first commit
This commit is contained in:
xxl
parent
07b8382957
commit
cb9fab3c2b
|
|
@ -0,0 +1,10 @@
|
|||
{
|
||||
"word_embedding_dimension": 2304,
|
||||
"pooling_mode_cls_token": false,
|
||||
"pooling_mode_mean_tokens": false,
|
||||
"pooling_mode_max_tokens": false,
|
||||
"pooling_mode_mean_sqrt_len_tokens": false,
|
||||
"pooling_mode_weightedmean_tokens": false,
|
||||
"pooling_mode_lasttoken": true,
|
||||
"include_prompt": true
|
||||
}
|
||||
124
README.md
124
README.md
|
|
@ -1,3 +1,123 @@
|
|||
# SFR-Embedding-Code-2B_R
|
||||
---
|
||||
license: cc-by-nc-4.0
|
||||
pipeline_tag: feature-extraction
|
||||
tags:
|
||||
- transformers
|
||||
- sentence-transformers
|
||||
- code
|
||||
- retrieval
|
||||
---
|
||||
<h1 align="center">Salesforce/SFR-Embedding-Code-2B_R</h1>
|
||||
|
||||
**SFR-Embedding by Salesforce Research.**
|
||||
|
||||
The Salesforce/SFR-Embedding-Code is a generalist embedding model family for multilingual and multi-task code and Text retrieval. It demonstrates superior performance compared to various open-source code embedding models across multiple code retrieval tasks.
|
||||
|
||||
Check out our [paper](https://arxiv.org/abs/2411.12644) for more details!
|
||||
|
||||
We also offer 400M-size model [Salesforce/SFR-Embedding-Code-400_R](https://huggingface.co/Salesforce/SFR-Embedding-Code-400M_R)
|
||||
|
||||
### Ethical Considerations
|
||||
This release is for research purposes only in support of an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. We encourage users to consider the common limitations of AI, comply with applicable laws, and leverage best practices when selecting use cases, particularly for high-risk scenarios where errors or misuse could significantly impact people’s lives, rights, or safety. For further guidance on use cases, refer to our [AUP](https://www.salesforce.com/content/dam/web/en_us/www/documents/legal/Agreements/policies/ExternalFacing_Services_Policy.pdf) and [AI AUP](https://www.salesforce.com/content/dam/web/en_us/www/documents/legal/Agreements/policies/ai-acceptable-use-policy.pdf).
|
||||
|
||||
### License Statement:
|
||||
Users need to make their own assessment regarding any obligations or responsibilities under the corresponding licenses or terms and conditions pertaining to the original datasets and data. This release is for research purposes only in support of an academic paper.
|
||||
|
||||
This released model is a fine-tuned version of Gemma and Gemma is provided under and subject to the Gemma Terms of Use found at ai.google.dev/gemma/terms. Additionally, the use of this model is restricted as set forth in the Gemma Prohibited Use Policy at ai.google.dev/gemma/prohibited_use_policy ("Prohibited Use Policy"), which is hereby incorporated by reference into this Agreement.
|
||||
|
||||
### Performance on CoIR Benchmark
|
||||
| Model | Model Size | CoIR AVG (NDCG@10) |
|
||||
|-----------------------|------------|---------------------|
|
||||
| **SFR-Embedding-Code** | 2B | 67.4 |
|
||||
| CodeSage-Large-v2 | 1.3B | 64.2 |
|
||||
| CodeSage-Large | 1.3B | 61.0 |
|
||||
| **SFR-Embedding-Code** | 400M | 61.9 |
|
||||
| CodeRankEmbed | 137M | 60.1 |
|
||||
| CodeSage-Base | 356M | 57.5 |
|
||||
| Voyage-Code-002 | - | 56.3 |
|
||||
| CodeSage-Small | 130M | 54.4 |
|
||||
|
||||
|
||||
SFR-Embedding Team († indicates co-leaders)
