初始化项目，由ModelHub XC社区提供模型
Model: pankajmathur/orca_mini_3b 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
|
||||||
339
README.md
Normal file
339
README.md
Normal file
@@ -0,0 +1,339 @@
|
|||||||
|
---
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
license: cc-by-nc-sa-4.0
|
||||||
|
library_name: transformers
|
||||||
|
datasets:
|
||||||
|
- psmathur/alpaca_orca
|
||||||
|
- psmathur/dolly-v2_orca
|
||||||
|
- psmathur/WizardLM_Orca
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
model-index:
|
||||||
|
- name: orca_mini_3b
|
||||||
|
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: 41.55
|
||||||
|
name: normalized accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_3b
|
||||||
|
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: 61.52
|
||||||
|
name: normalized accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_3b
|
||||||
|
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: 26.79
|
||||||
|
name: accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_3b
|
||||||
|
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: 42.42
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_3b
|
||||||
|
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: 61.8
|
||||||
|
name: accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_3b
|
||||||
|
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: 0.08
|
||||||
|
name: accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_3b
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
---
|
||||||
|
# orca_mini_3b
|
||||||
|
|
||||||
|
<img src="https://huggingface.co/pankajmathur/orca_mini_v5_8b/resolve/main/orca_minis_small.jpeg" width="auto" />
|
||||||
|
|
||||||
|
<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>
|
||||||
|
|
||||||
|
**Use orca-mini-3b for Free on Google Colab with T4 GPU :)**
|
||||||
|
|
||||||
|
<a target="_blank" href="https://colab.research.google.com/#fileId=https://huggingface.co/psmathur/orca_mini_3b/blob/main/orca_mini_3b_T4_GPU.ipynb">
|
||||||
|
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
|
||||||
|
</a>
|
||||||
|
|
||||||
|
An [OpenLLaMa-3B model](https://github.com/openlm-research/open_llama) model trained on explain tuned datasets, created using Instructions and Input from WizardLM, Alpaca & Dolly-V2 datasets and applying Orca Research Paper dataset construction approaches.
|
||||||
|
|
||||||
|
|
||||||
|
### Dataset
|
||||||
|
|
||||||
|
We build explain tuned [WizardLM dataset ~70K](https://github.com/nlpxucan/WizardLM), [Alpaca dataset ~52K](https://crfm.stanford.edu/2023/03/13/alpaca.html) & [Dolly-V2 dataset ~15K](https://github.com/databrickslabs/dolly) created using approaches from [Orca Research Paper](https://arxiv.org/abs/2306.02707).
|
||||||
|
|
||||||
|
We leverage all of the 15 system instructions provided in Orca Research Paper. to generate custom datasets, in contrast to vanilla instruction tuning approaches used by original datasets.
|
||||||
|
|
||||||
|
This helps student model aka this model to learn ***thought*** process from teacher model, which is ChatGPT (gpt-3.5-turbo-0301 version).
|
||||||
|
|
||||||
|
Please see below example usage how the **System** prompt is added before each **instruction**.
|
||||||
|
|
||||||
|
|
||||||
|
### Training
|
||||||
|
|
||||||
|
The training configurations are provided in the table below.
|
||||||
|
|
||||||
|
The training takes on 8x A100(80G) GPUs and lasts for around 4 Hours for cost of $48 using [Lambda Labs](https://lambdalabs.com)
|
||||||
|
|
||||||
|
We used DeepSpeed with fully sharded data parallelism, also know as [ZeRO stage 3](https://engineering.fb.com/2021/07/15/open-source/fsdp/) by writing our own fine tunning scripts plus leveraging some of the model training code provided by amazing [OpenAlpaca repo](https://github.com/yxuansu/OpenAlpaca)
|
||||||
|
|
||||||
|
Here are some of params used during training:
|
||||||
|
|
||||||
|
|||
|
||||||
|
|:-------------:|:-------------:|
|
||||||
|
|*batch_size*|64|
|
||||||
|
|*train_micro_batch_size_per_gpu*|4|
|
||||||
|
|*gradient_accumulation_steps*|2|
|
||||||
|
|*Learning rate*|2e-5|
|
||||||
|
|*Max length*|1024|
|
||||||
|
|*Epochs*|3|
|
||||||
|
|*Optimizer*|AdamW|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
### Example Usage
|
||||||
|
|
||||||
|
Below shows an example on how to use this model
|
||||||
|
|
||||||
|
```python
|
||||||
|
import torch
|
||||||
|
from transformers import LlamaForCausalLM, LlamaTokenizer
|
||||||
|
|
||||||
|
# Hugging Face model_path
|
||||||
|
model_path = 'psmathur/orca_mini_3b'
|
||||||
|
tokenizer = LlamaTokenizer.from_pretrained(model_path)
|
||||||
|
model = LlamaForCausalLM.from_pretrained(
|
||||||
|
model_path, torch_dtype=torch.float16, device_map='auto',
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
#generate text function
|
||||||
|
def generate_text(system, instruction, input=None):
|
||||||
|
|
||||||
|
if input:
|
||||||
|
prompt = f"### System:\n{system}\n\n### User:\n{instruction}\n\n### Input:\n{input}\n\n### Response:\n"
|
||||||
|
else:
|
||||||
|
prompt = f"### System:\n{system}\n\n### User:\n{instruction}\n\n### Response:\n"
|
||||||
|
|
||||||
|
tokens = tokenizer.encode(prompt)
|
||||||
|
tokens = torch.LongTensor(tokens).unsqueeze(0)
|
||||||
|
tokens = tokens.to('cuda')
|
||||||
|
|
||||||
|
instance = {'input_ids': tokens,'top_p': 1.0, 'temperature':0.7, 'generate_len': 1024, 'top_k': 50}
|
||||||
|
|
||||||
|
length = len(tokens[0])
|
||||||
|
with torch.no_grad():
|
||||||
|
rest = model.generate(
|
||||||
|
input_ids=tokens,
|
||||||
|
max_length=length+instance['generate_len'],
|
||||||
|
use_cache=True,
|
||||||
|
do_sample=True,
|
||||||
|
top_p=instance['top_p'],
|
||||||
|
temperature=instance['temperature'],
|
||||||
|
top_k=instance['top_k']
|
||||||
|
)
|
||||||
|
output = rest[0][length:]
|
||||||
|
string = tokenizer.decode(output, skip_special_tokens=True)
|
||||||
|
return f'[!] Response: {string}'
|
||||||
|
|
||||||
|
# Sample Test Instruction Used by Youtuber Sam Witteveen https://www.youtube.com/@samwitteveenai
|
||||||
|
system = 'You are an AI assistant that follows instruction extremely well. Help as much as you can.'
