初始化项目，由ModelHub XC社区提供模型
Model: VAIBHAV22334455/JARVIS 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
|
||||
221
README.md
Normal file
221
README.md
Normal file
@@ -0,0 +1,221 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
- hi
|
||||
license: apache-2.0
|
||||
datasets:
|
||||
- fka/awesome-chatgpt-prompts
|
||||
- DIBT/10k_prompts_ranked
|
||||
metrics:
|
||||
- bleu
|
||||
pipeline_tag: text-generation
|
||||
model-index:
|
||||
- name: JARVIS
|
||||
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: 32.08
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: >-
|
||||
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAIBHAV22334455/JARVIS
|
||||
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: 56.86
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: >-
|
||||
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAIBHAV22334455/JARVIS
|
||||
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: 27.15
|
||||
name: accuracy
|
||||
source:
|
||||
url: >-
|
||||
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAIBHAV22334455/JARVIS
|
||||
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: 37.33
|
||||
source:
|
||||
url: >-
|
||||
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAIBHAV22334455/JARVIS
|
||||
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: 60.14
|
||||
name: accuracy
|
||||
source:
|
||||
url: >-
|
||||
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAIBHAV22334455/JARVIS
|
||||
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: 1.14
|
||||
name: accuracy
|
||||
source:
|
||||
url: >-
|
||||
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAIBHAV22334455/JARVIS
|
||||
name: Open LLM Leaderboard
|
||||
tags:
|
||||
- code
|
||||
---
|
||||
# Model Card for Model ID
|
||||
|
||||
Overview
|
||||
This model is a conversational AI designed to engage in natural language interactions with users. It is based on the Causal Language Modeling (CLM) architecture and has been fine-tuned on conversational datasets to generate coherent and contextually relevant responses.
|
||||
|
||||
Usage
|
||||
To use this model, you can interact with it via the Hugging Face Inference API. Provide a text prompt, and the model will generate a response based on the given input.
|
||||
|
||||
Intended Use
|
||||
This model is intended for various conversational applications, including chatbots, virtual assistants, and dialogue systems. It can be deployed in environments where human-like interactions are required, such as customer service, educational platforms, or entertainment applications.
|
||||
|
||||
Limitations and Ethical Considerations
|
||||
While this model is capable of generating human-like responses, it may occasionally produce outputs that are inappropriate, offensive, or misleading. It is essential to monitor its responses and ensure responsible deployment to mitigate potential harms.
|
||||
|
||||
License
|
||||
The model is released under the Apache License 2.0, which allows for both commercial and non-commercial use with proper attribution.
|
||||
|
||||
Acknowledgments
|
||||
This model was trained using the Hugging Face Transformers library and fine-tuned on conversational datasets. We acknowledge the contributions of the open-source community and the developers of the Transformers library.
|
||||
|
||||
Contact Information
|
||||
For inquiries or feedback regarding this model, please contact [your contact information].
|
||||
|
||||
References
|
||||
Provide any relevant references, citations, or links to resources used in training or developing this model.
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
This model is a state-of-the-art conversational AI system based on the Causal Language Modeling (CLM) architecture. It has been fine-tuned on large-scale conversational datasets to generate contextually relevant and coherent responses to user inputs. The model utilizes self-attention mechanisms and deep neural networks to understand and process natural language inputs, allowing it to engage in human-like conversations across a wide range of topics and contexts.
|
||||
|
||||
Architecture
|
||||
The architecture of this model consists of multiple layers of transformer blocks, including self-attention mechanisms and feed-forward neural networks. It employs techniques such as positional encoding and layer normalization to enhance its ability to capture and process sequential information in text data. The model's parameters are optimized through training on conversational datasets using techniques such as gradient descent and backpropagation.
|
||||
|
||||
Fine-Tuning
|
||||
During the fine-tuning process, the model is trained on conversational datasets, where it learns to generate appropriate responses based on input prompts. Fine-tuning involves adjusting the parameters of the pre-trained model to better suit the conversational task at hand, thereby improving its performance in generating contextually relevant and coherent responses.
|
||||
|
||||
Performance
|
||||
The performance of this model is evaluated based on various metrics, including fluency, coherence, relevance, and engagement. It has been extensively tested on benchmark datasets and real-world conversational applications to assess its ability to produce human-like responses and maintain meaningful interactions with users.
|
||||
|
||||
Use Cases
|
||||
This model can be deployed in a variety of conversational applications, including chatbots, virtual assistants, customer support systems, and interactive storytelling platforms. It can facilitate natural language interactions between users and systems, enhancing user experience and providing valuable assistance across different domains and industries.
