初始化项目，由ModelHub XC社区提供模型
Model: h2oai/h2ogpt-gm-oasst1-en-1024-12b Source: Original Platform
This commit is contained in:
ModelHub XC
34
.gitattributes
vendored
Normal file
34
.gitattributes
vendored
Normal file
@@ -0,0 +1,34 @@
|
||||
*.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
|
||||
*.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
|
||||
199
README.md
Normal file
199
README.md
Normal file
@@ -0,0 +1,199 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
library_name: transformers
|
||||
tags:
|
||||
- gpt
|
||||
- llm
|
||||
- large language model
|
||||
- h2o-llmstudio
|
||||
inference: false
|
||||
thumbnail: >-
|
||||
https://h2o.ai/etc.clientlibs/h2o/clientlibs/clientlib-site/resources/images/favicon.ico
|
||||
license: apache-2.0
|
||||
datasets:
|
||||
- OpenAssistant/oasst1
|
||||
---
|
||||
# Model Card
|
||||
## Summary
|
||||
|
||||
This model was trained using [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio).
|
||||
- Base model: [EleutherAI/pythia-12b-deduped](https://huggingface.co/EleutherAI/pythia-12b-deduped)
|
||||
- Dataset preparation: [OpenAssistant/oasst1](https://github.com/h2oai/h2o-llmstudio/blob/1935d84d9caafed3ee686ad2733eb02d2abfce57/app_utils/utils.py#LL1896C5-L1896C28)
|
||||
|
||||
|
||||
## Usage
|
||||
|
||||
To use the model with the `transformers` library on a machine with GPUs, first make sure you have the `transformers` and `torch` libraries installed.
|
||||
|
||||
```bash
|
||||
pip install transformers==4.28.1
|
||||
pip install torch==2.0.0
|
||||
```
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import pipeline
|
||||
|
||||
generate_text = pipeline(
|
||||
model="h2oai/h2ogpt-gm-oasst1-en-1024-12b",
|
||||
torch_dtype=torch.float16,
|
||||
trust_remote_code=True,
|
||||
device_map={"": "cuda:0"},
|
||||
)
|
||||
|
||||
res = generate_text(
|
||||
"Why is drinking water so healthy?",
|
||||
min_new_tokens=2,
|
||||
max_new_tokens=256,
|
||||
do_sample=False,
|
||||
num_beams=2,
|
||||
temperature=float(0.3),
|
||||
repetition_penalty=float(1.2),
|
||||
)
|
||||
print(res[0]["generated_text"])
|
||||
```
|
||||
|
||||
You can print a sample prompt after the preprocessing step to see how it is feed to the tokenizer:
|
||||
|
||||
```python
|
||||
print(generate_text.preprocess("Why is drinking water so healthy?")["prompt_text"])
|
||||
```
|
||||
|
||||
```bash
|
||||
<|prompt|>Why is drinking water so healthy?<|endoftext|><|answer|>
|
||||
```
|
||||
|
||||
Alternatively, if you prefer to not use `trust_remote_code=True` you can download [h2oai_pipeline.py](h2oai_pipeline.py), store it alongside your notebook, and construct the pipeline yourself from the loaded model and tokenizer:
|
||||
|
||||
|
||||
```python
|
||||
import torch
|
||||
from h2oai_pipeline import H2OTextGenerationPipeline
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(
|
||||
"h2oai/h2ogpt-gm-oasst1-en-1024-12b",
|
||||
padding_side="left"
|
||||
)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
"h2oai/h2ogpt-gm-oasst1-en-1024-12b",
|
||||
torch_dtype=torch.float16,
|
||||
device_map={"": "cuda:0"}
|
||||
)
|
||||
generate_text = H2OTextGenerationPipeline(model=model, tokenizer=tokenizer)
|
||||
|
||||
res = generate_text(
|
||||
"Why is drinking water so healthy?",
|
||||
min_new_tokens=2,
|
||||
max_new_tokens=256,
|
||||
do_sample=False,
|
||||
num_beams=2,
|
||||
temperature=float(0.3),
|
||||
repetition_penalty=float(1.2),
|
||||
)
|
||||
print(res[0]["generated_text"])
|
||||
```
|
||||
|
||||
|
||||
You may also construct the pipeline from the loaded model and tokenizer yourself and consider the preprocessing steps:
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
|
||||
model_name = "h2oai/h2ogpt-gm-oasst1-en-1024-12b" # either local folder or huggingface model name