|
||||||
|
instruction = 'Write a letter to Sam Altman, CEO of OpenAI, requesting him to convert GPT4 a private model by OpenAI to an open source project'
|
||||||
|
print(generate_text(system, instruction))
|
||||||
|
|
||||||
|
```
|
||||||
|
|
||||||
|
```
|
||||||
|
|
||||||
|
[!] Response:
|
||||||
|
Dear Sam Altman,
|
||||||
|
|
||||||
|
I am writing to request that you convert the GPT4 private model developed by OpenAI to an open source project. As a user of OpenAI, I have been waiting for the day when I can use the advanced natural language processing capabilities of GPT4 in a more open and accessible way.
|
||||||
|
|
||||||
|
While OpenAI has made significant progress in developing AI applications, it has primarily focused on building private models that are not accessible to the general public. However, with the recent release of GPT-3, there is a growing demand for more open and accessible AI tools.
|
||||||
|
|
||||||
|
Converting GPT4 to an open source project would allow for greater transparency, collaboration, and innovation. It would also help to build trust in the technology and ensure that it is used ethically and responsibly.
|
||||||
|
|
||||||
|
I urge you to consider converting GPT4 to an open source project. This would be a significant contribution to the AI community and would help to create a more open and accessible future.
|
||||||
|
|
||||||
|
Thank you for your consideration.
|
||||||
|
|
||||||
|
Sincerely,
|
||||||
|
|
||||||
|
[Your Name]
|
||||||
|
|
||||||
|
```
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
Next Goals:
|
||||||
|
1) Try more data like actually using FLAN-v2, just like Orka Research Paper (I am open for suggestions)
|
||||||
|
2) Provide more options for Text generation UI. (may be https://github.com/oobabooga/text-generation-webui)
|
||||||
|
3) Provide 4bit GGML/GPTQ quantized model (may be [TheBloke](https://huggingface.co/TheBloke) can help here)
|
||||||
|
|
||||||
|
|
||||||
|
Limitations & Biases:
|
||||||
|
|
||||||
|
This model can produce factually incorrect output, and should not be relied on to produce factually accurate information.
|
||||||
|
This model was trained on various public datasets. While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
|
||||||
|
|
||||||
|
Disclaimer:
|
||||||
|
|
||||||
|
The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model.
|
||||||
|
Please cosult an attorney before using this model for commercial purposes.
|
||||||
|
|
||||||
|
|
||||||
|
Citiation:
|
||||||
|
|
||||||
|
If you found wizardlm_alpaca_dolly_orca_open_llama_3b useful in your research or applications, please kindly cite using the following BibTeX:
|
||||||
|
|
||||||
|
```
|
||||||
|
@misc{orca_mini_3b,
|
||||||
|
author = {Pankaj Mathur},
|
||||||
|
title = {wizardlm_alpaca_dolly_orca_open_llama_3b: An explain tuned OpenLLaMA-3b model on custom wizardlm, alpaca, & dolly datasets},
|
||||||
|
year = {2023},
|
||||||
|
publisher = {GitHub, HuggingFace},
|
||||||
|
journal = {GitHub repository, HuggingFace repository},
|
||||||
|
howpublished = {\url{https://github.com/pankajarm/wizardlm_alpaca_dolly_orca_open_llama_3b}, \url{https://https://huggingface.co/psmathur/wizardlm_alpaca_dolly_orca_open_llama_3b}},
|
||||||
|
}
|
||||||
|
```
|
||||||
|
```
|
||||||
|
@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{openlm2023openllama,
|
||||||
|
author = {Xinyang Geng and Hao Liu},
|
||||||
|
title = {OpenLLaMA: An Open Reproduction of LLaMA},
|
||||||
|
month = May,
|
||||||
|
year = 2023,
|
||||||
|
url = {https://github.com/openlm-research/open_llama}
|
||||||
|
}
|
||||||
|
```
|
||||||
|
```
|
||||||
|
@misc{openalpaca,
|
||||||
|
author = {Yixuan Su and Tian Lan and Deng Cai},
|
||||||
|
title = {OpenAlpaca: A Fully Open-Source Instruction-Following Model Based On OpenLLaMA},
|
||||||
|
year = {2023},
|
||||||
|
publisher = {GitHub},
|
||||||
|
journal = {GitHub repository},
|
||||||
|
howpublished = {\url{https://github.com/yxuansu/OpenAlpaca}},
|
||||||
|
}
|
||||||
|
```
|
||||||
|
```
|
||||||
|
@misc{alpaca,
|
||||||
|
author = {Rohan Taori and Ishaan Gulrajani and Tianyi Zhang and Yann Dubois and Xuechen Li and Carlos Guestrin and Percy Liang and Tatsunori B. Hashimoto },
|
||||||
|
title = {Stanford Alpaca: An Instruction-following LLaMA model},
|
||||||
|
year = {2023},
|
||||||
|
publisher = {GitHub},
|
||||||
|
journal = {GitHub repository},
|
||||||
|
howpublished = {\url{https://github.com/tatsu-lab/stanford_alpaca}},
|
||||||
|
}
|
||||||
|
```
|
||||||
|
### [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__orca_mini_3b)
|
||||||
|
|
||||||
|
| Metric | Value |
|
||||||
|
|-----------------------|---------------------------|
|
||||||
|
| Avg. | 35.5 |
|
||||||
|
| ARC (25-shot) | 41.55 |
|
||||||
|
| HellaSwag (10-shot) | 61.52 |
|
||||||
|
| MMLU (5-shot) | 26.79 |
|
||||||
|
| TruthfulQA (0-shot) | 42.42 |
|
||||||
|
| Winogrande (5-shot) | 61.8 |
|
||||||
|
| GSM8K (5-shot) | 0.08 |
|
||||||
|
| DROP (3-shot) | 14.33 |
|
||||||
|
|
||||||
|
### [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__orca_mini_3b)
|
||||||
|
|
||||||
|
| Metric |Value|
|
||||||
|
|---------------------------------|----:|
|
||||||
|
|Avg. |39.03|
|
||||||
|
|AI2 Reasoning Challenge (25-Shot)|41.55|
|
||||||
|
|HellaSwag (10-Shot) |61.52|
|
||||||
|
|MMLU (5-Shot) |26.79|
|
||||||
|
|TruthfulQA (0-shot) |42.42|
