初始化项目，由ModelHub XC社区提供模型
Model: h2oai/h2ogpt-oasst1-512-12b Source: Original Platform
This commit is contained in:
ModelHub XC
34
.gitattributes
vendored
Normal file
34
.gitattributes
vendored
Normal file
@@ -0,0 +1,34 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
166
README.md
Normal file
166
README.md
Normal file
@@ -0,0 +1,166 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
library_name: transformers
|
||||
inference: false
|
||||
thumbnail: https://h2o.ai/etc.clientlibs/h2o/clientlibs/clientlib-site/resources/images/favicon.ico
|
||||
tags:
|
||||
- gpt
|
||||
- llm
|
||||
- large language model
|
||||
- open-source
|
||||
datasets:
|
||||
- h2oai/openassistant_oasst1_h2ogpt_graded
|
||||
---
|
||||
# h2oGPT Model Card
|
||||
## Summary
|
||||
|
||||
H2O.ai's `h2ogpt-oasst1-512-12b` is a 12 billion parameter instruction-following large language model licensed for commercial use.
|
||||
|
||||
- Base model: [EleutherAI/pythia-12b](https://huggingface.co/EleutherAI/pythia-12b)
|
||||
- Fine-tuning dataset: [h2oai/openassistant_oasst1_h2ogpt_graded](https://huggingface.co/datasets/h2oai/openassistant_oasst1_h2ogpt_graded)
|
||||
- Data-prep and fine-tuning code: [H2O.ai GitHub](https://github.com/h2oai/h2ogpt)
|
||||
- Training logs: [zip](https://huggingface.co/h2oai/h2ogpt-oasst1-512-12b/blob/main/pythia-12b-deduped.h2oaiopenassistant_oasst1_h2ogpt_graded.3_epochs.2ccf687ea3f3f3775a501838e81c1a0066430455.4.zip)
|
||||
|
||||
## Chatbot
|
||||
|
||||
- Run your own chatbot: [H2O.ai GitHub](https://github.com/h2oai/h2ogpt)
|
||||
[](https://github.com/h2oai/h2ogpt)
|
||||
|
||||
## Usage
|
||||
|
||||
To use the model with the `transformers` library on a machine with GPUs, first make sure you have the `transformers` and `accelerate` libraries installed.
|
||||
|
||||
```bash
|
||||
pip install transformers==4.28.1
|
||||
pip install accelerate==0.18.0
|
||||
```
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import pipeline
|
||||
|
||||
generate_text = pipeline(model="h2oai/h2ogpt-oasst1-512-12b", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", prompt_type='human_bot')
|
||||
|
||||
res = generate_text("Why is drinking water so healthy?", max_new_tokens=100)
|
||||
print(res[0]["generated_text"])
|
||||
```
|
||||
|
||||
Alternatively, if you prefer to not use `trust_remote_code=True` you can download [instruct_pipeline.py](https://huggingface.co/h2oai/h2ogpt-oasst1-512-12b/blob/main/h2oai_pipeline.py),
|
||||
store it alongside your notebook, and construct the pipeline yourself from the loaded model and tokenizer:
|
||||
|
||||
```python
|
||||
import torch
|
||||
from h2oai_pipeline import H2OTextGenerationPipeline
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained("h2oai/h2ogpt-oasst1-512-12b", padding_side="left")
|
||||
model = AutoModelForCausalLM.from_pretrained("h2oai/h2ogpt-oasst1-512-12b", torch_dtype=torch.bfloat16, device_map="auto")
|
||||
generate_text = H2OTextGenerationPipeline(model=model, tokenizer=tokenizer, prompt_type='human_bot')
|
||||
|
||||
res = generate_text("Why is drinking water so healthy?", max_new_tokens=100)
|
||||
print(res[0]["generated_text"])
|
||||
```
|
||||
|
||||
## Model Architecture
|
||||
|
||||
```
|
||||
GPTNeoXForCausalLM(
|
||||
(gpt_neox): GPTNeoXModel(
|
||||
(embed_in): Embedding(50688, 5120)
|
||||
(layers): ModuleList(
|
||||
(0-35): 36 x GPTNeoXLayer(
|
||||
(input_layernorm): LayerNorm((5120,), eps=1e-05, elementwise_affine=True)
|
||||
(post_attention_layernorm): LayerNorm((5120,), eps=1e-05, elementwise_affine=True)
|
||||
(attention): GPTNeoXAttention(
|
||||
(rotary_emb): RotaryEmbedding()
|
||||
(query_key_value): Linear(in_features=5120, out_features=15360, bias=True)
|
||||
(dense): Linear(in_features=5120, out_features=5120, bias=True)
|
||||
)
|
||||
(mlp): GPTNeoXMLP(
|
||||
(dense_h_to_4h): Linear(in_features=5120, out_features=20480, bias=True)
|
||||
(dense_4h_to_h): Linear(in_features=20480, out_features=5120, bias=True)
|
||||
(act): GELUActivation()
|
||||
)
|
||||
)
|
||||
)
|
||||
(final_layer_norm): LayerNorm((5120,), eps=1e-05, elementwise_affine=True)
|
||||
)
|
||||
(embed_out): Linear(in_features=5120, out_features=50688, bias=False)
|
||||
)
|
||||
```
|
||||
|
||||
## Model Configuration
|
||||
|
||||
```json
|
||||
GPTNeoXConfig {
|
||||
"_name_or_path": "h2oai/h2ogpt-oasst1-512-12b",
|
||||
"architectures": [
|
||||
"GPTNeoXForCausalLM"
|
||||
],
|
||||
"bos_token_id": 0,
|
||||
"classifier_dropout": 0.1,
|
||||
"custom_pipelines": {
|
||||
"text-generation": {
|
||||
"impl": "h2oai_pipeline.H2OTextGenerationPipeline",
|
||||
"pt": "AutoModelForCausalLM"
|
||||
}
|
||||
},
|
||||
"eos_token_id": 0,
|
||||
"hidden_act": "gelu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 20480,
|
||||
"layer_norm_eps": 1e-05,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "gpt_neox",
|
||||
"num_attention_heads": 40,
|
||||
"num_hidden_layers": 36,
|
||||
"rotary_emb_base": 10000,
|
||||
"rotary_pct": 0.25,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.30.0.dev0",
|
||||
"use_cache": true,
|
||||
"use_parallel_residual": true,
|
||||
"vocab_size": 50688
|
||||
}
|
||||
|
||||
```
|
||||
|
||||
## Model Validation
|
||||
|
||||
Model validation results using [EleutherAI lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness).
