初始化项目，由ModelHub XC社区提供模型
Model: livekit/opt-125m-endpoint-detector-2 Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
|||||||
|
*.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
|
||||||
|
model.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model_quantized.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
115
LICENSE
Normal file
115
LICENSE
Normal file
@@ -0,0 +1,115 @@
|
|||||||
|
LIVEKIT MODEL LICENSE AGREEMENT
|
||||||
|
|
||||||
|
1. Introduction
|
||||||
|
|
||||||
|
LiveKit Incorporated ("LiveKit") is making available its proprietary models for
|
||||||
|
use pursuant to the terms and conditions of this Agreement. As further
|
||||||
|
described below, you may use these LiveKit models freely but can only use them
|
||||||
|
together with the LiveKit Agents framework. You cannot use the LiveKit models
|
||||||
|
on a standalone basis or with any other frameworks.
|
||||||
|
|
||||||
|
BY CLICKING "I ACCEPT," OR BY DOWNLOADING, INSTALLING, OR OTHERWISE ACCESSING
|
||||||
|
OR USING THE LIVEKIT MATERIALS, YOU AGREE THAT YOU HAVE READ AND UNDERSTOOD,
|
||||||
|
AND, AS A CONDITION TO YOUR USE OF THE LIVEKIT MATERIALS, YOU AGREE TO BE
|
||||||
|
BOUND BY, THE FOLLOWING TERMS AND CONDITIONS.
|
||||||
|
|
||||||
|
2. Definitions
|
||||||
|
|
||||||
|
"Agreement" means this LiveKit Model License Agreement.
|
||||||
|
|
||||||
|
"Documentation" means the specifications, manuals, and documentation
|
||||||
|
accompanying any LiveKit Model and distributed by LiveKit.
|
||||||
|
|
||||||
|
"Licensee" or "you" means the individual or entity agreeing to be bound by
|
||||||
|
this Agreement.
|
||||||
|
|
||||||
|
"LiveKit Agents" means the proprietary LiveKit software framework for building
|
||||||
|
real-time multimodal AI applications with programmable backend participants.
|
||||||
|
|
||||||
|
"LiveKit Materials" means, collectively, the LiveKit Models and Documentation.
|
||||||
|
|
||||||
|
"LiveKit Model" means any of LiveKit's proprietary software models or
|
||||||
|
algorithms, including machine-learning software code, model weights,
|
||||||
|
inference-enabling software code, training-enabling software code, and
|
||||||
|
fine-tuning enabling software code. Any derivative works of a LiveKit Model,
|
||||||
|
whether developed by LiveKit, you, or any third party, will be deemed the
|
||||||
|
"LiveKit Model" for the purposes of this Agreement.
|
||||||
|
|
||||||
|
3. License Rights
|
||||||
|
|
||||||
|
Right to Use LiveKit Materials. Subject to the terms and conditions of this
|
||||||
|
Agreement, including the requirements of Section 3.b, LiveKit grants you a
|
||||||
|
nonexclusive, nontransferable, worldwide, royalty-free license under LiveKit's
|
||||||
|
intellectual property rights to use, reproduce, distribute, copy, and create
|
||||||
|
derivative works of the LiveKit Materials.
|
||||||
|
|
||||||
|
Limitation on Use. As a condition to your use of the LiveKit Materials, you
|
||||||
|
agree: (i) not to use any LiveKit Models on a standalone basis or with any
|
||||||
|
frameworks other than LiveKit Agents; (ii) not to use any LiveKit Materials or
|
||||||
|
any output from, or results of using, LiveKit Models (including any derivative
|
||||||
|
works thereof) to improve or otherwise develop any other models that are not
|
||||||
|
LiveKit Models; or (iii) distribute or otherwise make available the LiveKit
|
||||||
|
Materials (including any derivative works thereof) except (x) pursuant to the
|
||||||
|
terms of this Agreement, and (y) you reproduce the above copyright notice.
|
||||||
|
|
||||||
|
4. Intellectual Property
|
||||||
|
|
||||||
|
The LiveKit Materials are owned by LiveKit and its licensors. Except for the
|
||||||
|
rights granted to you under this Agreement, all rights are reserved and no
|
||||||
|
other express or implied rights are granted.
|
||||||
|
|
||||||
|
You will own any derivative works that you created from the LiveKit Materials,
|
||||||
|
subject to the terms of this Agreement.