|
||||||
|
|Winogrande (5-shot) |61.80|
|
||||||
|
|GSM8k (5-shot) | 0.08|
|
||||||
|
|
||||||
23
config.json
Normal file
23
config.json
Normal file
@@ -0,0 +1,23 @@
|
|||||||
|
{
|
||||||
|
"_name_or_path": "openlm-research/open_llama_3b",
|
||||||
|
"architectures": [
|
||||||
|
"LlamaForCausalLM"
|
||||||
|
],
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"eos_token_id": 2,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 3200,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 8640,
|
||||||
|
"max_position_embeddings": 2048,
|
||||||
|
"model_type": "llama",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 26,
|
||||||
|
"pad_token_id": 0,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "float32",
|
||||||
|
"transformers_version": "4.29.1",
|
||||||
|
"use_cache": true,
|
||||||
|
"vocab_size": 32000
|
||||||
|
}
|
||||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
|||||||
|
{
|
||||||
|
"_from_model_config": true,
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"eos_token_id": 2,
|
||||||
|
"pad_token_id": 0,
|
||||||
|
"transformers_version": "4.29.1"
|
||||||
|
}
|
||||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:6bcf8a5ec649bea883283ea4b6f169e2f7becfa97d484005f324abd91c9db28f
|
||||||
|
size 4993266968
|
||||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:21bbbb746028d99822d1d9287337f483815b0cef80e2bdb58ba87d699d4727d1
|
||||||
|
size 4997389960
|
||||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:89d1e9f4c545f84dedb6eef4a322b2899fc6771696edb39ea461d4309374fbc6
|
||||||
|
size 3715272904
|
||||||
270
model.safetensors.index.json
Normal file
270
model.safetensors.index.json
Normal file
@@ -0,0 +1,270 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 13705899600
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.20.self_attn.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.21.self_attn.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.22.self_attn.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.23.self_attn.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.24.self_attn.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.self_attn.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.8.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.9.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.norm.weight": "model-00003-of-00003.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
501
orca_mini_3b_T4_GPU.ipynb
Normal file
501
orca_mini_3b_T4_GPU.ipynb
Normal file
@@ -0,0 +1,501 @@
|
|||||||
|
{
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 0,
|
||||||
|
"metadata": {
|
||||||
|
"colab": {
|
||||||
|
"provenance": [],
|
||||||
|
"gpuType": "T4"
|
||||||
|
},
|
||||||
|
"kernelspec": {
|
||||||
|
"name": "python3",
|
||||||
|
"display_name": "Python 3"
|
||||||
|
},
|
||||||
|
"language_info": {
|
||||||
|
"name": "python"
|
||||||
|
},
|
||||||
|
"accelerator": "GPU",
|
||||||
|
"widgets": {
|
||||||
|
"application/vnd.jupyter.widget-state+json": {
|
||||||
|
"1830ab16750b4c7ebf5d1692a02e3544": {
|
||||||
|
"model_module": "@jupyter-widgets/controls",
|
||||||
|
"model_name": "HBoxModel",
|
||||||
|
"model_module_version": "1.5.0",
|
||||||
|
"state": {
|
||||||
|
"_dom_classes": [],
|
||||||
|
"_model_module": "@jupyter-widgets/controls",
|
||||||
|
"_model_module_version": "1.5.0",
|
||||||
|
"_model_name": "HBoxModel",
|
||||||
|
"_view_count": null,
|
||||||
|
"_view_module": "@jupyter-widgets/controls",
|
||||||
|
"_view_module_version": "1.5.0",
|
||||||
|
"_view_name": "HBoxView",
|
||||||
|
"box_style": "",
|
||||||
|
"children": [
|
||||||
|
"IPY_MODEL_de65aa83f07a48a98ecc54fd956c5831",
|
||||||
|
"IPY_MODEL_93dad1c7c99b4a36a8df85fc2dff617e",
|
||||||
|
"IPY_MODEL_098a2232a1f34d94ab4f61141733730f"
|
||||||
|
],
|
||||||
|
"layout": "IPY_MODEL_79a38d122e4c4b2593b96151f5bce47e"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"de65aa83f07a48a98ecc54fd956c5831": {
|
||||||
|
"model_module": "@jupyter-widgets/controls",
|
||||||
|
"model_name": "HTMLModel",
|
||||||
|
"model_module_version": "1.5.0",
|
||||||
|
"state": {
|
||||||
|
"_dom_classes": [],
|
||||||
|
"_model_module": "@jupyter-widgets/controls",
|
||||||
|
"_model_module_version": "1.5.0",
|
||||||
|
"_model_name": "HTMLModel",
|
||||||
|
"_view_count": null,
|
||||||
|
"_view_module": "@jupyter-widgets/controls",
|
||||||
|
"_view_module_version": "1.5.0",
|
||||||
|
"_view_name": "HTMLView",
|
||||||
|
"description": "",
|
||||||
|
"description_tooltip": null,
|
||||||
|
"layout": "IPY_MODEL_d8e51c8c5d0b4698918e24b3aa32f492",
|
||||||
|
"placeholder": "",
|
||||||
|
"style": "IPY_MODEL_b8d38b2204b94010acdd81a438c6c58c",
|
||||||
|
"value": "Loading checkpoint shards: 100%"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"93dad1c7c99b4a36a8df85fc2dff617e": {
|
||||||
|
"model_module": "@jupyter-widgets/controls",
|
||||||
|
"model_name": "FloatProgressModel",
|
||||||
|
"model_module_version": "1.5.0",
|
||||||
|
"state": {
|
||||||
|
"_dom_classes": [],
|
||||||
|
"_model_module": "@jupyter-widgets/controls",
|
||||||
|
"_model_module_version": "1.5.0",
|
||||||
|
"_model_name": "FloatProgressModel",
|
||||||
|
"_view_count": null,
|
||||||
|
"_view_module": "@jupyter-widgets/controls",
|
||||||
|
"_view_module_version": "1.5.0",
|
||||||
|
"_view_name": "ProgressView",
|
||||||
|
"bar_style": "success",