|
||||
|
||||
|
||||
[eval source code](https://github.com/h2oai/h2ogpt/issues/125#issuecomment-1548239108)
|
||||
|
||||
| Task |Version| Metric |Value | |Stderr|
|
||||
|-------------|------:|--------|-----:|---|-----:|
|
||||
|arc_challenge| 0|acc |0.3157|± |0.0136|
|
||||
| | |acc_norm|0.3507|± |0.0139|
|
||||
|arc_easy | 0|acc |0.6932|± |0.0095|
|
||||
| | |acc_norm|0.6225|± |0.0099|
|
||||
|boolq | 1|acc |0.6685|± |0.0082|
|
||||
|hellaswag | 0|acc |0.5140|± |0.0050|
|
||||
| | |acc_norm|0.6803|± |0.0047|
|
||||
|openbookqa | 0|acc |0.2900|± |0.0203|
|
||||
| | |acc_norm|0.3740|± |0.0217|
|
||||
|piqa | 0|acc |0.7682|± |0.0098|
|
||||
| | |acc_norm|0.7661|± |0.0099|
|
||||
|winogrande | 0|acc |0.6369|± |0.0135|
|
||||
|
||||
|
||||
## Disclaimer
|
||||
|
||||
Please read this disclaimer carefully before using the large language model provided in this repository. Your use of the model signifies your agreement to the following terms and conditions.
|
||||
|
||||
- Biases and Offensiveness: The large language model is trained on a diverse range of internet text data, which may contain biased, racist, offensive, or otherwise inappropriate content. By using this model, you acknowledge and accept that the generated content may sometimes exhibit biases or produce content that is offensive or inappropriate. The developers of this repository do not endorse, support, or promote any such content or viewpoints.
|
||||
- Limitations: The large language model is an AI-based tool and not a human. It may produce incorrect, nonsensical, or irrelevant responses. It is the user's responsibility to critically evaluate the generated content and use it at their discretion.
|
||||
- Use at Your Own Risk: Users of this large language model must assume full responsibility for any consequences that may arise from their use of the tool. The developers and contributors of this repository shall not be held liable for any damages, losses, or harm resulting from the use or misuse of the provided model.
|
||||
- Ethical Considerations: Users are encouraged to use the large language model responsibly and ethically. By using this model, you agree not to use it for purposes that promote hate speech, discrimination, harassment, or any form of illegal or harmful activities.
|
||||
- Reporting Issues: If you encounter any biased, offensive, or otherwise inappropriate content generated by the large language model, please report it to the repository maintainers through the provided channels. Your feedback will help improve the model and mitigate potential issues.
|
||||
- Changes to this Disclaimer: The developers of this repository reserve the right to modify or update this disclaimer at any time without prior notice. It is the user's responsibility to periodically review the disclaimer to stay informed about any changes.
|
||||
|
||||
By using the large language model provided in this repository, you agree to accept and comply with the terms and conditions outlined in this disclaimer. If you do not agree with any part of this disclaimer, you should refrain from using the model and any content generated by it.
|
||||
31
config.json
Normal file
31
config.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"_name_or_path": "EleutherAI/pythia-12b-deduped",
|
||||
"architectures": [
|
||||
"GPTNeoXForCausalLM"
|
||||
],
|
||||
"bos_token_id": 0,
|
||||
"custom_pipelines": {
|
||||
"text-generation": {
|
||||
"impl": "h2oai_pipeline.H2OTextGenerationPipeline",
|
||||
"pt": "AutoModelForCausalLM"
|
||||
}
|
||||
},
|
||||
"eos_token_id": 0,
|
||||
"hidden_act": "gelu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 20480,
|
||||
"layer_norm_eps": 1e-05,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "gpt_neox",
|
||||
"num_attention_heads": 40,
|
||||
"num_hidden_layers": 36,
|
||||
"rotary_emb_base": 10000,
|
||||
"rotary_pct": 0.25,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.28.1",
|
||||
"use_cache": true,
|
||||
"use_parallel_residual": true,
|
||||
"vocab_size": 50688
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 0,
|
||||
"eos_token_id": 0,
|
||||
"transformers_version": "4.28.1"
|
||||
}
|
||||
774
h2oai_pipeline.py
Normal file
774
h2oai_pipeline.py
Normal file
@@ -0,0 +1,774 @@
|
||||
from transformers import TextGenerationPipeline
|
||||
from transformers.pipelines.text_generation import ReturnType
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
class H2OTextGenerationPipeline(TextGenerationPipeline):
|
||||
def __init__(self, *args, debug=False, chat=False, stream_output=False,
|
||||
sanitize_bot_response=True,
|
||||
use_prompter=True, prompter=None, prompt_type=None,
|
||||
max_input_tokens=2048 - 256, **kwargs):
|
||||
"""
|
||||
HF-like pipeline, but handle instruction prompting and stopping (for some models)
|
||||
:param args:
|
||||
:param debug:
|
||||
:param chat:
|
||||
:param stream_output:
|
||||
:param sanitize_bot_response:
|
||||
:param use_prompter: Whether to use prompter. If pass prompt_type, will make prompter
|
||||
:param prompter: prompter, can pass if have already
|
||||
:param prompt_type: prompt_type, e.g. human_bot. See prompt_type to model mapping in from prompter.py.
|
||||
If use_prompter, then will make prompter and use it.