|
||||
# Important: The prompt needs to be in the same format the model was trained with.
|
||||
# You can find an example prompt in the experiment logs.
|
||||
prompt = "<|prompt|>How are you?<|endoftext|><|answer|>"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
model = AutoModelForCausalLM.from_pretrained(model_name)
|
||||
model.cuda().eval()
|
||||
inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to("cuda")
|
||||
|
||||
# generate configuration can be modified to your needs
|
||||
tokens = model.generate(
|
||||
**inputs,
|
||||
min_new_tokens=2,
|
||||
max_new_tokens=256,
|
||||
do_sample=False,
|
||||
num_beams=2,
|
||||
temperature=float(0.3),
|
||||
repetition_penalty=float(1.2),
|
||||
)[0]
|
||||
|
||||
tokens = tokens[inputs["input_ids"].shape[1]:]
|
||||
answer = tokenizer.decode(tokens, skip_special_tokens=True)
|
||||
print(answer)
|
||||
```
|
||||
|
||||
## Model Architecture
|
||||
|
||||
```
|
||||
GPTNeoXForCausalLM(
|
||||
(gpt_neox): GPTNeoXModel(
|
||||
(embed_in): Embedding(50688, 5120)
|
||||
(layers): ModuleList(
|
||||
(0-35): 36 x GPTNeoXLayer(
|
||||
(input_layernorm): LayerNorm((5120,), eps=1e-05, elementwise_affine=True)
|
||||
(post_attention_layernorm): LayerNorm((5120,), eps=1e-05, elementwise_affine=True)
|
||||
(attention): GPTNeoXAttention(
|
||||
(rotary_emb): RotaryEmbedding()
|
||||
(query_key_value): Linear(in_features=5120, out_features=15360, bias=True)
|
||||
(dense): Linear(in_features=5120, out_features=5120, bias=True)
|
||||
)
|
||||
(mlp): GPTNeoXMLP(
|
||||
(dense_h_to_4h): Linear(in_features=5120, out_features=20480, bias=True)
|
||||
(dense_4h_to_h): Linear(in_features=20480, out_features=5120, bias=True)
|
||||
(act): GELUActivation()
|
||||
)
|
||||
)
|
||||
)
|
||||
(final_layer_norm): LayerNorm((5120,), eps=1e-05, elementwise_affine=True)
|
||||
)
|
||||
(embed_out): Linear(in_features=5120, out_features=50688, bias=False)
|
||||
)
|
||||
```
|
||||
|
||||
## Model Configuration
|
||||
|
||||
This model was trained using H2O LLM Studio and with the configuration in [cfg.yaml](cfg.yaml). Visit [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio) to learn how to train your own large language models.
|
||||
|
||||
|
||||
## Model Validation
|
||||
|
||||
Model validation results using [EleutherAI lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness).
|
||||
|
||||
```bash
|
||||
CUDA_VISIBLE_DEVICES=0 python main.py --model hf-causal-experimental --model_args pretrained=h2oai/h2ogpt-gm-oasst1-en-1024-12b --tasks openbookqa,arc_easy,winogrande,hellaswag,arc_challenge,piqa,boolq --device cuda &> eval.log
|
||||
```
|
||||
|
||||
| Task |Version| Metric |Value | |Stderr|
|
||||
|-------------|------:|--------|-----:|---|-----:|
|
||||
|arc_challenge| 0|acc |0.3345|± |0.0138|
|
||||
| | |acc_norm|0.3754|± |0.0142|
|
||||
|arc_easy | 0|acc |0.6435|± |0.0098|
|
||||
| | |acc_norm|0.5800|± |0.0101|
|
||||
|boolq | 1|acc |0.5098|± |0.0087|
|
||||
|hellaswag | 0|acc |0.5150|± |0.0050|
|
||||
| | |acc_norm|0.6951|± |0.0046|
|
||||
|openbookqa | 0|acc |0.3080|± |0.0207|
|
||||
| | |acc_norm|0.3980|± |0.0219|
|
||||
|piqa | 0|acc |0.7704|± |0.0098|
|
||||
| | |acc_norm|0.7704|± |0.0098|
|
||||
|winogrande | 0|acc |0.6622|± |0.0133|
|
||||
|
||||
|
||||
## Disclaimer
|
||||
|
||||
Please read this disclaimer carefully before using the large language model provided in this repository. Your use of the model signifies your agreement to the following terms and conditions.