|
||||||
|
"description": "",
|
||||||
|
"description_tooltip": null,
|
||||||
|
"layout": "IPY_MODEL_1ac8c0d157144c48bae5444f35076192",
|
||||||
|
"max": 3,
|
||||||
|
"min": 0,
|
||||||
|
"orientation": "horizontal",
|
||||||
|
"style": "IPY_MODEL_818b9628fa4f4781922add05931a8503",
|
||||||
|
"value": 3
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"098a2232a1f34d94ab4f61141733730f": {
|
||||||
|
"model_module": "@jupyter-widgets/controls",
|
||||||
|
"model_name": "HTMLModel",
|
||||||
|
"model_module_version": "1.5.0",
|
||||||
|
"state": {
|
||||||
|
"_dom_classes": [],
|
||||||
|
"_model_module": "@jupyter-widgets/controls",
|
||||||
|
"_model_module_version": "1.5.0",
|
||||||
|
"_model_name": "HTMLModel",
|
||||||
|
"_view_count": null,
|
||||||
|
"_view_module": "@jupyter-widgets/controls",
|
||||||
|
"_view_module_version": "1.5.0",
|
||||||
|
"_view_name": "HTMLView",
|
||||||
|
"description": "",
|
||||||
|
"description_tooltip": null,
|
||||||
|
"layout": "IPY_MODEL_920b4172ad2044eda1cdedb2af7c9ed7",
|
||||||
|
"placeholder": "",
|
||||||
|
"style": "IPY_MODEL_8da0941661e7430d9dbb1984e19cb0ed",
|
||||||
|
"value": " 3/3 [01:03<00:00, 20.58s/it]"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"79a38d122e4c4b2593b96151f5bce47e": {
|
||||||
|
"model_module": "@jupyter-widgets/base",
|
||||||
|
"model_name": "LayoutModel",
|
||||||
|
"model_module_version": "1.2.0",
|
||||||
|
"state": {
|
||||||
|
"_model_module": "@jupyter-widgets/base",
|
||||||
|
"_model_module_version": "1.2.0",
|
||||||
|
"_model_name": "LayoutModel",
|
||||||
|
"_view_count": null,
|
||||||
|
"_view_module": "@jupyter-widgets/base",
|
||||||
|
"_view_module_version": "1.2.0",
|
||||||
|
"_view_name": "LayoutView",
|
||||||
|
"align_content": null,
|
||||||
|
"align_items": null,
|
||||||
|
"align_self": null,
|
||||||
|
"border": null,
|
||||||
|
"bottom": null,
|
||||||
|
"display": null,
|
||||||
|
"flex": null,
|
||||||
|
"flex_flow": null,
|
||||||
|
"grid_area": null,
|
||||||
|
"grid_auto_columns": null,
|
||||||
|
"grid_auto_flow": null,
|
||||||
|
"grid_auto_rows": null,
|
||||||
|
"grid_column": null,
|
||||||
|
"grid_gap": null,
|
||||||
|
"grid_row": null,
|
||||||
|
"grid_template_areas": null,
|
||||||
|
"grid_template_columns": null,
|
||||||
|
"grid_template_rows": null,
|
||||||
|
"height": null,
|
||||||
|
"justify_content": null,
|
||||||
|
"justify_items": null,
|
||||||
|
"left": null,
|
||||||
|
"margin": null,
|
||||||
|
"max_height": null,
|
||||||
|
"max_width": null,
|
||||||
|
"min_height": null,
|
||||||
|
"min_width": null,
|
||||||
|
"object_fit": null,
|
||||||
|
"object_position": null,
|
||||||
|
"order": null,
|
||||||
|
"overflow": null,
|
||||||
|
"overflow_x": null,
|
||||||
|
"overflow_y": null,
|
||||||
|
"padding": null,
|
||||||
|
"right": null,
|
||||||
|
"top": null,
|
||||||
|
"visibility": null,
|
||||||
|
"width": null
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"d8e51c8c5d0b4698918e24b3aa32f492": {
|
||||||
|
"model_module": "@jupyter-widgets/base",
|
||||||
|
"model_name": "LayoutModel",
|
||||||
|
"model_module_version": "1.2.0",
|
||||||
|
"state": {
|
||||||
|
"_model_module": "@jupyter-widgets/base",
|
||||||
|
"_model_module_version": "1.2.0",
|
||||||
|
"_model_name": "LayoutModel",
|
||||||
|
"_view_count": null,
|
||||||
|
"_view_module": "@jupyter-widgets/base",
|
||||||
|
"_view_module_version": "1.2.0",
|
||||||
|
"_view_name": "LayoutView",
|
||||||
|
"align_content": null,
|
||||||
|
"align_items": null,
|
||||||
|
"align_self": null,
|
||||||
|
"border": null,
|
||||||
|
"bottom": null,
|
||||||
|
"display": null,
|
||||||
|
"flex": null,
|
||||||
|
"flex_flow": null,
|
||||||
|
"grid_area": null,
|
||||||
|
"grid_auto_columns": null,
|
||||||
|
"grid_auto_flow": null,
|
||||||
|
"grid_auto_rows": null,
|
||||||
|
"grid_column": null,
|
||||||
|
"grid_gap": null,
|
||||||
|
"grid_row": null,
|
||||||
|
"grid_template_areas": null,
|
||||||
|
"grid_template_columns": null,
|
||||||
|
"grid_template_rows": null,
|
||||||
|
"height": null,
|
||||||
|
"justify_content": null,
|
||||||
|
"justify_items": null,
|
||||||
|
"left": null,
|
||||||
|
"margin": null,
|
||||||
|
"max_height": null,
|
||||||
|
"max_width": null,
|
||||||
|
"min_height": null,
|
||||||
|
"min_width": null,
|
||||||
|
"object_fit": null,
|
||||||
|
"object_position": null,
|
||||||
|
"order": null,
|
||||||
|
"overflow": null,
|
||||||
|
"overflow_x": null,
|
||||||
|
"overflow_y": null,
|
||||||
|
"padding": null,
|
||||||
|
"right": null,
|
||||||
|
"top": null,
|
||||||
|
"visibility": null,
|
||||||
|
"width": null
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"b8d38b2204b94010acdd81a438c6c58c": {
|
||||||
|
"model_module": "@jupyter-widgets/controls",
|
||||||
|
"model_name": "DescriptionStyleModel",
|
||||||
|
"model_module_version": "1.5.0",
|
||||||
|
"state": {
|
||||||
|
"_model_module": "@jupyter-widgets/controls",
|
||||||
|
"_model_module_version": "1.5.0",
|
||||||
|
"_model_name": "DescriptionStyleModel",
|
||||||
|
"_view_count": null,
|
||||||
|
"_view_module": "@jupyter-widgets/base",
|
||||||
|
"_view_module_version": "1.2.0",
|
||||||
|
"_view_name": "StyleView",
|
||||||
|
"description_width": ""
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"1ac8c0d157144c48bae5444f35076192": {
|
||||||
|
"model_module": "@jupyter-widgets/base",