|
||||
:param max_input_tokens:
|
||||
:param kwargs:
|
||||
"""
|
||||
super().__init__(*args, **kwargs)
|
||||
self.prompt_text = None
|
||||
self.use_prompter = use_prompter
|
||||
self.prompt_type = prompt_type
|
||||
self.prompter = prompter
|
||||
if self.use_prompter:
|
||||
if self.prompter is not None:
|
||||
assert self.prompter.prompt_type is not None
|
||||
else:
|
||||
self.prompter = Prompter(self.prompt_type, debug=debug, chat=chat, stream_output=stream_output)
|
||||
self.human = self.prompter.humanstr
|
||||
self.bot = self.prompter.botstr
|
||||
self.can_stop = True
|
||||
else:
|
||||
self.prompter = None
|
||||
self.human = None
|
||||
self.bot = None
|
||||
self.can_stop = False
|
||||
self.sanitize_bot_response = sanitize_bot_response
|
||||
self.max_input_tokens = max_input_tokens # not for generate, so ok that not kwargs
|
||||
|
||||
def preprocess(self, prompt_text, prefix="", handle_long_generation=None, **generate_kwargs):
|
||||
data_point = dict(context='', instruction=prompt_text, input='')
|
||||
if self.prompter is not None:
|
||||
prompt_text = self.prompter.generate_prompt(data_point)
|
||||
self.prompt_text = prompt_text
|
||||
if handle_long_generation is None:
|
||||
# forces truncation of inputs to avoid critical failure
|
||||
handle_long_generation = 'hole'
|
||||
return super().preprocess(prompt_text, prefix=prefix, handle_long_generation=handle_long_generation,
|
||||
**generate_kwargs)
|
||||
|
||||
def postprocess(self, model_outputs, return_type=ReturnType.FULL_TEXT, clean_up_tokenization_spaces=True):
|
||||
records = super().postprocess(model_outputs, return_type=return_type,
|
||||
clean_up_tokenization_spaces=clean_up_tokenization_spaces)
|
||||
for rec in records:
|
||||
if self.use_prompter:
|
||||
outputs = rec['generated_text']
|
||||
outputs = self.prompter.get_response(outputs, prompt=self.prompt_text,
|
||||
sanitize_bot_response=self.sanitize_bot_response)
|
||||
elif self.bot and self.human:
|
||||
outputs = rec['generated_text'].split(self.bot)[1].strip().split(self.human)[0].strip()
|
||||
else:
|
||||
outputs = rec['generated_text']
|
||||
rec['generated_text'] = outputs
|
||||
return records
|
||||
|
||||
def _forward(self, model_inputs, **generate_kwargs):
|
||||
if self.can_stop:
|
||||
stopping_criteria = get_stopping(self.prompt_type, self.tokenizer, self.device, human=self.human,
|
||||
bot=self.bot)
|
||||
generate_kwargs['stopping_criteria'] = stopping_criteria
|
||||
# return super()._forward(model_inputs, **generate_kwargs)
|
||||
return self.__forward(model_inputs, **generate_kwargs)
|
||||
|
||||
# FIXME: Copy-paste of original _forward, but removed copy.deepcopy()
|
||||
# FIXME: https://github.com/h2oai/h2ogpt/issues/172
|
||||
def __forward(self, model_inputs, **generate_kwargs):
|
||||
input_ids = model_inputs["input_ids"]
|
||||
attention_mask = model_inputs.get("attention_mask", None)
|
||||
# Allow empty prompts
|
||||
if input_ids.shape[1] == 0:
|
||||
input_ids = None
|
||||
attention_mask = None
|
||||
in_b = 1
|
||||
else:
|
||||
in_b = input_ids.shape[0]
|
||||
prompt_text = model_inputs.pop("prompt_text")
|
||||
|
||||
## If there is a prefix, we may need to adjust the generation length. Do so without permanently modifying
|
||||
## generate_kwargs, as some of the parameterization may come from the initialization of the pipeline.
|
||||
# generate_kwargs = copy.deepcopy(generate_kwargs)
|
||||
prefix_length = generate_kwargs.pop("prefix_length", 0)
|
||||
if prefix_length > 0:
|
||||
has_max_new_tokens = "max_new_tokens" in generate_kwargs or (
|
||||
"generation_config" in generate_kwargs
|
||||
and generate_kwargs["generation_config"].max_new_tokens is not None
|
||||
)
|
||||
if not has_max_new_tokens:
|
||||
generate_kwargs["max_length"] = generate_kwargs.get("max_length") or self.model.config.max_length
|
||||
generate_kwargs["max_length"] += prefix_length
|
||||
has_min_new_tokens = "min_new_tokens" in generate_kwargs or (
|
||||
"generation_config" in generate_kwargs
|
||||
and generate_kwargs["generation_config"].min_new_tokens is not None
|
||||
)
|
||||
if not has_min_new_tokens and "min_length" in generate_kwargs:
|
||||
generate_kwargs["min_length"] += prefix_length
|
||||
|
||||
# BS x SL
|
||||
generated_sequence = self.model.generate(input_ids=input_ids, attention_mask=attention_mask, **generate_kwargs)
|
||||
out_b = generated_sequence.shape[0]
|
||||
if self.framework == "pt":
|
||||
generated_sequence = generated_sequence.reshape(in_b, out_b // in_b, *generated_sequence.shape[1:])
|
||||
elif self.framework == "tf":
|
||||
from transformers import is_tf_available
|
||||
if is_tf_available():
|
||||
import tensorflow as tf
|
||||
generated_sequence = tf.reshape(generated_sequence,
|
||||
(in_b, out_b // in_b, *generated_sequence.shape[1:]))
|
||||
else:
|
||||
raise ValueError("TF not avaialble.")
|
||||
return {"generated_sequence": generated_sequence, "input_ids": input_ids, "prompt_text": prompt_text}
|
||||
import torch
|
||||
from transformers import StoppingCriteria, StoppingCriteriaList
|
||||
|
||||
|
||||
|
||||
class StoppingCriteriaSub(StoppingCriteria):
|
||||
|
||||
def __init__(self, stops=[], encounters=[], device="cuda"):
|
||||
super().__init__()
|
||||
assert len(stops) % len(encounters) == 0, "Number of stops and encounters must match"
|
||||
self.encounters = encounters
|
||||
self.stops = [stop.to(device) for stop in stops]
|
||||
self.num_stops = [0] * len(stops)
|
||||
|
||||
def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
|
||||
for stopi, stop in enumerate(self.stops):
|
||||
if torch.all((stop == input_ids[0][-len(stop):])).item():
|
||||
self.num_stops[stopi] += 1
|
||||
if self.num_stops[stopi] >= self.encounters[stopi % len(self.encounters)]:
|
||||
# print("Stopped", flush=True)
|
||||
return True
|
||||
# print("Tokens: %s" % input_ids[0].cpu().numpy(), flush=True)
|
||||
# print("Stop Tokens: %s" % [x.cpu().numpy() for x in self.stops], flush=True)
|
||||
return False
|
||||
|
||||
|
||||
def get_stopping(prompt_type, tokenizer, device, human='<human>:', bot="<bot>:"):
|
||||
if prompt_type in [PromptType.human_bot.name, PromptType.instruct_vicuna.name, PromptType.instruct_with_end.name]:
|
||||
if prompt_type == PromptType.human_bot.name:
|
||||
# encounters = [prompt.count(human) + 1, prompt.count(bot) + 1]
|
||||
# stopping only starts once output is beyond prompt
|
||||
# 1 human is enough to trigger, but need 2 bots, because very first view back will be bot we added
|
||||
stop_words = [human, bot, '\n' + human, '\n' + bot]
|
||||
encounters = [1, 2]
|
||||
elif prompt_type == PromptType.instruct_vicuna.name:
|
||||
# even below is not enough, generic strings and many ways to encode
|
||||
stop_words = [
|
||||
'### Human:',
|
||||
"""
|
||||
### Human:""",
|
||||
"""
|
||||
### Human:
|
||||
""",
|
||||
'### Assistant:',
|
||||
"""
|
||||
### Assistant:""",
|
||||
"""
|
||||
### Assistant:
|
||||
""",
|
||||
]
|
||||
encounters = [1, 2]
|
||||
else:
|
||||
# some instruct prompts have this as end, doesn't hurt to stop on it since not common otherwise
|
||||
stop_words = ['### End']
|
||||
encounters = [1]
|
||||
stop_words_ids = [
|
||||
tokenizer(stop_word, return_tensors='pt')['input_ids'].squeeze() for stop_word in stop_words]
|
||||
# handle single token case
|
||||
stop_words_ids = [x if len(x.shape) > 0 else torch.tensor([x]) for x in stop_words_ids]
|
||||
