初始化项目，由ModelHub XC社区提供模型
Model: KnutJaegersberg/falcon-1b-t-sft Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
137
README.md
Normal file
137
README.md
Normal file
@@ -0,0 +1,137 @@
|
||||
---
|
||||
license: cc-by-nc-4.0
|
||||
datasets:
|
||||
- KnutJaegersberg/trilobite
|
||||
model-index:
|
||||
- name: falcon-1b-t-sft
|
||||
results:
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: AI2 Reasoning Challenge (25-Shot)
|
||||
type: ai2_arc
|
||||
config: ARC-Challenge
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 25
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 32.94
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/falcon-1b-t-sft
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: HellaSwag (10-Shot)
|
||||
type: hellaswag
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 10
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 57.24
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/falcon-1b-t-sft
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: MMLU (5-Shot)
|
||||
type: cais/mmlu
|
||||
config: all
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 25.26
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/falcon-1b-t-sft
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: TruthfulQA (0-shot)
|
||||
type: truthful_qa
|
||||
config: multiple_choice
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 0
|
||||
metrics:
|
||||
- type: mc2
|
||||
value: 38.49
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/falcon-1b-t-sft
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: Winogrande (5-shot)
|
||||
type: winogrande
|
||||
config: winogrande_xl
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 55.88
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/falcon-1b-t-sft
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: GSM8k (5-shot)
|
||||
type: gsm8k
|
||||
config: main
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 0.3
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/falcon-1b-t-sft
|
||||
name: Open LLM Leaderboard
|
||||
---
|
||||
|
||||
Made for the purpose of comparison with the tinyllama model. 3 epochs, neftune on trilobite.
|
||||
|
||||
Prompt Example:
|
||||
```
|
||||
### System:
|
||||
|
||||
You are an AI assistant. User will give you a task. Your goal is to complete the task as faithfully as you can. While performing the task think step-by-step and justify your steps.
|
||||
|
||||
|
||||
### Instruction:
|
||||
|
||||
How do you fine tune a large language model?
|
||||
|
||||
### Response:
|
||||
```
|
||||
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
||||
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_KnutJaegersberg__falcon-1b-t-sft)
|
||||
|
||||
| Metric |Value|
|
||||
|---------------------------------|----:|
|
||||
|Avg. |35.02|
|
||||
|AI2 Reasoning Challenge (25-Shot)|32.94|
|
||||
|HellaSwag (10-Shot) |57.24|
|
||||
|MMLU (5-Shot) |25.26|
|
||||
|TruthfulQA (0-shot) |38.49|
|
||||
|Winogrande (5-shot) |55.88|
|
||||
|GSM8k (5-shot) | 0.30|
|
||||
|
||||
35
config.json
Normal file
35
config.json
Normal file
@@ -0,0 +1,35 @@
|
||||
{
|
||||
"_name_or_path": "/run/media/knut/HD/huggingface models/language models/llama-alternatives/falcon-rw-1b/",
|
||||
"alibi": true,
|
||||
"apply_residual_connection_post_layernorm": false,
|
||||
"architectures": [
|
||||
"FalconForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"auto_map": {
|
||||
"AutoConfig": "configuration_falcon.FalconConfig",
|
||||
"AutoModel": "modeling_falcon.FalconModel",
|
||||
"AutoModelForCausalLM": "modeling_falcon.FalconForCausalLM",
|
||||
"AutoModelForQuestionAnswering": "modeling_falcon.FalconForQuestionAnswering",
|
||||
"AutoModelForSequenceClassification": "modeling_falcon.FalconForSequenceClassification",
|
||||
"AutoModelForTokenClassification": "modeling_falcon.FalconForTokenClassification"
|
||||
},
|
||||
"bias": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_dropout": 0.0,
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "falcon",
|
||||
"multi_query": false,
|
||||
"new_decoder_architecture": false,
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 24,
|
||||
"num_kv_heads": 32,
|
||||
"parallel_attn": false,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.35.2",