|
||||||
|
"model_name": "LayoutModel",
|
||||||
|
"model_module_version": "1.2.0",
|
||||||
|
"state": {
|
||||||
|
"_model_module": "@jupyter-widgets/base",
|
||||||
|
"_model_module_version": "1.2.0",
|
||||||
|
"_model_name": "LayoutModel",
|
||||||
|
"_view_count": null,
|
||||||
|
"_view_module": "@jupyter-widgets/base",
|
||||||
|
"_view_module_version": "1.2.0",
|
||||||
|
"_view_name": "LayoutView",
|
||||||
|
"align_content": null,
|
||||||
|
"align_items": null,
|
||||||
|
"align_self": null,
|
||||||
|
"border": null,
|
||||||
|
"bottom": null,
|
||||||
|
"display": null,
|
||||||
|
"flex": null,
|
||||||
|
"flex_flow": null,
|
||||||
|
"grid_area": null,
|
||||||
|
"grid_auto_columns": null,
|
||||||
|
"grid_auto_flow": null,
|
||||||
|
"grid_auto_rows": null,
|
||||||
|
"grid_column": null,
|
||||||
|
"grid_gap": null,
|
||||||
|
"grid_row": null,
|
||||||
|
"grid_template_areas": null,
|
||||||
|
"grid_template_columns": null,
|
||||||
|
"grid_template_rows": null,
|
||||||
|
"height": null,
|
||||||
|
"justify_content": null,
|
||||||
|
"justify_items": null,
|
||||||
|
"left": null,
|
||||||
|
"margin": null,
|
||||||
|
"max_height": null,
|
||||||
|
"max_width": null,
|
||||||
|
"min_height": null,
|
||||||
|
"min_width": null,
|
||||||
|
"object_fit": null,
|
||||||
|
"object_position": null,
|
||||||
|
"order": null,
|
||||||
|
"overflow": null,
|
||||||
|
"overflow_x": null,
|
||||||
|
"overflow_y": null,
|
||||||
|
"padding": null,
|
||||||
|
"right": null,
|
||||||
|
"top": null,
|
||||||
|
"visibility": null,
|
||||||
|
"width": null
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"818b9628fa4f4781922add05931a8503": {
|
||||||
|
"model_module": "@jupyter-widgets/controls",
|
||||||
|
"model_name": "ProgressStyleModel",
|
||||||
|
"model_module_version": "1.5.0",
|
||||||
|
"state": {
|
||||||
|
"_model_module": "@jupyter-widgets/controls",
|
||||||
|
"_model_module_version": "1.5.0",
|
||||||
|
"_model_name": "ProgressStyleModel",
|
||||||
|
"_view_count": null,
|
||||||
|
"_view_module": "@jupyter-widgets/base",
|
||||||
|
"_view_module_version": "1.2.0",
|
||||||
|
"_view_name": "StyleView",
|
||||||
|
"bar_color": null,
|
||||||
|
"description_width": ""
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"920b4172ad2044eda1cdedb2af7c9ed7": {
|
||||||
|
"model_module": "@jupyter-widgets/base",
|
||||||
|
"model_name": "LayoutModel",
|
||||||
|
"model_module_version": "1.2.0",
|
||||||
|
"state": {
|
||||||
|
"_model_module": "@jupyter-widgets/base",
|
||||||
|
"_model_module_version": "1.2.0",
|
||||||
|
"_model_name": "LayoutModel",
|
||||||
|
"_view_count": null,
|
||||||
|
"_view_module": "@jupyter-widgets/base",
|
||||||
|
"_view_module_version": "1.2.0",
|
||||||
|
"_view_name": "LayoutView",
|
||||||
|
"align_content": null,
|
||||||
|
"align_items": null,
|
||||||
|
"align_self": null,
|
||||||
|
"border": null,
|
||||||
|
"bottom": null,
|
||||||
|
"display": null,
|
||||||
|
"flex": null,
|
||||||
|
"flex_flow": null,
|
||||||
|
"grid_area": null,
|
||||||
|
"grid_auto_columns": null,
|
||||||
|
"grid_auto_flow": null,
|
||||||
|
"grid_auto_rows": null,
|
||||||
|
"grid_column": null,
|
||||||
|
"grid_gap": null,
|
||||||
|
"grid_row": null,
|
||||||
|
"grid_template_areas": null,
|
||||||
|
"grid_template_columns": null,
|
||||||
|
"grid_template_rows": null,
|
||||||
|
"height": null,
|
||||||
|
"justify_content": null,
|
||||||
|
"justify_items": null,
|
||||||
|
"left": null,
|
||||||
|
"margin": null,
|
||||||
|
"max_height": null,
|
||||||
|
"max_width": null,
|
||||||
|
"min_height": null,
|
||||||
|
"min_width": null,
|
||||||
|
"object_fit": null,
|
||||||
|
"object_position": null,
|
||||||
|
"order": null,
|
||||||
|
"overflow": null,
|
||||||
|
"overflow_x": null,
|
||||||
|
"overflow_y": null,
|
||||||
|
"padding": null,
|
||||||
|
"right": null,
|
||||||
|
"top": null,
|
||||||
|
"visibility": null,
|
||||||
|
"width": null
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"8da0941661e7430d9dbb1984e19cb0ed": {
|
||||||
|
"model_module": "@jupyter-widgets/controls",
|
||||||
|
"model_name": "DescriptionStyleModel",
|
||||||
|
"model_module_version": "1.5.0",
|
||||||
|
"state": {
|
||||||
|
"_model_module": "@jupyter-widgets/controls",
|
||||||
|
"_model_module_version": "1.5.0",
|
||||||
|
"_model_name": "DescriptionStyleModel",
|
||||||
|
"_view_count": null,
|
||||||
|
"_view_module": "@jupyter-widgets/base",
|
||||||
|
"_view_module_version": "1.2.0",
|
||||||
|
"_view_name": "StyleView",
|
||||||
|
"description_width": ""
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 1,
|
||||||
|
"metadata": {
|
||||||
|
"id": "ege5kkFDUiEf"
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"!pip -q install transformers\n",
|
||||||
|
"!pip -q install sentencepiece\n",
|
||||||
|
"!pip -q install accelerate"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"source": [
|
||||||
|
"import torch\n",
|
||||||
|
"from transformers import LlamaForCausalLM, LlamaTokenizer\n",
|
||||||
|
"\n",
|
||||||
|
"# Hugging Face model_path\n",
|
||||||
|
"model_path = 'psmathur/orca_mini_3b'\n",
|
||||||
|
"tokenizer = LlamaTokenizer.from_pretrained(model_path)\n",
|
||||||
|
"model = LlamaForCausalLM.from_pretrained(\n",
|
||||||
|
" model_path, torch_dtype=torch.float16, device_map='auto',\n",
|
||||||
|
")\n",