stop_words_ids = [x for x in stop_words_ids if x.shape[0] > 0]
|
||||
# avoid padding in front of tokens
|
||||
if tokenizer._pad_token: # use hidden variable to avoid annoying properly logger bug
|
||||
stop_words_ids = [x[1:] if x[0] == tokenizer.pad_token_id and len(x) > 1 else x for x in stop_words_ids]
|
||||
# handle fake \n added
|
||||
stop_words_ids = [x[1:] if y[0] == '\n' else x for x, y in zip(stop_words_ids, stop_words)]
|
||||
# build stopper
|
||||
stopping_criteria = StoppingCriteriaList(
|
||||
[StoppingCriteriaSub(stops=stop_words_ids, encounters=encounters, device=device)])
|
||||
else:
|
||||
stopping_criteria = StoppingCriteriaList()
|
||||
return stopping_criteria
|
||||
import time
|
||||
from enum import Enum
|
||||
|
||||
non_hf_types = ['gpt4all_llama', 'llama', 'gptj']
|
||||
|
||||
|
||||
class PromptType(Enum):
|
||||
plain = 0
|
||||
instruct = 1
|
||||
quality = 2
|
||||
human_bot = 3
|
||||
dai_faq = 4
|
||||
summarize = 5
|
||||
simple_instruct = 6
|
||||
instruct_vicuna = 7
|
||||
instruct_with_end = 8
|
||||
human_bot_orig = 9
|
||||
prompt_answer = 10
|
||||
open_assistant = 11
|
||||
wizard_lm = 12
|
||||
wizard_mega = 13
|
||||
instruct_vicuna2 = 14
|
||||
instruct_vicuna3 = 15
|
||||
wizard2 = 16
|
||||
wizard3 = 17
|
||||
|
||||
|
||||
prompt_type_to_model_name = {
|
||||
'plain': [
|
||||
'EleutherAI/gpt-j-6B',
|
||||
'EleutherAI/pythia-6.9b',
|
||||
'EleutherAI/pythia-12b',
|
||||
'EleutherAI/pythia-12b-deduped',
|
||||
'EleutherAI/gpt-neox-20b',
|
||||
'openlm-research/open_llama_7b_700bt_preview',
|
||||
'decapoda-research/llama-7b-hf',
|
||||
'decapoda-research/llama-13b-hf',
|
||||
'decapoda-research/llama-30b-hf',
|
||||
'decapoda-research/llama-65b-hf',
|
||||
'facebook/mbart-large-50-many-to-many-mmt',
|
||||
'philschmid/bart-large-cnn-samsum',
|
||||
'philschmid/flan-t5-base-samsum',
|
||||
'gpt2',
|
||||
'distilgpt2',
|
||||
'mosaicml/mpt-7b-storywriter',
|
||||
'mosaicml/mpt-7b-instruct', # internal code handles instruct
|
||||
'mosaicml/mpt-7b-chat', # NC, internal code handles instruct
|
||||
'gptj', # internally handles prompting
|
||||
'llama', # plain, or need to choose prompt_type for given TheBloke model
|
||||
'gpt4all_llama', # internally handles prompting
|
||||
],
|
||||
'prompt_answer': [
|
||||
'h2oai/h2ogpt-gm-oasst1-en-1024-20b',
|
||||
'h2oai/h2ogpt-gm-oasst1-en-1024-12b',
|
||||
'h2oai/h2ogpt-gm-oasst1-multilang-1024-20b',
|
||||
'h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt',
|
||||
'h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-v2',
|
||||
'h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-700bt',
|
||||
],
|
||||
'instruct': [],
|
||||
'instruct_with_end': ['databricks/dolly-v2-12b'],
|
||||
'quality': [],
|
||||
'human_bot': [
|
||||
'h2oai/h2ogpt-oasst1-512-12b',
|
||||
'h2oai/h2ogpt-oasst1-512-20b',
|
||||
'h2oai/h2ogpt-oig-oasst1-256-6_9b',
|
||||
'h2oai/h2ogpt-oig-oasst1-512-6_9b',
|
||||
'h2oai/h2ogpt-oig-oasst1-256-6.9b', # legacy
|
||||
'h2oai/h2ogpt-oig-oasst1-512-6.9b', # legacy
|
||||
'h2oai/h2ogpt-research-oasst1-512-30b',
|
||||
'h2oai/h2ogpt-oasst1-falcon-40b',
|
||||
],
|
||||
'dai_faq': [],
|
||||
'summarize': [],
|
||||
'simple_instruct': ['t5-small', 't5-large', 'google/flan-t5', 'google/flan-t5-xxl', 'google/flan-ul2'],
|
||||
'instruct_vicuna': ['AlekseyKorshuk/vicuna-7b', 'TheBloke/stable-vicuna-13B-HF', 'junelee/wizard-vicuna-13b'],
|
||||
'human_bot_orig': ['togethercomputer/GPT-NeoXT-Chat-Base-20B'],
|
||||
"open_assistant": ['OpenAssistant/oasst-sft-7-llama-30b-xor', 'oasst-sft-7-llama-30b'],
|
||||
"wizard_lm": ['ehartford/WizardLM-7B-Uncensored', 'ehartford/WizardLM-13B-Uncensored'],
|
||||
"wizard_mega": ['openaccess-ai-collective/wizard-mega-13b'],
|
||||
}
|
||||
|
||||
inv_prompt_type_to_model_name = {v.strip(): k for k, l in prompt_type_to_model_name.items() for v in l}
|
||||
inv_prompt_type_to_model_lower = {v.strip().lower(): k for k, l in prompt_type_to_model_name.items() for v in l}
|
||||
|
||||
prompt_types_strings = []
|
||||
for p in PromptType:
|
||||
prompt_types_strings.extend([p.name])
|
||||
|
||||
prompt_types = []
|
||||
for p in PromptType:
|
||||
prompt_types.extend([p.name, p.value, str(p.value)])
|
||||
|
||||
|
||||
def get_prompt(prompt_type, chat, context, reduced):
|
||||
if prompt_type in [PromptType.plain.value, str(PromptType.plain.value),
|
||||
PromptType.plain.name]:
|
||||
promptA = promptB = PreInstruct = PreInput = PreResponse = ''
|
||||
terminate_response = []
|
||||
chat_sep = ''
|
||||
humanstr = ''
|
||||
botstr = ''
|
||||
elif prompt_type == 'simple_instruct':
|
||||
promptA = promptB = PreInstruct = PreInput = PreResponse = None
|
||||
terminate_response = []
|
||||
chat_sep = '\n'
|
||||
humanstr = ''
|
||||
botstr = ''
|
||||
elif prompt_type in [PromptType.instruct.value, str(PromptType.instruct.value),
|
||||
PromptType.instruct.name] + [PromptType.instruct_with_end.value,
|
||||
str(PromptType.instruct_with_end.value),
|
||||
PromptType.instruct_with_end.name]:
|
||||
promptA = 'Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n' if not (
|
||||
chat and reduced) else ''
|
||||
promptB = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.\n' if not (
|
||||
chat and reduced) else ''
|
||||
|
||||
PreInstruct = """
|
||||
### Instruction:
|
||||
"""
|
||||
|
||||
PreInput = """
|
||||
### Input:
|
||||
"""
|
||||
|
||||
PreResponse = """
|
||||
### Response:
|
||||
"""
|
||||
if prompt_type in [PromptType.instruct_with_end.value, str(PromptType.instruct_with_end.value),
|
||||
PromptType.instruct_with_end.name]:
|
||||
terminate_response = ['### End']
|
||||
else:
|
||||
terminate_response = None
|
||||
chat_sep = '\n'
|
||||
humanstr = PreInstruct
|
||||
botstr = PreResponse
|
||||
elif prompt_type in [PromptType.quality.value, str(PromptType.quality.value),
|
||||
PromptType.quality.name]:
|
||||
promptA = 'Write a detailed high-quality, accurate, fair, Response with about 100 words by following the Instruction as applied on the Input.\n' if not (
|
||||
chat and reduced) else ''
|
||||
promptB = 'Write a detailed high-quality, accurate, fair, Response with about 100 words by following the Instruction.\n' if not (
|
||||
chat and reduced) else ''
|
||||
|
||||
PreInstruct = """
|
||||
### Instruction:
|
||||
"""
|
||||
|
||||
PreInput = """
|
||||
### Input:
|
||||
"""
|
||||
|
||||
PreResponse = """
|
||||
### Response:
|
||||
"""
|
||||
terminate_response = None
|
||||
chat_sep = '\n'
|
||||
humanstr = PreInstruct # first thing human says
|
||||
botstr = PreResponse # first thing bot says
|
||||
elif prompt_type in [PromptType.human_bot.value, str(PromptType.human_bot.value),
|
||||
PromptType.human_bot.name] + [PromptType.human_bot_orig.value,
|
||||
str(PromptType.human_bot_orig.value),
|
||||
PromptType.human_bot_orig.name]:
|
||||
human = '<human>:'
|
||||
bot = "<bot>:"
|
||||
if reduced or context or prompt_type in [PromptType.human_bot.value, str(PromptType.human_bot.value),
|
||||
PromptType.human_bot.name]:
|
||||
preprompt = ''
|
||||
else:
|
||||
cur_date = time.strftime('%Y-%m-%d')
|
||||
cur_time = time.strftime('%H:%M:%S %p %Z')
|
||||
|
||||
PRE_PROMPT = """\
|
||||
Current Date: {}
|
||||
Current Time: {}
|
||||
|
||||
"""
|
||||
preprompt = PRE_PROMPT.format(cur_date, cur_time)
|
||||
start = human
|
||||
promptB = promptA = '%s%s ' % (preprompt, start)
|
||||
|
||||
PreInstruct = ""
|
||||
|
||||
PreInput = None
|
||||
|
||||
if reduced:
|
||||