|
||||
|
||||
- Biases and Offensiveness: The large language model is trained on a diverse range of internet text data, which may contain biased, racist, offensive, or otherwise inappropriate content. By using this model, you acknowledge and accept that the generated content may sometimes exhibit biases or produce content that is offensive or inappropriate. The developers of this repository do not endorse, support, or promote any such content or viewpoints.
|
||||
- Limitations: The large language model is an AI-based tool and not a human. It may produce incorrect, nonsensical, or irrelevant responses. It is the user's responsibility to critically evaluate the generated content and use it at their discretion.
|
||||
- Use at Your Own Risk: Users of this large language model must assume full responsibility for any consequences that may arise from their use of the tool. The developers and contributors of this repository shall not be held liable for any damages, losses, or harm resulting from the use or misuse of the provided model.
|
||||
- Ethical Considerations: Users are encouraged to use the large language model responsibly and ethically. By using this model, you agree not to use it for purposes that promote hate speech, discrimination, harassment, or any form of illegal or harmful activities.
|
||||
- Reporting Issues: If you encounter any biased, offensive, or otherwise inappropriate content generated by the large language model, please report it to the repository maintainers through the provided channels. Your feedback will help improve the model and mitigate potential issues.
|
||||
- Changes to this Disclaimer: The developers of this repository reserve the right to modify or update this disclaimer at any time without prior notice. It is the user's responsibility to periodically review the disclaimer to stay informed about any changes.
|
||||
|
||||
By using the large language model provided in this repository, you agree to accept and comply with the terms and conditions outlined in this disclaimer. If you do not agree with any part of this disclaimer, you should refrain from using the model and any content generated by it.
|
||||
90
cfg.yaml
Normal file
90
cfg.yaml
Normal file
@@ -0,0 +1,90 @@
|
||||
architecture:
|
||||
backbone_dtype: float16
|
||||
force_embedding_gradients: false
|
||||
gradient_checkpointing: true
|
||||
intermediate_dropout: 0.0
|
||||
pretrained: true
|
||||
pretrained_weights: ''
|
||||
augmentation:
|
||||
random_parent_probability: 0.1
|
||||
skip_parent_probability: 0.0
|
||||
token_mask_probability: 0.0
|
||||
dataset:
|
||||
add_eos_token_to_answer: true
|
||||
add_eos_token_to_prompt: true
|
||||
answer_column: output
|
||||
data_sample: 1.0
|
||||
data_sample_choice:
|
||||
- Train
|
||||
- Validation
|
||||
mask_prompt_labels: false
|
||||
parent_id_column: parent_id
|
||||
prompt_column:
|
||||
- instruction
|
||||
text_answer_separator: <|answer|>
|
||||
text_prompt_start: <|prompt|>
|
||||
train_dataframe: data/user/oasst/train_full_allrank.pq
|
||||
validation_dataframe: data/user/oasst/gpt4_val_v0.csv
|
||||
validation_size: 0.01
|
||||
validation_strategy: custom
|
||||
environment:
|
||||
compile_model: false
|
||||
find_unused_parameters: false
|
||||
gpus:
|
||||
- '0'
|
||||
- '1'
|
||||
- '2'
|
||||
- '3'
|
||||
mixed_precision: true
|
||||
number_of_workers: 8
|
||||
seed: -1
|
||||
trust_remote_code: false
|
||||
use_fsdp: false
|
||||
experiment_name: h2ogpt-gm-oasst1-en-1024-12b
|
||||
llm_backbone: EleutherAI/pythia-12b-deduped
|
||||
logging:
|
||||
logger: Neptune
|
||||
neptune_project: Zoo/h2o-llm
|
||||
number_of_texts: 10
|
||||
output_directory: output/user/h2ogpt-gm-oasst1-en-1024-12b/
|
||||
prediction:
|
||||
batch_size_inference: 0
|
||||
do_sample: false
|
||||
max_length_inference: 256
|
||||
metric: GPT3.5
|
||||
min_length_inference: 2
|
||||
num_beams: 2
|
||||
repetition_penalty: 1.2
|
||||
stop_tokens: ''
|
||||
temperature: 0.3
|
||||
problem_type: text_causal_language_modeling
|
||||
tokenizer:
|
||||
add_prefix_space: false
|
||||
add_prompt_answer_tokens: false
|
||||
max_length: 1024
|
||||
max_length_answer: 512
|
||||
max_length_prompt: 512
|
||||
padding_quantile: 1.0
|
||||
training:
|
||||
batch_size: 16
|
||||
differential_learning_rate: 1.0e-05
|
||||
differential_learning_rate_layers: []
|
||||
drop_last_batch: true
|
||||
epochs: 2
|
||||
evaluate_before_training: true
|
||||
evaluation_epochs: 0.5
|
||||
grad_accumulation: 1
|
||||
gradient_clip: 0.0
|
||||
learning_rate: 0.0005
|
||||
lora: true
|
||||
lora_alpha: 33
|
||||
lora_dropout: 0.05
|
||||
lora_r: 16
|
||||
lora_target_modules: ''
|
||||
loss_function: CrossEntropy
|
||||
optimizer: AdamW
|
||||
save_best_checkpoint: false
|
||||
schedule: Cosine
|
||||
train_validation_data: false
|
||||
warmup_epochs: 0.0
|
||||
weight_decay: 0.0
|
||||
33
config.json
Normal file
33
config.json
Normal file
@@ -0,0 +1,33 @@
|
||||
{
|
||||
"_name_or_path": "EleutherAI/pythia-12b-deduped",
|
||||
"architectures": [
|
||||
"GPTNeoXForCausalLM"
|
||||
],
|
||||
"attention_probs_dropout_prob": 0.0,
|
||||
"bos_token_id": 0,
|
||||
"custom_pipelines": {
|
||||
"text-generation": {
|
||||
"impl": "h2oai_pipeline.H2OTextGenerationPipeline",
|
||||
"pt": "AutoModelForCausalLM"
|
||||
}
|
||||
},
|
||||
"eos_token_id": 0,
|
||||
"hidden_act": "gelu",
|
||||
"hidden_dropout_prob": 0.0,
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 20480,
|
||||
"layer_norm_eps": 1e-05,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "gpt_neox",
|
||||
"num_attention_heads": 40,
|
||||
"num_hidden_layers": 36,
|
||||
"rotary_emb_base": 10000,
|
||||
"rotary_pct": 0.25,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.28.1",
|
||||
"use_cache": true,
|
||||
"use_parallel_residual": true,
|
||||
"vocab_size": 50688
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 0,
|
||||
"eos_token_id": 0,
|
||||
"transformers_version": "4.28.1"
|
||||
}
|
||||
42
h2oai_pipeline.py
Normal file
42
h2oai_pipeline.py
Normal file
@@ -0,0 +1,42 @@
|
||||
from transformers import TextGenerationPipeline
|
||||
from transformers.pipelines.text_generation import ReturnType
|
||||
|
||||
STYLE = "<|prompt|>{instruction}<|endoftext|><|answer|>"
|
||||
|
||||
|
||||
class H2OTextGenerationPipeline(TextGenerationPipeline):
|
||||
def __init__(self, *args, **kwargs):
|
||||
super().__init__(*args, **kwargs)
|
||||
self.prompt = STYLE
|
||||
|
||||
def preprocess(
|
||||
self, prompt_text, prefix="", handle_long_generation=None, **generate_kwargs
|
||||
):
|
||||
prompt_text = self.prompt.format(instruction=prompt_text)
|
||||
return super().preprocess(
|
||||
prompt_text,