|
||||
* Ye Liu
|
||||
* Rui Meng
|
||||
* Shafiq Rayhan Joty
|
||||
* Silvio Savarese
|
||||
* Caiming Xiong †
|
||||
* Yingbo Zhou †
|
||||
* Semih Yavuz †
|
||||
|
||||
## How to run
|
||||
|
||||
#### Transformers
|
||||
```python
|
||||
import torch.nn.functional as F
|
||||
from transformers import AutoTokenizer, AutoModel
|
||||
|
||||
# Each query needs to be accompanied by an corresponding instruction describing the task.
|
||||
query_instruction_example = "Given Code or Text, retrieval relevant content"
|
||||
queries = [
|
||||
"how to implement quick sort in Python?"
|
||||
]
|
||||
|
||||
# No instruction needed for retrieval passages
|
||||
passages = [
|
||||
"def quick_sort(arr):\n if len(arr) <= 1:\n return arr\n pivot = arr[len(arr) // 2]\n left = [x for x in arr if x < pivot]\n middle = [x for x in arr if x == pivot]\n right = [x for x in arr if x > pivot]\n return quick_sort(left) + middle + quick_sort(right)",
|
||||
"def bubble_sort(arr):\n n = len(arr)\n for i in range(n):\n for j in range(0, n-i-1):\n if arr[j] > arr[j+1]:\n arr[j], arr[j+1] = arr[j+1], arr[j]\n return arr"
|
||||
]
|
||||
|
||||
# load model with tokenizer
|
||||
model = AutoModel.from_pretrained('Salesforce/SFR-Embedding-Code-2B_R', trust_remote_code=True)
|
||||
|
||||
# get the embeddings
|
||||
max_length = 32768
|
||||
query_embeddings = model.encode_queries(queries, instruction=query_instruction_example, max_length=max_length)
|
||||
passage_embeddings = model.encode_corpus(passages, max_length=max_length)
|
||||
|
||||
# normalize embeddings
|
||||
query_embeddings = F.normalize(query_embeddings, p=2, dim=1)
|
||||
passage_embeddings = F.normalize(passage_embeddings, p=2, dim=1)
|
||||
|
||||
scores = (query_embeddings @ passage_embeddings.T) * 100
|
||||
print(scores.tolist())
|
||||
# [[69.26929473876953, 58.41606903076172]]
|
||||
```
|
||||
|
||||
#### Sentence Transformers
|
||||
|
||||
```python
|
||||
from sentence_transformers import SentenceTransformer
|
||||
|
||||
# Each query needs to be accompanied by an corresponding instruction describing the task.
|
||||
query_instruction_example = "Instruct: Given Code or Text, retrieval relevant content\nQuery: "
|
||||
queries = ["how to implement quick sort in Python?"]
|
||||
|
||||
# No instruction needed for retrieval passages
|
||||
passages = [
|
||||
"def quick_sort(arr):\n if len(arr) <= 1:\n return arr\n pivot = arr[len(arr) // 2]\n left = [x for x in arr if x < pivot]\n middle = [x for x in arr if x == pivot]\n right = [x for x in arr if x > pivot]\n return quick_sort(left) + middle + quick_sort(right)",
|
||||
"def bubble_sort(arr):\n n = len(arr)\n for i in range(n):\n for j in range(0, n-i-1):\n if arr[j] > arr[j+1]:\n arr[j], arr[j+1] = arr[j+1], arr[j]\n return arr"
|
||||
]
|
||||
|
||||
# Load the Sentence Transformer model, including pooling
|
||||
model = SentenceTransformer('Salesforce/SFR-Embedding-Code-2B_R', trust_remote_code=True)
|
||||
|
||||
# Compute the embeddings for both queries and passages. Use 'prompt' for queries only
|
||||
query_embeddings = model.encode(queries, prompt=query_instruction_example)
|
||||
passage_embeddings = model.encode(passages)
|
||||
|
||||
# Compute the similarities between the queries and passages
|
||||
similarities = model.similarity(query_embeddings, passage_embeddings)
|
||||
print(similarities)