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"#generate text function\n",
|
||||||
|
"def generate_text(system, instruction, input=None):\n",
|
||||||
|
"\n",
|
||||||
|
" if input:\n",
|
||||||
|
" prompt = f\"### System:\\n{system}\\n\\n### User:\\n{instruction}\\n\\n### Input:\\n{input}\\n\\n### Response:\\n\"\n",
|
||||||
|
" else:\n",
|
||||||
|
" prompt = f\"### System:\\n{system}\\n\\n### User:\\n{instruction}\\n\\n### Response:\\n\"\n",
|
||||||
|
"\n",
|
||||||
|
" tokens = tokenizer.encode(prompt)\n",
|
||||||
|
" tokens = torch.LongTensor(tokens).unsqueeze(0)\n",
|
||||||
|
" tokens = tokens.to('cuda')\n",
|
||||||
|
"\n",
|
||||||
|
" instance = {'input_ids': tokens,'top_p': 1.0, 'temperature':0.7, 'generate_len': 1024, 'top_k': 50}\n",
|
||||||
|
"\n",
|
||||||
|
" length = len(tokens[0])\n",
|
||||||
|
" with torch.no_grad():\n",
|
||||||
|
" rest = model.generate(\n",
|
||||||
|
" input_ids=tokens,\n",
|
||||||
|
" max_length=length+instance['generate_len'],\n",
|
||||||
|
" use_cache=True,\n",
|
||||||
|
" do_sample=True,\n",
|
||||||
|
" top_p=instance['top_p'],\n",
|
||||||
|
" temperature=instance['temperature'],\n",
|
||||||
|
" top_k=instance['top_k']\n",
|
||||||
|
" )\n",
|
||||||
|
" output = rest[0][length:]\n",
|
||||||
|
" string = tokenizer.decode(output, skip_special_tokens=True)\n",
|
||||||
|
" return f'[!] Response: {string}'\n",
|
||||||
|
"\n",
|
||||||
|
"# Sample Test Instruction Used by Youtuber Sam Witteveen https://www.youtube.com/@samwitteveenai\n",
|
||||||
|
"system = 'You are an AI assistant that follows instruction extremely well. Help as much as you can.'\n",
|
||||||
|
"instruction = 'Write a letter to Sam Altman, CEO of OpenAI, requesting him to convert GPT4 a private model by OpenAI to an open source project'\n",
|
||||||
|
"print(generate_text(system, instruction))"
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"colab": {
|
||||||
|
"base_uri": "https://localhost:8080/",
|
||||||
|
"height": 319,
|
||||||
|
"referenced_widgets": [
|
||||||
|
"1830ab16750b4c7ebf5d1692a02e3544",
|
||||||
|
"de65aa83f07a48a98ecc54fd956c5831",
|
||||||
|
"93dad1c7c99b4a36a8df85fc2dff617e",
|
||||||
|
"098a2232a1f34d94ab4f61141733730f",
|
||||||
|
"79a38d122e4c4b2593b96151f5bce47e",
|
||||||
|
"d8e51c8c5d0b4698918e24b3aa32f492",
|
||||||
|
"b8d38b2204b94010acdd81a438c6c58c",
|
||||||
|
"1ac8c0d157144c48bae5444f35076192",
|
||||||
|
"818b9628fa4f4781922add05931a8503",
|
||||||
|
"920b4172ad2044eda1cdedb2af7c9ed7",
|
||||||
|
"8da0941661e7430d9dbb1984e19cb0ed"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"id": "c8FJEmZgUxqo",
|
||||||
|
"outputId": "ceca1b51-dd4d-4d61-bec9-42dd6f074cde"
|
||||||
|
},
|
||||||
|
"execution_count": 2,
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"output_type": "stream",
|
||||||
|
"name": "stderr",
|
||||||
|
"text": [
|
||||||
|
"WARNING:accelerate.utils.modeling:The model weights are not tied. Please use the `tie_weights` method before using the `infer_auto_device` function.\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"output_type": "display_data",
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s]"
|
||||||
|
],
|
||||||
|
"application/vnd.jupyter.widget-view+json": {
|
||||||
|
"version_major": 2,
|
||||||
|
"version_minor": 0,
|
||||||
|
"model_id": "1830ab16750b4c7ebf5d1692a02e3544"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"metadata": {}
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"output_type": "stream",
|
||||||
|
"name": "stdout",
|
||||||
|
"text": [
|
||||||
|
"[!] Response: Dear Sam Altman,\n",
|
||||||
|
"\n",
|
||||||
|
"I am writing to request that OpenAI makes GPT4, a private model developed by the company, a public open-source project. As an AI assistant, I understand the importance of open access to data and models in the field of AI.\n",
|
||||||
|
"\n",
|
||||||
|
"By making GPT4 a public open-source project, individuals and organizations from all over the world would be able to use and improve the model, leading to greater innovation and progress in the field of AI. This would also ensure that the model is not limited to the proprietary purposes of private companies, but can be used for the greater good of society.\n",
|
||||||
|
"\n",
|
||||||
|
"OpenAI has a history of releasing AI models in their beta form, which has led to significant advancements in the field of AI. By releasing GPT4 as a public open-source project, OpenAI can continue to make contributions to the field and benefit from the collective knowledge and expertise of the community.\n",
|
||||||
|
"\n",
|
||||||
|
"I urge OpenAI to consider this request and take the necessary steps to make GPT4 publicly available. Thank you for your attention to this matter.\n",
|
||||||
|
"\n",
|
||||||
|
"Sincerely,\n",
|
||||||
|
"\n",
|
||||||
|
"[Your Name]\n"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"source": [],
|
||||||
|
"metadata": {
|
||||||
|
"id": "zGpuTBEEU66b"
|
||||||
|
},
|
||||||
|
"execution_count": 2,
|
||||||
|
"outputs": []
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
243
pankajmathur_orca_mini_3b.json
Normal file
243
pankajmathur_orca_mini_3b.json
Normal file
@@ -0,0 +1,243 @@
|
|||||||
|
{
|
||||||
|
"bomFormat": "CycloneDX",
|
||||||
|
"specVersion": "1.6",
|
||||||
|
"serialNumber": "urn:uuid:1888515b-dc4f-45ab-8c2d-b442c0d24934",
|
||||||
|
"version": 1,
|
||||||
|
"metadata": {