|
||||
prefix=prefix,
|
||||
handle_long_generation=handle_long_generation,
|
||||
**generate_kwargs,
|
||||
)
|
||||
|
||||
def postprocess(
|
||||
self,
|
||||
model_outputs,
|
||||
return_type=ReturnType.FULL_TEXT,
|
||||
clean_up_tokenization_spaces=True,
|
||||
):
|
||||
records = super().postprocess(
|
||||
model_outputs,
|
||||
return_type=return_type,
|
||||
clean_up_tokenization_spaces=clean_up_tokenization_spaces,
|
||||
)
|
||||
for rec in records:
|
||||
rec["generated_text"] = (
|
||||
rec["generated_text"]
|
||||
.split("<|answer|>")[1]
|
||||
.strip()
|
||||
.split("<|prompt|>")[0]
|
||||
.strip()
|
||||
)
|
||||
return records
|
||||
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 sha256:06be28b6807e92346529b50533097144a528a87ad51b1e6ba60b280495de9a83
|
||||
size 10025460694
|
||||
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 sha256:1980c36ea4a5675f7d45b7379eaee43a84cec1f4c48e17c04990f62789aed33c
|
||||
size 9921691824
|
||||
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:f15ecd3684c7ac2d19cc487daab0113f0624641c9031b5235eff562c453ac7d6
|
||||
size 3896184559
|
||||
551
pytorch_model.bin.index.json
Normal file
551
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,551 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 23711021384.0
|
||||
},
|
||||
"weight_map": {
|
||||
"embed_out.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.embed_in.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.0.attention.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.0.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.1.attention.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.1.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.10.attention.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.10.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.11.attention.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.11.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.12.attention.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.13.attention.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.14.attention.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.15.attention.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.16.attention.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.16.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.16.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.16.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.16.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.16.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.16.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.16.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.17.attention.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.17.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.17.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.17.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.17.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.17.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.17.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.17.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.18.attention.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.18.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.18.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.18.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.18.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.18.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.18.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.18.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.19.attention.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.19.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.19.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.19.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.19.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.19.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.19.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.19.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.2.attention.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.2.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.20.attention.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.20.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.20.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.20.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.20.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.20.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.20.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.20.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.21.attention.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.21.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.21.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.21.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.21.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.21.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.21.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.21.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.22.attention.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.22.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.22.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.22.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.22.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.22.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.22.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.23.attention.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.23.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.23.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.23.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.23.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.23.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.23.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.24.attention.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.24.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.24.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.24.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.25.attention.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.25.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.25.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.26.attention.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.26.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.27.attention.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.27.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.28.attention.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.28.