|
||||||
|
|
||||||
|
5. Disclaimer
|
||||||
|
|
||||||
|
UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING, LIVEKIT PROVIDES
|
||||||
|
THE LIVEKIT MATERIALS, AND ANY OUTPUT OR RESULTS THEREFROM, ON AN "AS IS"
|
||||||
|
BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED,
|
||||||
|
INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OR CONDITIONS OF TITLE,
|
||||||
|
NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU
|
||||||
|
ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR
|
||||||
|
REDISTRIBUTING THE LIVEKIT MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR
|
||||||
|
USE OF THE LIVEKIT MATERIALS AND ANY OUTPUT AND RESULTS.
|
||||||
|
|
||||||
|
6. Limitation of Liability
|
||||||
|
|
||||||
|
IN NO EVENT AND UNDER NO LEGAL THEORY, WHETHER IN TORT (INCLUDING NEGLIGENCE),
|
||||||
|
CONTRACT, OR OTHERWISE, UNLESS REQUIRED BY APPLICABLE LAW (SUCH AS DELIBERATE
|
||||||
|
AND GROSSLY NEGLIGENT ACTS) OR AGREED TO IN WRITING, WILL LIVEKIT BE LIABLE TO
|
||||||
|
YOU FOR INDIRECT DAMAGES, INCLUDING ANY SPECIAL, INCIDENTAL, OR CONSEQUENTIAL
|
||||||
|
DAMAGES OF ANY CHARACTER ARISING AS A RESULT OF THIS AGREEMENT OR OUT OF THE
|
||||||
|
USE OR INABILITY TO USE THE LIVEKIT MATERIALS OR ANY OUTPUT OR RESULTS
|
||||||
|
THEREFROM (INCLUDING BUT NOT LIMITED TO DAMAGES FOR LOSS OF GOODWILL, WORK
|
||||||
|
STOPPAGE, COMPUTER FAILURE OR MALFUNCTION, OR ANY AND ALL OTHER COMMERCIAL
|
||||||
|
DAMAGES OR LOSSES), EVEN IF LIVEKIT HAS BEEN ADVISED OF THE POSSIBILITY OF
|
||||||
|
SUCH DAMAGES.
|
||||||
|
|
||||||
|
7. Trademarks
|
||||||
|
|
||||||
|
This Agreement does not grant permission to use the trade names, trademarks,
|
||||||
|
service marks, or product names of LiveKit, except as required for reasonable
|
||||||
|
and customary use in describing the origin of the LiveKit Materials.
|
||||||
|
|
||||||
|
8. Term and Termination
|
||||||
|
|
||||||
|
The term of this Agreement commences upon your acceptance of this Agreement
|
||||||
|
and continues in effect until you cease using the LiveKit Materials or it is
|
||||||
|
terminated by either party (on immediate written notice to the other party).
|
||||||
|
This Agreement will automatically terminate if you breach any of its terms.
|
||||||
|
Upon termination, you must immediately cease all use of the LiveKit Materials.
|
||||||
|
Sections 4, 5, 6, and 9 will survive termination.
|
||||||
|
|
||||||
|
9. Governing Law and Venue
|
||||||
|
|
||||||
|
This Agreement is subject to the laws of the State of California, without
|
||||||
|
regard to its conflict of laws principles. The UN Convention on Contracts for
|
||||||
|
the International Sale of Goods does not apply to this Agreement. The courts
|
||||||
|
located in San Francisco, California, have exclusive jurisdiction for any
|
||||||
|
dispute arising out of this Agreement.