|
||||
# tensor([[0.6927, 0.5842]])
|
||||
```
|
||||
|
||||
### Citation
|
||||
```bibtex
|
||||
@article{liu2024codexembed,
|
||||
title={CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval},
|
||||
author={Liu, Ye and Meng, Rui and Jot, Shafiq and Savarese, Silvio and Xiong, Caiming and Zhou, Yingbo and Yavuz, Semih},
|
||||
journal={arXiv preprint arXiv:2411.12644},
|
||||
year={2024}
|
||||
}
|
||||
```
|
||||
|
||||
SFR-Embedding-Code-2B_R
|
||||
|
|
@ -0,0 +1,40 @@
|
|||
{
|
||||
"_name_or_path": "Salesforce/SFR-Embedding-Code-2B_R",
|
||||
"architectures": [
|
||||
"CodeXEmbedModel2B"
|
||||
],
|
||||
"auto_map": {
|
||||
"AutoConfig": "configuration_gemma2.CodeXEmbedConfig",
|
||||
"AutoModel": "modeling_gemma2.CodeXEmbedModel2B"
|
||||
},
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"attn_logit_softcapping": 50.0,
|
||||
"bos_token_id": 2,
|
||||
"cache_implementation": "hybrid",
|
||||
"eos_token_id": [
|
||||
1,
|
||||
107
|
||||
],
|
||||
"final_logit_softcapping": 30.0,
|
||||
"head_dim": 256,
|
||||
"hidden_act": "gelu_pytorch_tanh",
|
||||
"hidden_activation": "gelu_pytorch_tanh",
|
||||
"hidden_size": 2304,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 9216,
|
||||
"max_position_embeddings": 8192,
|
||||
"model_type": "codexembed2b",
|
||||
"num_attention_heads": 8,
|
||||
"num_hidden_layers": 26,
|
||||
"num_key_value_heads": 4,
|
||||
"pad_token_id": 0,
|
||||
"query_pre_attn_scalar": 256,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_theta": 10000.0,
|
||||
"sliding_window": 4096,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.45.1",
|
||||
"use_cache": true,
|
||||
"vocab_size": 256000
|
||||
}
|
||||
|
|
@ -0,0 +1,10 @@
|
|||
{
|
||||
"__version__": {
|
||||
"sentence_transformers": "3.0.1",
|
||||
"transformers": "4.41.2",
|
||||
"pytorch": "2.3.0+cu121"
|
||||
},
|
||||
"prompts": {},
|
||||
"default_prompt_name": null,
|
||||
"similarity_fn_name": "cosine"
|
||||
}
|
||||
|
|
@ -0,0 +1,156 @@
|
|||
# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
|
||||
# This file was automatically generated from <path_to_diff_file.py>.
|
||||
# Do NOT edit this file manually as any edits will be overwritten by the generation of
|
||||
# the file from the diff. If any change should be done, please apply the change to the
|
||||
# diff.py file directly.
|
||||
# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
|
||||
# coding=utf-8
|
||||
# Copyright 2024 Google Inc. 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.
|
||||
from transformers import PretrainedConfig
|
||||
|
||||
|
||||
class CodeXEmbedConfig(PretrainedConfig):
|
||||
r"""
|
||||
This is the configuration class to store the configuration of a [`Gemma2Model`]. It is used to instantiate an Gemma2
|
||||
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 Gemma2-7B.
|
||||
e.g. [google/gemma2-7b](https://huggingface.co/google/gemma2-7b)
|
||||
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 256000):
|
||||
Vocabulary size of the Gemma2 model. Defines the number of different tokens that can be represented by the
|
||||
`inputs_ids` passed when calling [`Gemma2Model`]
|
||||
hidden_size (`int`, *optional*, defaults to 3072):
|
||||
Dimension of the hidden representations.
|
||||
intermediate_size (`int`, *optional*, defaults to 24576):
|
||||
Dimension of the MLP representations.