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.28.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.28.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.28.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.28.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.28.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.28.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.28.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.29.attention.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.29.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.29.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.29.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.29.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.29.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.29.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.29.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.29.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.3.attention.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.3.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.30.attention.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.30.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.30.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.30.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.30.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.30.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.30.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.30.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.30.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"gpt_neox.layers.31.attention.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.31.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.31.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.31.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.31.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.31.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.31.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.31.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.31.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.32.attention.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.32.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.32.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.32.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.32.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.32.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.32.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.32.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.32.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.32.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.32.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.32.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.32.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.33.attention.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.33.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.33.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.33.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.33.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.33.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.33.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.33.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.33.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.33.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.33.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.33.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.33.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.34.attention.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.34.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.34.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.34.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.34.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.34.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.34.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.34.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.34.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.34.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.34.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.34.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.34.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.35.attention.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.35.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.35.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.35.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.35.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.35.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.35.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.35.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.35.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.35.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.35.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.35.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.35.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"gpt_neox.layers.4.attention.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.4.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.5.attention.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.5.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.6.attention.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.6.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.7.attention.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.7.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.8.attention.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.8.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.9.attention.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.9.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin"
|
||||
}
|
||||
}
|
||||
8
special_tokens_map.json
Normal file
8
special_tokens_map.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"bos_token": "<|endoftext|>",
|
||||
"cls_token": "<|endoftext|>",
|
||||
"eos_token": "<|endoftext|>",
|
||||
"pad_token": "<|endoftext|>",
|
||||
"sep_token": "<|endoftext|>",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
100529
tokenizer.json
Normal file
100529
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
9
tokenizer_config.json
Normal file
9
tokenizer_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"bos_token": "<|endoftext|>",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"tokenizer_class": "GPTNeoXTokenizer",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
Reference in New Issue
Block a user