|
||||
|
||||
Limitations and Ethical Considerations
|
||||
While this model demonstrates advanced capabilities in generating human-like responses, it may occasionally produce outputs that are inappropriate, biased, or misleading. Careful monitoring and evaluation are necessary to ensure responsible deployment and mitigate potential risks, such as spreading misinformation or perpetuating harmful stereotypes.
|
||||
|
||||
License
|
||||
The model is released under the Apache License 2.0, allowing for both commercial and non-commercial use with proper attribution.
|
||||
|
||||
Contact Information
|
||||
For inquiries or feedback regarding this model, please contact [your contact information].
|
||||
|
||||
References
|
||||
Provide any relevant references, citations, or links to resources used in training or developing this model.
|
||||
|
||||
|
||||
|
||||
- **Developed by:** [VAIBHAV VERMA]
|
||||
- **Model type:** [conversational AI]
|
||||
- **Language(s) (NLP):** [PYTHON]
|
||||
- **License:** [Apache License 2.0]
|
||||
- INSPIRED BY [OEvortex/vortex-3b ]
|
||||
|
||||
|
||||
|
||||
## Uses
|
||||
|
||||
The model can be utilized in various conversational applications across different domains and industries. Some potential uses include:
|
||||
|
||||
Chatbots: Deploy the model as a chatbot to engage with users in natural language conversations, providing assistance, answering questions, and offering recommendations.
|
||||
|
||||
Virtual Assistants: Integrate the model into virtual assistant applications to help users with tasks such as scheduling appointments, setting reminders, and retrieving information from the web.
|
||||
|
||||
Customer Support Systems: Use the model to power customer support chat systems, where it can handle customer inquiries, troubleshoot issues, and escalate complex queries to human agents when necessary.
|
||||
|
||||
Interactive Storytelling: Employ the model in interactive storytelling platforms to create immersive narrative experiences where users can engage with virtual characters and influence the plot through their interactions.
|
||||
|
||||
Language Learning: Develop language learning applications that leverage the model to provide conversational practice and feedback to learners, helping them improve their language skills through realistic dialogue simulations.
|
||||
|
||||
Social Media Engagement: Integrate the model into social media platforms to enhance user engagement by enabling automated responses to comments, messages, and posts, personalized recommendations, and conversational interactions.
|
||||
|
||||
Healthcare Assistants: Adapt the model for use in healthcare applications, where it can assist patients with medical inquiries, provide health-related information, and offer support for mental health and wellness.
|
||||
|
||||
Educational Tools: Incorporate the model into educational applications to create interactive tutoring systems, virtual classroom assistants, and language practice tools that engage students in conversational learning experiences.
|
||||
|
||||
Note:
|
||||
This AI model marks my first deployment on the Hugging Face platform. I am grateful for the invaluable assistance provided by Vortex Bahi throughout the development and deployment process. Their guidance and support have been instrumental in bringing this project to fruition.
|
||||
# [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_VAIBHAV22334455__JARVIS)
|
||||
| Metric |Value|
|
||||
|---------------------------------|----:|
|
||||
|Avg. |35.78|
|
||||
|AI2 Reasoning Challenge (25-Shot)|32.08|
|
||||
|HellaSwag (10-Shot) |56.86|
|
||||
|MMLU (5-Shot) |27.15|
|
||||
|TruthfulQA (0-shot) |37.33|
|
||||
|Winogrande (5-shot) |60.14|
|
||||
|GSM8k (5-shot) | 1.14|
|
||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"_name_or_path": "OEvortex/vortex-3b",
|
||||
"architectures": [
|
||||
"GPTNeoXForCausalLM"
|
||||
],
|
||||
"attention_bias": true,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 0,
|
||||
"classifier_dropout": 0.1,
|
||||
"eos_token_id": 0,
|
||||
"hidden_act": "gelu",
|
||||
"hidden_dropout": 0.0,
|
||||
"hidden_size": 2560,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 10240,
|
||||
"layer_norm_eps": 1e-05,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "gpt_neox",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"rope_scaling": null,
|
||||
"rotary_emb_base": 10000,
|
||||
"rotary_pct": 0.25,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.40.0.dev0",
|
||||
"use_cache": false,
|
||||
"use_parallel_residual": true,
|
||||
"vocab_size": 50304
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 0,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 0,
|
||||
"transformers_version": "4.40.0.dev0"
|
||||
}
|
||||
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e1dd5b440f3ddf111174cbef57007bcacfe7951020be15bc6721fa6ca450f568
|
||||
size 4978208880
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:15029e36097dd05c58bcdcf1cfcd9bfe405d7cfdcaaf98720404974c033aa8d3
|
||||
size 572254832
|
||||
395
model.safetensors.index.json
Normal file
395
model.safetensors.index.json
Normal file
@@ -0,0 +1,395 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 5550417920
|
||||
},
|
||||
"weight_map": {
|
||||
"embed_out.weight": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.embed_in.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.final_layer_norm.bias": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.final_layer_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.10.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.10.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.10.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.10.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.11.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.11.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.11.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.11.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.12.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.12.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.12.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.12.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.12.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.13.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.13.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.13.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.13.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.13.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.14.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.14.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.14.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.14.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.14.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.15.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.15.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.15.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.15.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.15.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.16.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.16.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.16.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.16.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.16.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.17.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.17.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.17.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.17.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.17.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.18.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.18.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.18.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.18.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.18.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.19.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.19.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.19.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.19.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.19.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.20.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.20.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.20.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.20.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.20.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.21.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.21.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.21.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.21.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.21.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.22.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.22.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.22.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.22.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.22.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.23.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.23.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.23.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.23.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.23.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.24.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.24.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.24.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.24.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.24.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.24.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.25.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.25.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.25.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.25.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.25.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.25.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.26.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.26.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.26.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.26.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.26.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.26.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.27.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.27.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.27.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.27.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.27.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.27.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.28.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.28.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.28.