|
||||
"use_cache": false,
|
||||
"vocab_size": 50257
|
||||
}
|
||||
147
configuration_falcon.py
Normal file
147
configuration_falcon.py
Normal file
@@ -0,0 +1,147 @@
|
||||
# coding=utf-8
|
||||
# Copyright 2023 the Falcon authors and HuggingFace Inc. team. All rights reserved.
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
""" Falcon configuration"""
|
||||
from transformers.configuration_utils import PretrainedConfig
|
||||
from transformers.utils import logging
|
||||
|
||||
|
||||
logger = logging.get_logger(__name__)
|
||||
|
||||
FALCON_PRETRAINED_CONFIG_ARCHIVE_MAP = {
|
||||
"tiiuae/falcon-40b": "https://huggingface.co/tiiuae/falcon-40b/resolve/main/config.json",
|
||||
"tiiuae/falcon-7b": "https://huggingface.co/tiiuae/falcon-7b/resolve/main/config.json",
|
||||
}
|
||||
|
||||
|
||||
class FalconConfig(PretrainedConfig):
|
||||
r"""
|
||||
This is the configuration class to store the configuration of a [`FalconModel`]. It is used to instantiate a Falcon
|
||||
model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
|
||||
defaults will yield a similar configuration to that of the
|
||||
[tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b) architecture.
|
||||
|
||||
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
||||
documentation from [`PretrainedConfig`] for more information.
|
||||
|
||||
|
||||
Args:
|
||||
vocab_size (`int`, *optional*, defaults to 65024):
|
||||
Vocabulary size of the Falcon model. Defines the number of different tokens that can be represented by the
|
||||
`inputs_ids` passed when calling [`FalconModel`]
|
||||
hidden_size (`int`, *optional*, defaults to 4544):
|
||||
Dimension of the hidden representations.
|
||||
num_hidden_layers (`int`, *optional*, defaults to 32):
|
||||
Number of hidden layers in the Transformer decoder.
|
||||
num_attention_heads (`int`, *optional*, defaults to 71):
|
||||
Number of attention heads for each attention layer in the Transformer encoder.
|
||||
initializer_range (`float`, *optional*, defaults to 0.02):
|
||||
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
||||
use_cache (`bool`, *optional*, defaults to `True`):
|
||||
Whether the model should return the last key/values attentions (not used by all models). Only relevant if
|
||||
`config.is_decoder=True`.
|
||||
layer_norm_epsilon (`float`, *optional*, defaults to 1e-5):
|
||||
The epsilon used by the layer normalization layers.
|
||||
hidden_dropout (`float`, *optional*, defaults to 0.0):
|
||||
The dropout probability for MLP layers.
|
||||
attention_dropout (`float`, *optional*, defaults to 0.0):
|
||||
The dropout probability for attention layers.
|
||||
num_kv_heads (`int`, *optional*):
|
||||
Number of key-value heads to use per attention layer. If unset, defaults to the same value as
|
||||
`num_attention_heads`.
|
||||
alibi (`bool`, *optional*, defaults to `False`):
|
||||
Whether to use ALiBi positional biases during self-attention.
|
||||
new_decoder_architecture (`bool`, *optional*, defaults to `False`):
|
||||
Whether to use the new (Falcon-40B) decoder architecture. If `True`, the `multi_query` and `parallel_attn`
|
||||
arguments are ignored, as the new decoder always uses parallel attention.
|
||||
multi_query (`bool`, *optional*, defaults to `True`):
|
||||
Whether to use multi-query attention in the decoder. Ignored when `new_decoder_architecture` is `True`.
|
||||
parallel_attn (`bool`, *optional*, defaults to `True`):
|
||||
Whether to compute attention in parallel with the feedforward layer. If False, they are consecutive
|
||||
instead, as in the original Transformer architecture. Ignored when `new_decoder_architecture` is `True`.
|
||||
bias (`bool`, *optional*, defaults to `False`):
|
||||
Whether to use bias on Linear layers.
|
||||
bos_token_id (`int`, *optional*, defaults to 11):
|
||||
The id of the "beginning-of-sequence" token.
|
||||
eos_token_id (`int`, *optional*, defaults to 11):
|
||||
The id of the "end-of-sequence" token.