# when making context, want it to appear as-if LLM generated, which starts with space after :
|
||||
PreResponse = bot + ' '
|
||||
else:
|
||||
# normally LLM adds space after this, because was how trained.
|
||||
# if add space here, non-unique tokenization will often make LLM produce wrong output
|
||||
PreResponse = bot
|
||||
|
||||
terminate_response = [start, PreResponse]
|
||||
chat_sep = '\n'
|
||||
humanstr = human # tag before human talks
|
||||
botstr = bot # tag before bot talks
|
||||
elif prompt_type in [PromptType.dai_faq.value, str(PromptType.dai_faq.value),
|
||||
PromptType.dai_faq.name]:
|
||||
promptA = ''
|
||||
promptB = 'Answer the following Driverless AI question.\n'
|
||||
|
||||
PreInstruct = """
|
||||
### Driverless AI frequently asked question:
|
||||
"""
|
||||
|
||||
PreInput = None
|
||||
|
||||
PreResponse = """
|
||||
### Driverless AI documentation answer:
|
||||
"""
|
||||
terminate_response = ['\n\n']
|
||||
chat_sep = terminate_response
|
||||
humanstr = PreInstruct
|
||||
botstr = PreResponse
|
||||
elif prompt_type in [PromptType.summarize.value, str(PromptType.summarize.value),
|
||||
PromptType.summarize.name]:
|
||||
promptA = promptB = PreInput = ''
|
||||
PreInstruct = '## Main Text\n\n'
|
||||
PreResponse = '\n\n## Summary\n\n'
|
||||
terminate_response = None
|
||||
chat_sep = '\n'
|
||||
humanstr = PreInstruct
|
||||
botstr = PreResponse
|
||||
elif prompt_type in [PromptType.instruct_vicuna.value, str(PromptType.instruct_vicuna.value),
|
||||
PromptType.instruct_vicuna.name]:
|
||||
promptA = promptB = "A chat between a curious human and an artificial intelligence assistant. " \
|
||||
"The assistant gives helpful, detailed, and polite answers to the human's questions." if not (
|
||||
chat and reduced) else ''
|
||||
|
||||
PreInstruct = """
|
||||
### Human:
|
||||
"""
|
||||
|
||||
PreInput = None
|
||||
|
||||
PreResponse = """
|
||||
### Assistant:
|
||||
"""
|
||||
terminate_response = [
|
||||
'### Human:'] # but only allow terminate after prompt is found correctly, else can't terminate
|
||||
chat_sep = '\n'
|
||||
humanstr = PreInstruct
|
||||
botstr = PreResponse
|
||||
elif prompt_type in [PromptType.prompt_answer.value, str(PromptType.prompt_answer.value),
|
||||
PromptType.prompt_answer.name]:
|
||||
preprompt = ''
|
||||
prompt_tokens = "<|prompt|>"
|
||||
answer_tokens = "<|answer|>"
|
||||
start = prompt_tokens
|
||||
promptB = promptA = '%s%s' % (preprompt, start)
|
||||
PreInstruct = ""
|
||||
PreInput = None
|
||||
PreResponse = answer_tokens
|
||||
eos = '<|endoftext|>' # neox eos
|
||||
terminate_response = [start, PreResponse, eos]
|
||||
chat_sep = eos
|
||||
humanstr = prompt_tokens
|
||||
botstr = answer_tokens
|
||||
elif prompt_type in [PromptType.open_assistant.value, str(PromptType.open_assistant.value),
|
||||
PromptType.open_assistant.name]:
|
||||
# From added_tokens.json
|
||||
preprompt = ''
|
||||
prompt_tokens = "<|prompter|>"
|
||||
answer_tokens = "<|assistant|>"
|
||||
start = prompt_tokens
|
||||
promptB = promptA = '%s%s' % (preprompt, start)
|
||||
PreInstruct = ""
|
||||
PreInput = None
|
||||
PreResponse = answer_tokens
|
||||
pend = "<|prefix_end|>"
|
||||
eos = "</s>"
|
||||
terminate_response = [start, PreResponse, pend, eos]
|
||||
chat_sep = eos
|
||||
humanstr = prompt_tokens
|
||||
botstr = answer_tokens
|
||||
elif prompt_type in [PromptType.wizard_lm.value, str(PromptType.wizard_lm.value),
|
||||
PromptType.wizard_lm.name]:
|
||||
# https://github.com/ehartford/WizardLM/blob/main/src/train_freeform.py
|
||||
preprompt = ''
|
||||
start = ''
|
||||
promptB = promptA = '%s%s' % (preprompt, start)
|
||||
PreInstruct = ""
|
||||
PreInput = None
|
||||
PreResponse = "\n\n### Response\n"
|
||||
eos = "</s>"
|
||||
terminate_response = [PreResponse, eos]
|
||||
chat_sep = eos
|
||||
humanstr = promptA
|
||||
botstr = PreResponse
|
||||
elif prompt_type in [PromptType.wizard_mega.value, str(PromptType.wizard_mega.value),
|
||||
PromptType.wizard_mega.name]:
|
||||
preprompt = ''
|
||||
start = ''
|
||||
promptB = promptA = '%s%s' % (preprompt, start)
|
||||
PreInstruct = """
|
||||
### Instruction:
|
||||
"""
|
||||
PreInput = None
|
||||
PreResponse = """
|
||||
### Assistant:
|
||||
"""
|
||||
terminate_response = [PreResponse]
|
||||
chat_sep = '\n'
|
||||
humanstr = PreInstruct
|
||||
botstr = PreResponse
|
||||
elif prompt_type in [PromptType.instruct_vicuna2.value, str(PromptType.instruct_vicuna2.value),
|
||||
PromptType.instruct_vicuna2.name]:
|
||||
promptA = promptB = "" if not (
|
||||
chat and reduced) else ''
|
||||
|
||||
PreInstruct = """
|
||||
HUMAN:
|
||||
"""
|
||||
|
||||
PreInput = None
|
||||
|
||||
PreResponse = """
|
||||
ASSISTANT:
|
||||
"""
|
||||
terminate_response = [
|
||||
'HUMAN:'] # but only allow terminate after prompt is found correctly, else can't terminate
|
||||
chat_sep = '\n'
|
||||
humanstr = PreInstruct
|
||||
botstr = PreResponse
|
||||
elif prompt_type in [PromptType.instruct_vicuna3.value, str(PromptType.instruct_vicuna3.value),
|
||||
PromptType.instruct_vicuna3.name]:
|
||||
promptA = promptB = "" if not (
|
||||
chat and reduced) else ''
|
||||
|
||||
PreInstruct = """
|
||||
### User:
|
||||
"""
|
||||
|
||||
PreInput = None
|
||||
|
||||
PreResponse = """
|
||||
### Assistant:
|
||||
"""
|
||||
terminate_response = [
|
||||
'### User:'] # but only allow terminate after prompt is found correctly, else can't terminate
|
||||
chat_sep = '\n'
|
||||
humanstr = PreInstruct
|
||||
botstr = PreResponse
|
||||
elif prompt_type in [PromptType.wizard2.value, str(PromptType.wizard2.value),
|
||||
PromptType.wizard2.name]:
|
||||
# https://huggingface.co/TheBloke/WizardLM-7B-uncensored-GGML
|
||||
preprompt = """Below is an instruction that describes a task. Write a response that appropriately completes the request."""
|
||||
start = ''
|
||||
promptB = promptA = '%s%s' % (preprompt, start)
|
||||
PreInstruct = """
|
||||
### Instruction:
|
||||
"""
|
||||
PreInput = None
|
||||
PreResponse = """
|
||||
### Response:
|
||||
"""
|
||||
terminate_response = [PreResponse]
|
||||
chat_sep = '\n'
|
||||
humanstr = PreInstruct
|
||||
botstr = PreResponse
|
||||
elif prompt_type in [PromptType.wizard3.value, str(PromptType.wizard3.value),
|
||||
PromptType.wizard3.name]:
|
||||
# https://huggingface.co/TheBloke/wizardLM-13B-1.0-GGML
|
||||
preprompt = """A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions."""
|
||||
start = ''
|
||||
promptB = promptA = '%s%s' % (preprompt, start)
|
||||
PreInstruct = """USER: """
|
||||
PreInput = None
|
||||
PreResponse = """ASSISTANT: """
|
||||
terminate_response = [PreResponse]
|
||||
chat_sep = '\n'
|
||||
humanstr = PreInstruct
|
||||
botstr = PreResponse
|
||||
|
||||
else:
|
||||
raise RuntimeError("No such prompt_type=%s" % prompt_type)
|
||||
|
||||
return promptA, promptB, PreInstruct, PreInput, PreResponse, terminate_response, chat_sep, humanstr, botstr
|
||||
|
||||
|
||||
def generate_prompt(data_point, prompt_type, chat, reduced):
|
||||
context = data_point.get('context')
|
||||
if context is None:
|
||||
context = ''
|
||||
instruction = data_point.get('instruction')
|
||||
input = data_point.get('input')
|
||||
output = data_point.get('output')
|
||||
prompt_type = data_point.get('prompt_type', prompt_type)
|
||||
assert prompt_type in prompt_types, "Bad prompt type: %s" % prompt_type
|
||||
promptA, promptB, PreInstruct, PreInput, PreResponse, \
|
||||