|
||||
num_hidden_layers (`int`, *optional*, defaults to 28):
|
||||
Number of hidden layers in the Transformer decoder.
|
||||
num_attention_heads (`int`, *optional*, defaults to 16):
|
||||
Number of attention heads for each attention layer in the Transformer decoder.
|
||||
num_key_value_heads (`int`, *optional*, defaults to 16):
|
||||
This is the number of key_value heads that should be used to implement Grouped Query Attention. If
|
||||
`num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
|
||||
`num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When
|
||||
converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
|
||||
by meanpooling all the original heads within that group. For more details checkout [this
|
||||
paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
|
||||
`num_attention_heads`.
|
||||
head_dim (`int`, *optional*, defaults to 256):
|
||||
The attention head dimension.
|
||||
hidden_activation (`str` or `function`, *optional*, defaults to `"gelu_pytorch_tanh"`):
|
||||
The non-linear activation function (function or string) in the decoder.
|
||||
max_position_embeddings (`int`, *optional*, defaults to 8192):
|
||||
The maximum sequence length that this model might ever be used with.
|
||||
initializer_range (`float`, *optional*, defaults to 0.02):
|
||||
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
||||
rms_norm_eps (`float`, *optional*, defaults to 1e-06):
|
||||
The epsilon used by the rms normalization layers.
|
||||
use_cache (`bool`, *optional*, defaults to `True`):
|
||||
Whether or not the model should return the last key/values attentions (not used by all models). Only
|
||||
relevant if `config.is_decoder=True`.
|
||||
pad_token_id (`int`, *optional*, defaults to 0):
|
||||
Padding token id.
|
||||
eos_token_id (`int`, *optional*, defaults to 1):
|
||||
End of stream token id.
|
||||
bos_token_id (`int`, *optional*, defaults to 2):
|
||||
Beginning of stream token id.
|
||||
tie_word_embeddings (`bool`, *optional*, defaults to `True`):
|
||||
Whether to tie weight embeddings
|
||||
rope_theta (`float`, *optional*, defaults to 10000.0):
|
||||
The base period of the RoPE embeddings.
|
||||
attention_bias (`bool`, defaults to `False`, *optional*, defaults to `False`):
|
||||
Whether to use a bias in the query, key, value and output projection layers during self-attention.
|
||||
attention_dropout (`float`, *optional*, defaults to 0.0):
|
||||
The dropout ratio for the attention probabilities.
|
||||
final_logit_softcapping (`float`, *optional*, defaults to 30.0): scaling factor when applying tanh softcapping on the logits.
|
||||
attn_logit_softcapping (`float`, *optional*, defaults to 50.0): scaling factor when applying tanh softcapping on the attention scores.
|
||||
query_pre_attn_scalar (`float`, *optional*, defaults to 224): scaling factor used on the attention scores
|
||||
sliding_window (`int`, *optional*, defaults to 4096): in Gemma2, every other layer uses sliding window attention. This is the
|
||||
size of the sliding window.