|
||||
|
||||
Example:
|
||||
|
||||
```python
|
||||
>>> from transformers import FalconModel, FalconConfig
|
||||
|
||||
>>> # Initializing a small (2-layer) Falcon configuration
|
||||
>>> configuration = FalconConfig(num_hidden_layers=2)
|
||||
|
||||
>>> # Initializing a model from the small configuration
|
||||
>>> model = FalconModel(configuration)
|
||||
|
||||
>>> # Accessing the model configuration
|
||||
>>> configuration = model.config
|
||||
```"""
|
||||
model_type = "falcon"
|
||||
keys_to_ignore_at_inference = ["past_key_values"]
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
vocab_size=65024,
|
||||
hidden_size=4544,
|
||||
num_hidden_layers=32,
|
||||
num_attention_heads=71,
|
||||
layer_norm_epsilon=1e-5,
|
||||
initializer_range=0.02,
|
||||
use_cache=True,
|
||||
hidden_dropout=0.0,
|
||||
attention_dropout=0.0,
|
||||
num_kv_heads=None,
|
||||
alibi=False,
|
||||
new_decoder_architecture=False,
|
||||
multi_query=True,
|
||||
parallel_attn=True,
|
||||
bias=False,
|
||||
bos_token_id=11,
|
||||
eos_token_id=11,
|
||||
**kwargs,
|
||||
):
|
||||
self.vocab_size = vocab_size
|
||||
# Backward compatibility with n_embed kwarg
|
||||
n_embed = kwargs.pop("n_embed", None)
|
||||
self.hidden_size = hidden_size if n_embed is None else n_embed
|
||||
self.num_hidden_layers = num_hidden_layers
|
||||
self.num_attention_heads = num_attention_heads
|
||||
self.layer_norm_epsilon = layer_norm_epsilon
|
||||
self.initializer_range = initializer_range
|
||||
self.use_cache = use_cache
|
||||
self.hidden_dropout = hidden_dropout
|
||||
self.attention_dropout = attention_dropout
|
||||
|
||||
self.bos_token_id = bos_token_id
|
||||
self.eos_token_id = eos_token_id
|
||||
self.num_kv_heads = num_attention_heads if num_kv_heads is None else num_kv_heads
|
||||
self.alibi = alibi
|
||||
self.new_decoder_architecture = new_decoder_architecture
|
||||
self.multi_query = multi_query # Ignored when new_decoder_architecture is True
|
||||
self.parallel_attn = parallel_attn
|
||||
self.bias = bias
|
||||
|
||||
super().__init__(bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)
|
||||
|
||||
@property
|
||||
def head_dim(self):
|
||||
return self.hidden_size // self.num_attention_heads
|
||||
|
||||
@property
|
||||
def rotary(self):
|
||||
return not self.alibi
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.35.2"
|
||||
}
|
||||
50001
merges.txt
Normal file
50001
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:305912bff5026e3c916ac1ccf904b3910edf879692d14952065c0a9c0d59116a
|
||||
size 4977548344
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:00dd5c560aa979bcc7017193e8101a80b0470fafd85c5022f992ace07607f3ff
|
||||
size 268601552
|
||||
298
model.safetensors.index.json
Normal file
298
model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 5246115840
|
||||
},
|
||||
"weight_map": {
|
||||
"transformer.h.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.self_attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.self_attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.self_attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.self_attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.self_attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.self_attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.self_attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.self_attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.self_attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.self_attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.self_attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.self_attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.self_attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.self_attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.self_attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.22.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.22.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.22.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.22.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.22.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.22.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.22.self_attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.22.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.22.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.22.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.23.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.23.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.23.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.23.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.23.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.23.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.23.self_attention.dense.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.23.self_attention.dense.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.23.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.23.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.self_attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.self_attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.self_attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.self_attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.self_attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.self_attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.self_attention.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.ln_f.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.ln_f.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.word_embeddings.weight": "model-00001-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
1262
modeling_falcon.py
Normal file
1262
modeling_falcon.py
Normal file
File diff suppressed because it is too large
Load Diff
6
special_tokens_map.json
Normal file
6
special_tokens_map.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"bos_token": "<|endoftext|>",
|
||||
"eos_token": "<|endoftext|>",
|
||||
"pad_token": "<|endoftext|>",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
100305
tokenizer.json
Normal file
100305
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
20
tokenizer_config.json
Normal file
20
tokenizer_config.json
Normal file
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"50256": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"bos_token": "<|endoftext|>",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"model_max_length": 1024,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user