|
||||||
|
|
||||||
|
+ + + +
|
||||||
|
|
||||||
|
Last Updated: November 25, 2024
|
||||||
|
|
||||||
|
|
||||||
199
README.md
Normal file
199
README.md
Normal file
@@ -0,0 +1,199 @@
|
|||||||
|
---
|
||||||
|
library_name: transformers
|
||||||
|
tags: []
|
||||||
|
---
|
||||||
|
|
||||||
|
# Model Card for Model ID
|
||||||
|
|
||||||
|
<!-- Provide a quick summary of what the model is/does. -->
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
## Model Details
|
||||||
|
|
||||||
|
### Model Description
|
||||||
|
|
||||||
|
<!-- Provide a longer summary of what this model is. -->
|
||||||
|
|
||||||
|
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
||||||
|
|
||||||
|
- **Developed by:** [More Information Needed]
|
||||||
|
- **Funded by [optional]:** [More Information Needed]
|
||||||
|
- **Shared by [optional]:** [More Information Needed]
|
||||||
|
- **Model type:** [More Information Needed]
|
||||||
|
- **Language(s) (NLP):** [More Information Needed]
|
||||||
|
- **License:** [More Information Needed]
|
||||||
|
- **Finetuned from model [optional]:** [More Information Needed]
|
||||||
|
|
||||||
|
### Model Sources [optional]
|
||||||
|
|
||||||
|
<!-- Provide the basic links for the model. -->
|
||||||
|
|
||||||
|
- **Repository:** [More Information Needed]
|
||||||
|
- **Paper [optional]:** [More Information Needed]
|
||||||
|
- **Demo [optional]:** [More Information Needed]
|
||||||
|
|
||||||
|
## Uses
|
||||||
|
|
||||||
|
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||||
|
|
||||||
|
### Direct Use
|
||||||
|
|
||||||
|
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
### Downstream Use [optional]
|
||||||
|
|
||||||
|
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
### Out-of-Scope Use
|
||||||
|
|
||||||
|
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Bias, Risks, and Limitations
|
||||||
|
|
||||||
|
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
### Recommendations
|
||||||
|
|
||||||
|
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||||
|
|
||||||
|
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||||
|
|
||||||
|
## How to Get Started with the Model
|
||||||
|
|
||||||
|
Use the code below to get started with the model.
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Training Details
|
||||||
|
|
||||||
|
### Training Data
|
||||||
|
|
||||||
|
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
### Training Procedure
|
||||||
|
|
||||||
|
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||||
|
|
||||||
|
#### Preprocessing [optional]
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
|
||||||
|
#### Training Hyperparameters
|
||||||
|
|
||||||
|
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||||
|
|
||||||
|
#### Speeds, Sizes, Times [optional]
|
||||||
|
|
||||||
|
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Evaluation
|
||||||
|
|
||||||
|
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||||
|
|
||||||
|
### Testing Data, Factors & Metrics
|
||||||
|
|
||||||
|
#### Testing Data
|
||||||
|
|
||||||
|
<!-- This should link to a Dataset Card if possible. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
#### Factors
|
||||||
|
|
||||||
|
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
#### Metrics
|
||||||
|
|
||||||
|
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
### Results
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
#### Summary
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
## Model Examination [optional]
|
||||||
|
|
||||||
|
<!-- Relevant interpretability work for the model goes here -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Environmental Impact
|
||||||
|
|
||||||
|
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||||
|
|
||||||
|
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
||||||
|
|
||||||
|
- **Hardware Type:** [More Information Needed]
|
||||||
|
- **Hours used:** [More Information Needed]
|
||||||
|
- **Cloud Provider:** [More Information Needed]
|
||||||
|
- **Compute Region:** [More Information Needed]
|
||||||
|
- **Carbon Emitted:** [More Information Needed]
|
||||||
|
|
||||||
|
## Technical Specifications [optional]
|
||||||
|
|
||||||
|
### Model Architecture and Objective
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
### Compute Infrastructure
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
#### Hardware
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
#### Software
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Citation [optional]
|
||||||
|
|
||||||
|
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||||
|
|
||||||
|
**BibTeX:**
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
**APA:**
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Glossary [optional]
|
||||||
|
|
||||||
|
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## More Information [optional]
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Model Card Authors [optional]
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Model Card Contact
