruan Silva, Eric Michael Smith,
|
||||
Ranjan Subramanian, Xiaoqing Ellen Tan, Binh Tang, Ross Taylor, Adina Williams, Jian Xiang Kuan, Puxin Xu , Zheng Yan, Iliyan Zarov, Yuchen Zhang, Angela Fan,
|
||||
Melanie Kambadur, Sharan Narang, Aurelien Rodriguez, Robert Stojnic, Sergey Edunov, Thomas Scialom},
|
||||
year={2023}
|
||||
}
|
||||
```
|
||||
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
||||
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_psmathur__model_101)
|
||||
|
||||
| Metric | Value |
|
||||
|-----------------------|---------------------------|
|
||||
| Avg. | 66.55 |
|
||||
| ARC (25-shot) | 68.69 |
|
||||
| HellaSwag (10-shot) | 86.42 |
|
||||
| MMLU (5-shot) | 69.92 |
|
||||
| TruthfulQA (0-shot) | 58.85 |
|
||||
| Winogrande (5-shot) | 82.08 |
|
||||
| GSM8K (5-shot) | 44.81 |
|
||||
| DROP (3-shot) | 55.1 |
|
||||
|
||||
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
||||
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_psmathur__model_101)
|
||||
|
||||
| Metric |Value|
|
||||
|---------------------------------|----:|
|
||||
|Avg. |68.46|
|
||||
|AI2 Reasoning Challenge (25-Shot)|68.69|
|
||||
|HellaSwag (10-Shot) |86.42|
|
||||
|MMLU (5-Shot) |69.92|
|
||||
|TruthfulQA (0-shot) |58.85|
|
||||
|Winogrande (5-shot) |82.08|
|
||||
|GSM8k (5-shot) |44.81|
|
||||
|
||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"_name_or_path": "TheBloke/Llama-2-70B-fp16",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 8192,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 28672,
|
||||
"max_position_embeddings": 4096,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 64,
|
||||
"num_hidden_layers": 80,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 0,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.32.0.dev0",
|
||||
"use_cache": false,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
BIN
default_input_screenshot.png
Normal file
BIN
default_input_screenshot.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 599 KiB |
8
generation_config.json
Normal file
8
generation_config.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.32.0.dev0",
|
||||
"use_cache": false
|
||||
}
|
||||
3
model-00001-of-00015.safetensors
Normal file
3
model-00001-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7646282846263a120d2b1f366cb8e3bda6bce4313c5b473d022cebdc712347d5
|
||||
size 9852589808
|
||||
3
model-00002-of-00015.safetensors
Normal file
3
model-00002-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d46f4ce08f5dbd5067d59ef2243dc7bf7675a185e8fb5956ba634ba4a430e027
|
||||
size 9798096872
|
||||
3
model-00003-of-00015.safetensors
Normal file
3
model-00003-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:69c930c7d5ae9514df0d9358daa3b71c1a8880e4bdadeca013d141bd258201db
|
||||
size 9965868720
|
||||
3
model-00004-of-00015.safetensors
Normal file
3
model-00004-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c80a67a6599aa481a7097d1fc7c2a33bacaa1bb1f92447d48a4c053f05f12894
|
||||
size 9798063912
|
||||
3
model-00005-of-00015.safetensors
Normal file
3
model-00005-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:98c258a7451dc59f7733f8c6919013668c697ef43a6a1d0590484edbdb3a7f9d
|
||||
size 9798096904
|
||||
3
model-00006-of-00015.safetensors
Normal file
3
model-00006-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fa036b528f904bc347fadc3413d9d7d9c9f40b6a96c2e56309903a2dbb2c30d1
|
||||
size 9798096904
|
||||
3
model-00007-of-00015.safetensors
Normal file
3
model-00007-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b3776f316f62c327395e8614ca008f22a2ef4d678a64ad71ba2d1de093893616
|
||||
size 9965868720
|
||||
3
model-00008-of-00015.safetensors
Normal file
3
model-00008-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:330c12cd87f04de0bc5ea5970509947c525443be815b77db8fb014c4fb33e08a
|
||||
size 9798063912
|
||||
3
model-00009-of-00015.safetensors
Normal file
3
model-00009-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7a5034b6942669da8b1c64a77a304a18a143dbc834fb291035ed451fb77861d8
|
||||
size 9798096904
|
||||
3
model-00010-of-00015.safetensors
Normal file
3
model-00010-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0990b1a7d07d36748736ace49ead325c1695baabed9268b471f478f1376ac5e9
|
||||
size 9798096904
|
||||
3
model-00011-of-00015.safetensors
Normal file
3
model-00011-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4a46682aa09937d16eebb6be1ca53375d93e906e28603f73eeb11f0bd49575e7
|
||||
size 9965868720
|
||||
3
model-00012-of-00015.safetensors
Normal file
3
model-00012-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a4fe81bd7e887eda85aaf5186212ec7b3c40266a4c9b44126a0fe40b0d4c4ef8
|
||||
size 9798063912
|
||||
3
model-00013-of-00015.safetensors
Normal file
3
model-00013-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b85e2fc40ab9c23da3ec4692c2d84d318cefa311350a4db0462dd2c879d62fad
|
||||
size 9798096904
|
||||
3
model-00014-of-00015.safetensors
Normal file
3
model-00014-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3b3994771d9765325b13526effa9c0d7cbc5529892f94e99a8b4ef8571581d24
|
||||
size 9496123024
|
||||
3
model-00015-of-00015.safetensors
Normal file
3
model-00015-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9ce51c4fa8826580aa33397125e679add49407b82d1a53a39b9fb510f0a7a22e
|
||||
size 524288128
|
||||
730
model.safetensors.index.json
Normal file
730
model.safetensors.index.json
Normal file
@@ -0,0 +1,730 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 137953296384
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00015-of-00015.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.48.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.48.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.48.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.48.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.48.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.48.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.48.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.48.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.48.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.49.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.49.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.49.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.49.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.49.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.49.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.49.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.49.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.49.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.50.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.50.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.50.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.50.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.50.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.50.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.50.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.50.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.50.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.51.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.51.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.51.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.51.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.51.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.51.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.51.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.51.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.51.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.52.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.52.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.52.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.52.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.52.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.52.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.52.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.52.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.52.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.53.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.53.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.53.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.53.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.53.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.53.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.53.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.53.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.53.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.54.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.54.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.54.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.54.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.54.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.54.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.54.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.54.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.54.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.55.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.55.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.55.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.55.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.55.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.55.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.55.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.55.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.55.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.56.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.56.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.56.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.56.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.56.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.56.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.56.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.56.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.56.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.57.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.57.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.57.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.57.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.57.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.57.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.57.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.57.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.57.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.58.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.58.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.58.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.58.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.58.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.58.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.58.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.58.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.58.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.59.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.59.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.59.