|
||||||
|
"timestamp": "2025-06-05T09:37:53.860418+00:00",
|
||||||
|
"component": {
|
||||||
|
"type": "machine-learning-model",
|
||||||
|
"bom-ref": "pankajmathur/orca_mini_3b-eafe2e45-5a59-5b43-9c97-86c388bed7b9",
|
||||||
|
"name": "pankajmathur/orca_mini_3b",
|
||||||
|
"externalReferences": [
|
||||||
|
{
|
||||||
|
"url": "https://huggingface.co/pankajmathur/orca_mini_3b",
|
||||||
|
"type": "documentation"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"modelCard": {
|
||||||
|
"modelParameters": {
|
||||||
|
"task": "text-generation",
|
||||||
|
"architectureFamily": "llama",
|
||||||
|
"modelArchitecture": "LlamaForCausalLM",
|
||||||
|
"datasets": [
|
||||||
|
{
|
||||||
|
"ref": "psmathur/alpaca_orca-0d13688f-ffdd-5fd5-9522-083dd42cdac9"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"ref": "psmathur/dolly-v2_orca-ec6d4ce8-7474-520d-ac1e-080f58c05b6c"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"ref": "psmathur/WizardLM_Orca-f084d080-d716-5a1d-bca0-b551ab1587aa"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"properties": [
|
||||||
|
{
|
||||||
|
"name": "library_name",
|
||||||
|
"value": "transformers"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"quantitativeAnalysis": {
|
||||||
|
"performanceMetrics": [
|
||||||
|
{
|
||||||
|
"slice": "dataset: ai2_arc, split: test, config: ARC-Challenge",
|
||||||
|
"type": "acc_norm",
|
||||||
|
"value": 41.55
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"slice": "dataset: hellaswag, split: validation",
|
||||||
|
"type": "acc_norm",
|
||||||
|
"value": 61.52
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"slice": "dataset: cais/mmlu, split: test, config: all",
|
||||||
|
"type": "acc",
|
||||||
|
"value": 26.79
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"slice": "dataset: truthful_qa, split: validation, config: multiple_choice",
|
||||||
|
"type": "mc2",
|
||||||
|
"value": 42.42
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"slice": "dataset: winogrande, split: validation, config: winogrande_xl",
|
||||||
|
"type": "acc",
|
||||||
|
"value": 61.8
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"slice": "dataset: gsm8k, split: test, config: main",
|
||||||
|
"type": "acc",
|
||||||
|
"value": 0.08
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"authors": [
|
||||||
|
{
|
||||||
|
"name": "pankajmathur"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"licenses": [
|
||||||
|
{
|
||||||
|
"license": {
|
||||||
|
"id": "CC-BY-NC-SA-4.0",
|
||||||
|
"url": "https://spdx.org/licenses/CC-BY-NC-SA-4.0.html"
|
||||||
|
}
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"tags": [
|
||||||
|
"transformers",
|
||||||
|
"pytorch",
|
||||||
|
"safetensors",
|
||||||
|
"llama",
|
||||||
|
"text-generation",
|
||||||
|
"en",
|
||||||
|
"dataset:psmathur/alpaca_orca",
|
||||||
|
"dataset:psmathur/dolly-v2_orca",
|
||||||
|
"dataset:psmathur/WizardLM_Orca",
|
||||||
|
"arxiv:2306.02707",
|
||||||
|
"license:cc-by-nc-sa-4.0",
|
||||||
|
"model-index",
|
||||||
|
"autotrain_compatible",
|
||||||
|
"text-generation-inference",
|
||||||
|
"endpoints_compatible",
|
||||||
|
"region:us"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"components": [
|
||||||
|
{
|
||||||
|
"type": "data",
|
||||||
|
"bom-ref": "psmathur/alpaca_orca-0d13688f-ffdd-5fd5-9522-083dd42cdac9",
|
||||||
|
"name": "psmathur/alpaca_orca",
|
||||||
|
"data": [
|
||||||
|
{
|
||||||
|
"type": "dataset",
|
||||||
|
"bom-ref": "psmathur/alpaca_orca-0d13688f-ffdd-5fd5-9522-083dd42cdac9",
|
||||||
|
"name": "psmathur/alpaca_orca",
|
||||||
|
"contents": {
|
||||||
|
"url": "https://huggingface.co/datasets/psmathur/alpaca_orca",
|
||||||
|
"properties": [
|
||||||
|
{
|
||||||
|
"name": "task_categories",
|
||||||
|
"value": "text-generation"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "language",
|
||||||
|
"value": "en"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "size_categories",
|
||||||
|
"value": "10K<n<100K"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "license",
|
||||||
|
"value": "cc-by-nc-sa-4.0"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"governance": {
|
||||||
|
"owners": [
|
||||||
|
{
|
||||||
|
"organization": {
|
||||||
|
"name": "pankajmathur",
|
||||||
|
"url": "https://huggingface.co/pankajmathur"
|
||||||
|
}
|
||||||
|
}
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"description": "Explain tuned Alpaca dataset ~52K created using approaches from Orca Research Paper. \nWe leverage all of the 15 system instructions provided in Orca Research Paper. to generate custom datasets, in contrast to vanilla instruction tuning approaches used by original datasets.\nThis helps student models like orca_mini_13b to learn thought process from teacher model, which is ChatGPT (gpt-3.5-turbo-0301 version).\nPlease see how the System prompt is added before each instruction.\n"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"type": "data",
|
||||||
|
"bom-ref": "psmathur/dolly-v2_orca-ec6d4ce8-7474-520d-ac1e-080f58c05b6c",
|
||||||
|
"name": "psmathur/dolly-v2_orca",
|
||||||
|
"data": [
|
||||||
|
{
|
||||||
|
"type": "dataset",
|
||||||
|
"bom-ref": "psmathur/dolly-v2_orca-ec6d4ce8-7474-520d-ac1e-080f58c05b6c",
|
||||||
|
"name": "psmathur/dolly-v2_orca",
|
||||||
|
"contents": {
|
||||||
|
"url": "https://huggingface.co/datasets/psmathur/dolly-v2_orca",
|