terminate_response, chat_sep, humanstr, botstr = get_prompt(prompt_type, chat, context, reduced)
|
||||
|
||||
prompt = context if not reduced else ''
|
||||
|
||||
if input and promptA:
|
||||
prompt += f"""{promptA}"""
|
||||
elif promptB:
|
||||
prompt += f"""{promptB}"""
|
||||
|
||||
if instruction and PreInstruct is not None and input and PreInput is not None:
|
||||
prompt += f"""{PreInstruct}{instruction}{PreInput}{input}"""
|
||||
prompt = inject_newline(prompt_type, prompt)
|
||||
elif instruction and input and PreInstruct is None and PreInput is not None:
|
||||
prompt += f"""{PreInput}{instruction}
|
||||
{input}"""
|
||||
prompt = inject_newline(prompt_type, prompt)
|
||||
elif input and instruction and PreInput is None and PreInstruct is not None:
|
||||
prompt += f"""{PreInstruct}{instruction}
|
||||
{input}"""
|
||||
prompt = inject_newline(prompt_type, prompt)
|
||||
elif instruction and PreInstruct is not None:
|
||||
prompt += f"""{PreInstruct}{instruction}"""
|
||||
prompt = inject_newline(prompt_type, prompt)
|
||||
elif input and PreInput is not None:
|
||||
prompt += f"""{PreInput}{input}"""
|
||||
prompt = inject_newline(prompt_type, prompt)
|
||||
elif input and instruction and PreInput is not None:
|
||||
prompt += f"""{PreInput}{instruction}{input}"""
|
||||
prompt = inject_newline(prompt_type, prompt)
|
||||
elif input and instruction and PreInstruct is not None:
|
||||
prompt += f"""{PreInstruct}{instruction}{input}"""
|
||||
prompt = inject_newline(prompt_type, prompt)
|
||||
elif input and instruction:
|
||||
# i.e. for simple_instruct
|
||||
prompt += f"""{instruction}: {input}"""
|
||||
prompt = inject_newline(prompt_type, prompt)
|
||||
elif input:
|
||||
prompt += f"""{input}"""
|
||||
prompt = inject_newline(prompt_type, prompt)
|
||||
elif instruction:
|
||||
prompt += f"""{instruction}"""
|
||||
prompt = inject_newline(prompt_type, prompt)
|
||||
|
||||
if PreResponse is not None:
|
||||
prompt += f"""{PreResponse}"""
|
||||
pre_response = PreResponse # Don't use strip
|
||||
else:
|
||||
pre_response = ''
|
||||
|
||||
if output:
|
||||
prompt += f"""{output}"""
|
||||
|
||||
return prompt, pre_response, terminate_response, chat_sep
|
||||
|
||||
|
||||
def inject_newline(prompt_type, prompt):
|
||||
if prompt_type not in [-1, '-1', 'plain', 'simple_instruct']:
|
||||
# only add new line if structured prompt, while 'plain' is just generation of next tokens from input
|
||||
prompt += '\n'
|
||||
return prompt
|
||||
|
||||
|
||||
class Prompter(object):
|
||||
def __init__(self, prompt_type, debug=False, chat=False, stream_output=False, repeat_penalty=True,
|
||||
allowed_repeat_line_length=10):
|
||||
self.prompt_type = prompt_type
|
||||
data_point = dict(instruction='', input='', output='')
|
||||
_, self.pre_response, self.terminate_response, self.chat_sep = \
|
||||
generate_prompt(data_point, prompt_type, chat, False)
|
||||
self.debug = debug
|
||||
self.chat = chat
|
||||
self.stream_output = stream_output
|
||||
self.repeat_penalty = repeat_penalty
|
||||
self.allowed_repeat_line_length = allowed_repeat_line_length
|
||||
self.prompt = None
|
||||
context = "" # not for chat context
|
||||
reduced = False # not for chat context
|
||||
self.promptA, self.promptB, self.PreInstruct, self.PreInput, self.PreResponse, \
|
||||
self.terminate_response, self.chat_sep, self.humanstr, self.botstr = \
|
||||
get_prompt(prompt_type, chat, context, reduced)
|
||||
|
||||
def generate_prompt(self, data_point):
|
||||
reduced = False
|
||||
prompt, _, _, _ = generate_prompt(data_point, self.prompt_type, self.chat, reduced)
|
||||
if self.debug:
|
||||
print("prompt: ", prompt, flush=True)
|
||||
self.prompt = prompt
|
||||
return prompt
|
||||
|
||||
def get_response(self, outputs, prompt=None, sanitize_bot_response=True):
|
||||
if isinstance(outputs, str):
|
||||
outputs = [outputs]
|
||||
if self.debug:
|
||||
print("output:\n", '\n\n'.join(outputs), flush=True)
|
||||
if prompt is not None:
|
||||
self.prompt = prompt
|
||||
|
||||
def clean_response(response):
|
||||
meaningless_words = ['<pad>', '</s>', '<|endoftext|>']
|
||||
for word in meaningless_words:
|
||||
response = response.replace(word, "")
|
||||
if sanitize_bot_response:
|
||||
from better_profanity import profanity
|
||||
response = profanity.censor(response)
|
||||
response = response.strip("\n")
|
||||
return response
|
||||
|
||||
def clean_repeats(response):
|
||||
lines = response.split('\n')
|
||||
new_lines = []
|
||||
[new_lines.append(line) for line in lines if
|
||||
line not in new_lines or len(line) < self.allowed_repeat_line_length]
|
||||
if self.debug and len(lines) != len(new_lines):
|
||||
print("cleaned repeats: %s %s" % (len(lines), len(new_lines)), flush=True)
|
||||
response = '\n'.join(new_lines)
|
||||
return response
|
||||
|
||||
multi_output = len(outputs) > 1
|
||||
|
||||
for oi, output in enumerate(outputs):
|
||||
if self.prompt_type in [PromptType.plain.value, str(PromptType.plain.value), PromptType.plain.name]:
|
||||
output = clean_response(output)
|
||||
elif prompt is None:
|
||||
# then use most basic parsing like pipeline
|
||||
if self.botstr in output:
|
||||
if self.humanstr:
|
||||
output = clean_response(output.split(self.botstr)[1].strip().split(self.humanstr)[0].strip())
|
||||
else:
|
||||
# i.e. use after bot but only up to next bot
|
||||
output = clean_response(output.split(self.botstr)[1].strip().split(self.botstr)[0].strip())
|
||||
else:
|
||||
# output = clean_response(output.strip())
|
||||
# assume just not printed yet
|
||||
output = ""
|
||||
else:
|
||||
# find first instance of prereponse
|
||||
# prompt sometimes has odd characters, that mutate length,
|
||||
# so can't go by length alone
|
||||
if self.pre_response:
|
||||
outputi = output.find(prompt)
|
||||
if outputi >= 0:
|
||||
output = output[outputi + len(prompt):]
|
||||
allow_terminate = True
|
||||
else:
|
||||
# subtraction is risky due to space offsets sometimes, so only do if necessary
|
||||
output = output[len(prompt) - len(self.pre_response):]
|
||||
# [1] to avoid repeated pre_response, just take first (after prompt - pre_response for chat)
|
||||
if self.pre_response in output:
|
||||
output = output.split(self.pre_response)[1]
|
||||
allow_terminate = True
|
||||
else:
|
||||
if output:
|
||||
print("Failure of parsing or not enough output yet: %s" % output, flush=True)
|
||||
allow_terminate = False
|
||||
else:
|
||||
allow_terminate = True
|
||||
output = output[len(prompt):]
|
||||
# clean after subtract prompt out, so correct removal of pre_response
|
||||
output = clean_response(output).strip()
|
||||
if self.repeat_penalty:
|
||||
output = clean_repeats(output).strip()
|
||||
if self.terminate_response and allow_terminate:
|
||||
finds = []
|
||||
for term in self.terminate_response:
|
||||
finds.append(output.find(term))
|
||||
finds = [x for x in finds if x >= 0]
|
||||
if len(finds) > 0:
|
||||
termi = finds[0]
|
||||
output = output[:termi].strip()
|
||||
else:
|
||||
output = output.strip()
|
||||
else:
|
||||
output = output.strip()
|
||||
if multi_output:
|
||||
# prefix with output counter
|
||||
output = "\n=========== Output %d\n\n" % (1 + oi) + output
|
||||
if oi > 0:
|
||||
# post fix outputs with seperator
|
||||
output += '\n'
|
||||
outputs[oi] = output
|
||||
# join all outputs, only one extra new line between outputs
|
||||
output = '\n'.join(outputs)
|
||||
if self.debug:
|
||||
print("outputclean:\n", '\n\n'.join(outputs), flush=True)