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.59.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.59.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.59.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.59.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.59.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.59.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.60.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.60.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.60.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.60.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.60.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.60.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.60.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.60.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.60.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.61.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.61.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.61.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.61.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.61.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.61.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.61.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.61.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.61.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.62.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.62.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.62.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.62.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.62.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.62.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.62.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.62.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.62.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.63.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.63.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.63.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.63.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.63.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.63.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.63.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.63.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.63.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.64.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.64.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.64.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.64.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.64.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.64.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.64.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.64.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.64.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.65.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.65.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.65.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.65.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.65.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.65.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.65.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.65.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.65.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.66.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.66.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.66.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.66.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.66.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.66.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.66.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.66.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.66.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.67.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.67.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.67.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.67.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.67.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.67.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.67.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.67.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.67.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.68.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.68.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.68.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.68.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.68.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.68.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.68.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.68.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.68.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.69.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.69.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.69.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.69.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.69.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.69.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.69.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.69.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.69.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.70.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.70.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.70.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.70.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.70.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.70.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.70.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.70.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.70.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.71.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.71.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.71.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.71.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.71.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.71.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.71.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.71.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.71.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.72.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.72.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.72.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.72.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.72.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.72.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.72.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.72.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.72.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.73.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.73.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.73.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.73.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.73.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.73.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.73.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.73.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.73.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.74.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.74.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.74.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.74.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.74.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.74.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.74.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.74.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.74.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.75.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.75.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.75.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.75.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.75.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.75.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.75.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.75.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.75.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.76.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.76.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.76.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.76.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.76.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.76.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.76.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.76.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.76.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.77.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.77.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.77.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.77.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.77.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.77.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.77.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.77.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.77.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.78.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.78.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.78.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.78.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.78.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.78.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.78.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.78.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.78.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.79.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.79.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.79.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.79.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.79.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.79.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.79.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.79.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.79.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.norm.weight": "model-00014-of-00015.safetensors"
|
||||
}
|
||||
}
|
||||
BIN
oobabooga_model_load_screenshot.png
Normal file
BIN
oobabooga_model_load_screenshot.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 617 KiB |
3
pytorch_model-00001-of-00015.bin
Normal file
3
pytorch_model-00001-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b84c9df2412bfb4418d99bb8d1e0a5358f9d2beb23b16c54e16577933d491967
|
||||
size 9852602021
|
||||
3
pytorch_model-00002-of-00015.bin
Normal file
3
pytorch_model-00002-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b5155ea1c31c61a3591b21ce72d05acec56ad9cfce4bd65e237d0bef1846dbe9
|
||||
size 9798109597
|
||||
3
pytorch_model-00003-of-00015.bin
Normal file