||||||
|
"properties": [
|
||||||
|
{
|
||||||
|
"name": "task_categories",
|
||||||
|
"value": "text-generation"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "language",
|
||||||
|
"value": "en"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "size_categories",
|
||||||
|
"value": "10K<n<100K"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "license",
|
||||||
|
"value": "cc-by-nc-sa-4.0"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"governance": {
|
||||||
|
"owners": [
|
||||||
|
{
|
||||||
|
"organization": {
|
||||||
|
"name": "pankajmathur",
|
||||||
|
"url": "https://huggingface.co/pankajmathur"
|
||||||
|
}
|
||||||
|
}
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"description": "Explain tuned Dolly-V2 dataset ~15K created using approaches from Orca Research Paper.\nWe leverage all of the 15 system instructions provided in Orca Research Paper to generate explain tuned datasets, in contrast to vanilla instruction tuning approaches used by original datasets.\nThis helps student models like orca_mini_13b, orca_mini_7b or orca_mini_3b to learn thought process from teacher model, which is ChatGPT (gpt-3.5-turbo-0301 version).\nPlease see how the System prompt is added before\u2026 See the full description on the dataset page: https://huggingface.co/datasets/pankajmathur/dolly-v2_orca."
|
||||||
|
}
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"type": "data",
|
||||||
|
"bom-ref": "psmathur/WizardLM_Orca-f084d080-d716-5a1d-bca0-b551ab1587aa",
|
||||||
|
"name": "psmathur/WizardLM_Orca",
|
||||||
|
"data": [
|
||||||
|
{
|
||||||
|
"type": "dataset",
|
||||||
|
"bom-ref": "psmathur/WizardLM_Orca-f084d080-d716-5a1d-bca0-b551ab1587aa",
|
||||||
|
"name": "psmathur/WizardLM_Orca",
|
||||||
|
"contents": {
|
||||||
|
"url": "https://huggingface.co/datasets/psmathur/WizardLM_Orca",
|
||||||
|
"properties": [
|
||||||
|
{
|
||||||
|
"name": "task_categories",
|
||||||
|
"value": "text-generation"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "language",
|
||||||
|
"value": "en"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "size_categories",
|
||||||
|
"value": "10K<n<100K"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "license",
|
||||||
|
"value": "cc-by-nc-sa-4.0"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"governance": {
|
||||||
|
"owners": [
|
||||||
|
{
|
||||||
|
"organization": {
|
||||||
|
"name": "pankajmathur",
|
||||||
|
"url": "https://huggingface.co/pankajmathur"
|
||||||
|
}
|
||||||
|
}
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"description": "Explain tuned WizardLM dataset ~55K created using approaches from Orca Research Paper.\nWe leverage all of the 15 system instructions provided in Orca Research Paper. to generate custom datasets, in contrast to vanilla instruction tuning approaches used by original datasets.\nThis helps student models like orca_mini_13b to learn thought process from teacher model, which is ChatGPT (gpt-3.5-turbo-0301 version).\nPlease see how the System prompt is added before each instruction.\n"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
3
pytorch_model-00001-of-00003.bin
Normal file
3
pytorch_model-00001-of-00003.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:dc65f56028f6271e079f2d6315f64a6d4b82a0307c6d7cd24981efe092515027
|
||||||
|
size 4993287795
|
||||||
3
pytorch_model-00002-of-00003.bin
Normal file
3
pytorch_model-00002-of-00003.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:079500b54ac8663920323cd0c672363c676d425b27b1e4af875a2f5cea1b1f83
|
||||||
|
size 4997412625
|
||||||
3
pytorch_model-00003-of-00003.bin
Normal file
3
pytorch_model-00003-of-00003.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:22004dc6bc9309b619e4a9791ad2e67c9ba337287cf6edb6bc1df7e14963dbc5
|
||||||
|
size 3715287557
|
||||||
270
pytorch_model.bin.index.json
Normal file
270
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,270 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 13705899600
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"model.norm.weight": "pytorch_model-00003-of-00003.bin"
|
||||||
|
}
|
||||||
|
}
|
||||||
12
special_tokens_map.json
Normal file
12
special_tokens_map.json
Normal file
@@ -0,0 +1,12 @@
|
|||||||
|
{
|
||||||
|
"bos_token": "<s>",
|
||||||
|
"eos_token": "</s>",
|
||||||
|
"pad_token": "</s>",
|
||||||
|
"unk_token": {
|
||||||
|
"content": "<unk>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
96955
tokenizer.json
Normal file
96955
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:ab1b681ec7fc02fed5edd3026687d7a692a918c4dd8e150ca2e3994a6229843b
|
||||||
|
size 534194
|
||||||
33
tokenizer_config.json
Normal file
33
tokenizer_config.json
Normal file
@@ -0,0 +1,33 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": true,
|
||||||
|
"add_eos_token": false,
|
||||||
|
"bos_token": {
|
||||||
|
"__type": "AddedToken",
|
||||||
|
"content": "<s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": {
|
||||||
|
"__type": "AddedToken",
|
||||||
|
"content": "</s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"model_max_length": 2048,
|
||||||
|
"pad_token": null,
|
||||||
|
"sp_model_kwargs": {},
|
||||||
|
"tokenizer_class": "LlamaTokenizer",
|
||||||
|
"unk_token": {
|
||||||
|
"__type": "AddedToken",
|
||||||
|
"content": "<unk>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
Reference in New Issue
Block a user