|
||||
return output
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6de2981e86829a691119eafde29428b084e0adae7e0c15899714345a7276f750
|
||||
size 219206244
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:93438f2d371679804df1663ecaab602df8a3d2f7781b07426617464377d816ed
|
||||
size 219472570
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c902a0a7531e5c9c29de6ec4d0b710feaf4a641437e23ca6db976d4a13e79df6
|
||||
size 219659869
|
||||
3
pytorch_model-00001-of-00005.bin
Normal file
3
pytorch_model-00001-of-00005.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:64691fa6fa33a63aa2fad165e6215a17e79dac4a203b9f8c887907a72278660b
|
||||
size 4957630318
|
||||
3
pytorch_model-00002-of-00005.bin
Normal file
3
pytorch_model-00002-of-00005.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:75dd532c4cb4c3649e80191dac7f0120ce0d3a0f573f66da11f61290936eeb46
|
||||
size 4853861544
|
||||
3
pytorch_model-00003-of-00005.bin
Normal file
3
pytorch_model-00003-of-00005.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7ace0311fd3b140629c0bda15e5d6ebf23987d4905124da10fac7c0ff11e583e
|
||||
size 4858068625
|
||||
3
pytorch_model-00004-of-00005.bin
Normal file
3
pytorch_model-00004-of-00005.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ea6b0c3b72599fc88f0328bb9c1f5058cd33eff5a5897c0863cd09d713ffbea1
|
||||
size 5015385889
|
||||
3
pytorch_model-00005-of-00005.bin
Normal file
3
pytorch_model-00005-of-00005.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:17f12d59a0255f9b07e531081be6666b3e9507baa82d25ac412536f6badaffdd
|
||||
size 4158379959
|
||||
551
pytorch_model.bin.index.json
Normal file
551
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,551 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 23711021384.0
|
||||
},
|
||||
"weight_map": {
|
||||
"embed_out.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.embed_in.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.final_layer_norm.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.final_layer_norm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.0.attention.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.0.attention.masked_bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.1.attention.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.1.attention.masked_bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.10.attention.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.10.attention.masked_bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.11.attention.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.11.attention.masked_bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.12.attention.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.13.attention.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.14.attention.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.15.attention.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.16.attention.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.16.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.16.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.16.attention.masked_bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.16.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.16.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.16.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.16.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.17.attention.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.17.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.17.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.17.attention.masked_bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.17.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.17.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.17.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.17.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.18.attention.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.18.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.18.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.18.attention.masked_bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.18.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.18.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.18.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.18.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.19.attention.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.19.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.19.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.19.attention.masked_bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.19.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.19.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.19.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.19.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.2.attention.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.2.attention.masked_bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.20.attention.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.20.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.20.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.20.attention.masked_bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.20.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.20.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.20.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.20.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.21.attention.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.21.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.21.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.21.attention.masked_bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.21.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.21.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.21.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.21.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.22.attention.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.22.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.22.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.22.attention.masked_bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.22.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.22.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.22.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"gpt_neox.layers.23.attention.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.23.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.23.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.23.attention.masked_bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.23.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.23.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.23.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.24.attention.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.24.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.24.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.24.attention.masked_bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.25.attention.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.25.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.25.attention.masked_bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.26.attention.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.26.attention.masked_bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.27.attention.