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.28.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.28.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.28.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.29.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.29.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.29.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.29.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.29.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.29.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.30.attention.dense.bias": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.30.attention.dense.weight": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.30.attention.query_key_value.bias": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.30.attention.query_key_value.weight": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.30.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.30.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.31.attention.dense.bias": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.31.attention.dense.weight": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.31.attention.query_key_value.bias": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.31.attention.query_key_value.weight": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.31.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"gpt_neox.layers.4.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.4.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.4.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.4.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.5.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.5.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.5.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.5.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.6.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.6.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.6.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.6.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.7.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.7.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.7.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.7.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.8.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.8.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.8.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.8.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.9.attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.9.attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.9.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.9.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"gpt_neox.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
3
pytorch_model-00001-of-00002.bin
Normal file
3
pytorch_model-00001-of-00002.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:77e7d29dccb56591a312a3b8c2ea489d2433d58502fb4bda3655cf4179a874ca
|
||||
size 4978296149
|
||||
3
pytorch_model-00002-of-00002.bin
Normal file
3
pytorch_model-00002-of-00002.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b7b6930e09e6652f96112197d796c75982a1dc0451d63e8b73cfab978655eae8
|
||||
size 572260680
|
||||
395
pytorch_model.bin.index.json
Normal file
395
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,395 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 5550417920
|
||||
},
|
||||
"weight_map": {
|
||||
"embed_out.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"gpt_neox.embed_in.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"gpt_neox.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.16.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.16.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.16.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.16.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.16.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.17.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.17.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.17.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.17.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.17.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.18.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.18.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.18.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.18.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.18.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.19.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.19.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.19.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.19.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.19.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.20.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.20.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.20.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.20.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.20.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.20.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.21.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.21.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.21.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.21.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.21.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.21.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.22.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.22.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.22.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.22.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.22.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.23.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.23.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.23.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.23.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.23.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.24.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.24.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.25.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.28.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.28.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.28.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.28.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.28.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.28.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.28.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.28.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.29.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.29.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.29.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.29.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.29.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.29.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.29.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.29.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.30.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"gpt_neox.layers.30.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"gpt_neox.layers.30.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"gpt_neox.layers.30.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"gpt_neox.layers.30.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.30.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"gpt_neox.layers.30.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.30.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.31.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"gpt_neox.layers.31.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"gpt_neox.layers.31.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"gpt_neox.layers.31.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"gpt_neox.layers.31.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"gpt_neox.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"gpt_neox.layers.31.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin"
|
||||
}
|
||||
}
|
||||
35
special_tokens_map.json
Normal file
35
special_tokens_map.json
Normal file
@@ -0,0 +1,35 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"### End",
|
||||
"### Instruction:",
|
||||
"### Response:"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "[PAD]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
100565
tokenizer.json
Normal file
100565
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
249
tokenizer_config.json
Normal file
249
tokenizer_config.json
Normal file
@@ -0,0 +1,249 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<|padding|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50254": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50255": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50256": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50257": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50258": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50259": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50260": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50261": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50262": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50263": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50264": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50265": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50266": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50267": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50268": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50269": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50270": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50271": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50272": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50273": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50274": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50275": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50276": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50277": {
|
||||
"content": "[PAD]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50278": {
|
||||
"content": "### End",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50279": {
|
||||
"content": "### Instruction:",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50280": {
|
||||
"content": "### Response:",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"### End",
|
||||
"### Instruction:",
|
||||
"### Response:"
|
||||
],
|
||||
"bos_token": "<|endoftext|>",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "[PAD]",
|
||||
"tokenizer_class": "GPTNeoXTokenizer",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
Reference in New Issue
Block a user