|
||||
```python
|
||||
>>> from transformers import Gemma2Model, CodeXEmbedConfig
|
||||
>>> # Initializing a Gemma2 gemma2-9b style configuration
|
||||
>>> configuration = CodeXEmbedConfig()
|
||||
>>> # Initializing a model from the gemma2-9b style configuration
|
||||
>>> model = Gemma2Model(configuration)
|
||||
>>> # Accessing the model configuration
|
||||
>>> configuration = model.config
|
||||
```"""
|
||||
|
||||
model_type = "codexembed2b"
|
||||
keys_to_ignore_at_inference = ["past_key_values"]
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
vocab_size=256000,
|
||||
hidden_size=3072,
|
||||
intermediate_size=24576,
|
||||
num_hidden_layers=28,
|
||||
num_attention_heads=16,
|
||||
num_key_value_heads=16,
|
||||
head_dim=256,
|
||||
hidden_activation="gelu_pytorch_tanh",
|
||||
max_position_embeddings=8192,
|
||||
initializer_range=0.02,
|
||||
rms_norm_eps=1e-6,
|
||||
use_cache=True,
|
||||
pad_token_id=0,
|
||||
eos_token_id=1,
|
||||
bos_token_id=2,
|
||||
tie_word_embeddings=True,
|
||||
rope_theta=10000.0,
|
||||
attention_bias=False,
|
||||
attention_dropout=0.0,
|
||||
final_logit_softcapping=30.0,
|
||||
attn_logit_softcapping=50.0,
|
||||
query_pre_attn_scalar=224,
|
||||
sliding_window=4096,
|
||||
**kwargs,
|
||||
):
|
||||
self.vocab_size = vocab_size
|
||||
self.max_position_embeddings = max_position_embeddings
|
||||
self.hidden_size = hidden_size
|
||||
self.intermediate_size = intermediate_size
|
||||
self.num_hidden_layers = num_hidden_layers
|
||||
self.num_attention_heads = num_attention_heads
|
||||
self.head_dim = head_dim
|
||||
self.num_key_value_heads = num_key_value_heads
|
||||
self.hidden_activation = hidden_activation
|
||||
self.initializer_range = initializer_range
|
||||
self.rms_norm_eps = rms_norm_eps
|
||||
self.use_cache = use_cache
|
||||
self.rope_theta = rope_theta
|
||||
self.attention_bias = attention_bias
|
||||
self.attention_dropout = attention_dropout
|
||||
self.attn_logit_softcapping = attn_logit_softcapping
|
||||
|
||||
super().__init__(
|
||||
pad_token_id=pad_token_id,
|
||||
bos_token_id=bos_token_id,
|
||||
eos_token_id=eos_token_id,
|
||||
tie_word_embeddings=tie_word_embeddings,
|
||||
**kwargs,
|
||||
)
|
||||
self.final_logit_softcapping = final_logit_softcapping
|
||||
self.query_pre_attn_scalar = query_pre_attn_scalar
|
||||
self.sliding_window = sliding_window
|
||||
self.cache_implementation = "hybrid"
|
||||
|
||||
MODEL_TYPE = "codexembed2b"
|
||||
from transformers import AutoConfig
|
||||
AutoConfig.register(MODEL_TYPE, CodeXEmbedConfig)
|
||||
Binary file not shown.
Binary file not shown.
|
|
@ -0,0 +1,295 @@
|
|||
{
|
||||
"metadata": {
|
||||
"total_size": 5228683776
|
||||
},
|
||||
"weight_map": {
|
||||
"embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.0.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.1.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.10.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.10.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.11.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.11.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.12.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.12.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.13.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.13.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.14.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.14.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.15.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.15.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.16.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.16.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.17.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.17.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.18.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.18.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.19.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.19.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.2.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.20.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.20.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.21.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.21.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.22.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.22.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.23.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.23.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"layers.24.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"layers.24.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"layers.25.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"layers.25.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.3.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.4.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.5.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.6.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.7.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.8.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.8.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.9.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.9.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"norm.weight": "model-00002-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,14 @@
|
|||
[
|
||||
{
|
||||
"idx": 0,
|
||||
"name": "0",
|
||||
"path": "",
|
||||
"type": "sentence_transformers.models.Transformer"
|
||||
},
|
||||
{
|
||||
"idx": 1,
|
||||
"name": "1",
|
||||
"path": "1_Pooling",
|
||||
"type": "sentence_transformers.models.Pooling"
|
||||
}
|
||||
]
|
||||
|
|
@ -0,0 +1,4 @@
|
|||
{
|
||||
"max_seq_length": 4096,
|
||||
"do_lower_case": false
|
||||
}
|
||||
|
|
@ -0,0 +1,34 @@
|
|||
{
|
||||
"additional_special_tokens": [
|
||||
"<start_of_turn>",
|
||||
"<end_of_turn>"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<bos>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<eos>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
Binary file not shown.
Binary file not shown.
File diff suppressed because it is too large
Load Diff
Loading…
Reference in New Issue