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
6
added_tokens.json
Normal file
6
added_tokens.json
Normal file
@@ -0,0 +1,6 @@
|
|||||||
|
{
|
||||||
|
"<|assistant|>": 50268,
|
||||||
|
"<|im_end|>": 50266,
|
||||||
|
"<|im_start|>": 50265,
|
||||||
|
"<|user|>": 50267
|
||||||
|
}
|
||||||
31
config.json
Normal file
31
config.json
Normal file
@@ -0,0 +1,31 @@
|
|||||||
|
{
|
||||||
|
"_attn_implementation_autoset": true,
|
||||||
|
"_name_or_path": "/tmp/tmpgd41_aot",
|
||||||
|
"_remove_final_layer_norm": false,
|
||||||
|
"activation_dropout": 0.0,
|
||||||
|
"activation_function": "relu",
|
||||||
|
"architectures": [
|
||||||
|
"OPTForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 2,
|
||||||
|
"do_layer_norm_before": true,
|
||||||
|
"dropout": 0.1,
|
||||||
|
"enable_bias": true,
|
||||||
|
"eos_token_id": 2,
|
||||||
|
"ffn_dim": 3072,
|
||||||
|
"hidden_size": 768,
|
||||||
|
"init_std": 0.02,
|
||||||
|
"layer_norm_elementwise_affine": true,
|
||||||
|
"layerdrop": 0.0,
|
||||||
|
"max_position_embeddings": 2048,
|
||||||
|
"model_type": "opt",
|
||||||
|
"num_attention_heads": 12,
|
||||||
|
"num_hidden_layers": 12,
|
||||||
|
"pad_token_id": 1,
|
||||||
|
"prefix": "</s>",
|
||||||
|
"transformers_version": "4.46.3",
|
||||||
|
"use_cache": true,
|
||||||
|
"vocab_size": 50269,
|
||||||
|
"word_embed_proj_dim": 768
|
||||||
|
}
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
|||||||
|
{
|
||||||
|
"_from_model_config": true,
|
||||||
|
"bos_token_id": 2,
|
||||||
|
"eos_token_id": 2,
|
||||||
|
"pad_token_id": 1,
|
||||||
|
"transformers_version": "4.46.3"
|
||||||
|
}
|
||||||
50001
merges.txt
Normal file
50001
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:2c80c6cc55c8148165f05889eced757f15154e6f9b3125bf803038a8892a2f2f
|
||||||
|
size 500970384
|
||||||
3
model_quantized.onnx
Normal file
3
model_quantized.onnx
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:3d58bfb3708b5ac6840565259c0d6b500fab3424273d095c834ffeb7536fddd7
|
||||||
|
size 126099906
|
||||||
33
ort_config.json
Normal file
33
ort_config.json
Normal file
@@ -0,0 +1,33 @@
|
|||||||
|
{
|
||||||
|
"one_external_file": true,
|
||||||
|
"opset": null,
|
||||||
|
"optimization": {},
|
||||||
|
"quantization": {
|
||||||
|
"activations_dtype": "QUInt8",
|
||||||
|
"activations_symmetric": false,
|
||||||
|
"format": "QOperator",
|
||||||
|
"is_static": false,
|
||||||
|
"mode": "IntegerOps",
|
||||||
|
"nodes_to_exclude": [],
|
||||||
|
"nodes_to_quantize": [],
|
||||||
|
"operators_to_quantize": [
|
||||||
|
"Conv",
|
||||||
|
"MatMul",
|
||||||
|
"Attention",
|
||||||
|
"LSTM",
|
||||||
|
"Gather",
|
||||||
|
"Transpose",
|
||||||
|
"EmbedLayerNormalization"
|
||||||
|
],
|
||||||
|
"per_channel": false,
|
||||||
|
"qdq_add_pair_to_weight": false,
|
||||||
|
"qdq_dedicated_pair": false,
|
||||||
|
"qdq_op_type_per_channel_support_to_axis": {
|
||||||
|
"MatMul": 1
|
||||||
|
},
|
||||||
|
"reduce_range": false,
|
||||||
|
"weights_dtype": "QInt8",
|
||||||
|
"weights_symmetric": true
|
||||||
|
},
|
||||||
|
"use_external_data_format": false
|
||||||
|
}
|
||||||
36
special_tokens_map.json
Normal file
36
special_tokens_map.json
Normal file
@@ -0,0 +1,36 @@
|
|||||||
|
{
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|user|>",
|
||||||
|
"<|assistant|>"
|
||||||
|
],
|
||||||
|
"bos_token": {
|
||||||
|
"content": "</s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "</s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<pad>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"unk_token": {
|
||||||
|
"content": "</s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
250401
tokenizer.json
Normal file
250401
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
69
tokenizer_config.json
Normal file
69
tokenizer_config.json
Normal file
@@ -0,0 +1,69 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": true,
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"1": {
|
||||||
|
"content": "<pad>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"2": {
|
||||||
|
"content": "</s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"50265": {
|
||||||
|
"content": "<|im_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"50266": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"50267": {
|
||||||
|
"content": "<|user|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"50268": {
|
||||||
|
"content": "<|assistant|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|user|>",
|
||||||
|
"<|assistant|>"
|
||||||
|
],
|
||||||
|
"bos_token": "</s>",
|
||||||
|
"chat_template": "{% for message in messages %}{{'<|im_start|>' + '<|' + message['role'] + '|>' + message['content'] + '<|im_end|>'}}{% endfor %}",
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "</s>",
|
||||||
|
"errors": "replace",
|
||||||
|
"model_max_length": 1000000000000000019884624838656,
|
||||||
|
"pad_token": "<pad>",
|
||||||
|
"tokenizer_class": "GPT2Tokenizer",
|
||||||
|
"unk_token": "</s>"
|
||||||
|
}
|
||||||
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