3
pytorch_model-00003-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:be977f3d8b26e797cb4c19a53432fa72e667106c3523575b7e866dccf8e2fb77
|
||||
size 9965880719
|
||||
3
pytorch_model-00004-of-00015.bin
Normal file
3
pytorch_model-00004-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4eae71b53cc1e3fbb0dd7e7514a30c9f47b500f67e324cea57d853b6225a35fd
|
||||
size 9798076069
|
||||
3
pytorch_model-00005-of-00015.bin
Normal file
3
pytorch_model-00005-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:eb192a058fe20979c94eb80f628d2ea725fde9e59ba54343340e35561ead51e7
|
||||
size 9798109577
|
||||
3
pytorch_model-00006-of-00015.bin
Normal file
3
pytorch_model-00006-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:efb3cc3b737f0b9f6577958da34e57e692fba2398f95e7a2f1c43fde5524a11e
|
||||
size 9798109661
|
||||
3
pytorch_model-00007-of-00015.bin
Normal file
3
pytorch_model-00007-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3e7d80835b72996c651eff639f0e23377e3aae2aaf5bd6590474d0425f371e95
|
||||
size 9965880719
|
||||
3
pytorch_model-00008-of-00015.bin
Normal file
3
pytorch_model-00008-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:71fce05129d737c3ee1f81240c4432582ca2035b98caa649ba6d5bca65c17d3d
|
||||
size 9798076069
|
||||
3
pytorch_model-00009-of-00015.bin
Normal file
3
pytorch_model-00009-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cbd639c013ecbf3a761d5694a2d7d251de029b9a6436afadf149b7f408ecf2d4
|
||||
size 9798109577
|
||||
3
pytorch_model-00010-of-00015.bin
Normal file
3
pytorch_model-00010-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d70de2777112df9f562b06e4f4fff3cce881586b1b9777f368a06e4bfc5dfd09
|
||||
size 9798109661
|
||||
3
pytorch_model-00011-of-00015.bin
Normal file
3
pytorch_model-00011-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7ab6730603e09a202c7443c760820c4cfe065a56247e66fabc59a3565f6b66ca
|
||||
size 9965880719
|
||||
3
pytorch_model-00012-of-00015.bin
Normal file
3
pytorch_model-00012-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c402e947cb8ce55f87f51cff770f125d2f81a5810cf4e9e73e7f3bb30e9793eb
|
||||
size 9798076069
|
||||
3
pytorch_model-00013-of-00015.bin
Normal file
3
pytorch_model-00013-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ab7182ff08fb57956ed46626623258561bcd4a49ec42c999db9a536d137e236a
|
||||
size 9798109577
|
||||
3
pytorch_model-00014-of-00015.bin
Normal file
3
pytorch_model-00014-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:75da30e197b44300045525dcfb8572b182a90f55df75971f142e2ebb94984351
|
||||
size 9496135043
|
||||
3
pytorch_model-00015-of-00015.bin
Normal file
3
pytorch_model-00015-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a91315da57f53c2d8ffd9fef4919b46207b35a3c093fb9f78da70024adc71579
|
||||
size 524288938
|
||||
730
pytorch_model.bin.index.json
Normal file
730
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,730 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 137953296384
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00015-of-00015.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.34.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.35.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.40.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.40.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.40.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.40.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.40.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.40.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.40.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.40.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.40.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.45.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.45.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.45.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.45.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.45.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.45.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.45.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.45.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.45.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.46.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.46.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.46.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.46.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.46.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.46.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.46.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.46.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.46.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.50.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.50.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.50.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.50.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.50.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.50.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.50.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.50.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.50.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.51.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.51.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.51.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.51.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.51.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.51.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.51.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.51.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.51.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.52.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.52.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.52.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.52.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.52.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.52.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.52.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.52.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.52.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.57.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.57.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.57.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.57.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.57.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.57.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.57.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.57.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.57.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.58.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.58.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.58.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.58.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.58.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.58.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.58.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.58.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.58.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.60.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.60.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.60.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.60.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.60.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.60.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.60.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.60.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.60.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.63.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.63.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.63.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.63.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.63.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.63.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.63.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.63.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.63.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.68.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.68.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.68.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.68.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.68.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.68.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.68.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.68.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.68.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.69.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.69.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.69.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.69.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.69.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.69.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.69.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.69.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.69.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.70.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.70.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.70.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.70.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.70.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.70.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.70.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.70.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.70.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.74.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.74.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.74.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.74.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.74.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.74.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.74.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.74.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.74.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.75.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.75.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.75.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.75.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.75.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.75.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.75.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.75.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.75.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.norm.weight": "pytorch_model-00014-of-00015.bin"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
93391
tokenizer.json
Normal file
93391
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
||||
size 499723
|
||||
32
tokenizer_config.json
Normal file
32
tokenizer_config.json
Normal file
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"legacy": false,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": null,
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user