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.27.attention.masked_bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.28.attention.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.28.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.28.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.28.attention.masked_bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.28.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.28.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.28.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.28.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.28.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.29.attention.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.29.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.29.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.29.attention.masked_bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.29.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.29.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.29.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.29.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.29.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.3.attention.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.3.attention.masked_bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.30.attention.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.30.attention.dense.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.30.attention.dense.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.30.attention.masked_bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.30.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.30.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.30.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.30.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.30.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"gpt_neox.layers.31.attention.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.31.attention.dense.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.31.attention.dense.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.31.attention.masked_bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.31.attention.query_key_value.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.31.attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.31.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.31.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.31.post_attention_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.32.attention.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.32.attention.dense.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.32.attention.dense.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.32.attention.masked_bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.32.attention.query_key_value.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.32.attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.32.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.32.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.32.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.32.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.32.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.32.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.32.post_attention_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.33.attention.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.33.attention.dense.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.33.attention.dense.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.33.attention.masked_bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.33.attention.query_key_value.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.33.attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.33.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.33.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.33.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.33.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.33.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.33.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.33.post_attention_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.34.attention.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.34.attention.dense.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.34.attention.dense.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.34.attention.masked_bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.34.attention.query_key_value.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.34.attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.34.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.34.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.34.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.34.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.34.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.34.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.34.post_attention_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.35.attention.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.35.attention.dense.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.35.attention.dense.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.35.attention.masked_bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.35.attention.query_key_value.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.35.attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.35.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.35.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.35.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.35.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.35.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.35.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.35.post_attention_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"gpt_neox.layers.4.attention.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.4.attention.masked_bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.5.attention.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.5.attention.masked_bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.6.attention.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.6.attention.masked_bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.7.attention.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.7.attention.masked_bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"gpt_neox.layers.8.attention.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.8.attention.masked_bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.9.attention.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.9.attention.masked_bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
||||
"gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin"
|
||||
}
|
||||
}
|
||||
5
special_tokens_map.json
Normal file
5
special_tokens_map.json
Normal file
@@ -0,0 +1,5 @@
|
||||
{
|
||||
"bos_token": "<|endoftext|>",
|
||||
"eos_token": "<|endoftext|>",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
100529
tokenizer.json
Normal file
100529
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
9
tokenizer_config.json
Normal file
9
tokenizer_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"bos_token": "<|endoftext|>",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"tokenizer_class": "GPTNeoXTokenizer",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
Reference in New Issue
Block a user