microsoft/phi-2-pytdml
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: microsoft/phi-2-pytdml
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-12 18:57:21 +08:00
commit 482b0d2544
19 changed files with 51198 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
.gitattributes vendored Normal file
View File

@@ -0,0 +1,49 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 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
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack 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
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text

9
CODE_OF_CONDUCT.md Normal file
View File

@@ -0,0 +1,9 @@
# Microsoft Open Source Code of Conduct
This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
Resources:
- [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/)
- [Microsoft Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/)
- Contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with questions or concerns

22
LICENSE Normal file
View File

@@ -0,0 +1,22 @@
Microsoft.
Copyright (c) Microsoft Corporation.
MIT License
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED *AS IS*, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.

38
NOTICE.md Normal file
View File

@@ -0,0 +1,38 @@
NOTICES AND INFORMATION
Do Not Translate or Localize
This software incorporates material from third parties.
**Component.** https://github.com/Dao-AILab/flash-attention
**Open Source License/Copyright Notice.**
BSD 3-Clause License
Copyright (c) 2022, the respective contributors, as shown by the AUTHORS file.
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice, this
list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright notice,
this list of conditions and the following disclaimer in the documentation
and/or other materials provided with the distribution.
* Neither the name of the copyright holder nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

160
README.md Normal file
View File

@@ -0,0 +1,160 @@
---
license: mit
license_link: https://huggingface.co/microsoft/phi-2/resolve/main/LICENSE
language:
- en
pipeline_tag: text-generation
tags:
- nlp
- code
---
## Model Summary
Phi-2 is a Transformer with **2.7 billion** parameters. It was trained using the same data sources as [Phi-1.5](https://huggingface.co/microsoft/phi-1.5), augmented with a new data source that consists of various NLP synthetic texts and filtered websites (for safety and educational value). When assessed against benchmarks testing common sense, language understanding, and logical reasoning, Phi-2 showcased a nearly state-of-the-art performance among models with less than 13 billion parameters.
Our model hasn't been fine-tuned through reinforcement learning from human feedback. The intention behind crafting this open-source model is to provide the research community with a non-restricted small model to explore vital safety challenges, such as reducing toxicity, understanding societal biases, enhancing controllability, and more.
### PyTorch DirectML Changes
This model has been optimized by refining the scripts for enhanced DirectML (DML) performance. The optimization process includes simplifying the implementation and incorporating operator fusions to accelerate model inference. These optimized versions are hosted in the samples on the DirectML GitHub. Despite the changes, the original model checkpoints remain compatible, though some weights need updates to align with the new transformations.
#### Fused Operators for DML
- `apply_rotary_position_emb`
- `multi_head_attention`
- `mlp_phi2`
## How to Use
Phi-2 has been integrated in the `transformers` version 4.37.0, please ensure that you are using a version equal or higher than it.
Phi-2 is known for having an attention overflow issue (with FP16). If you are facing this issue, please enable/disable autocast on the [PhiAttention.forward()](https://github.com/huggingface/transformers/blob/main/src/transformers/models/phi/modeling_phi.py#L306) function.
## Intended Uses
Given the nature of the training data, the Phi-2 model is best suited for prompts using the QA format, the chat format, and the code format.
### QA Format:
You can provide the prompt as a standalone question as follows:
```markdown
Write a detailed analogy between mathematics and a lighthouse.
```
where the model generates the text after "." .
To encourage the model to write more concise answers, you can also try the following QA format using "Instruct: \<prompt\>\nOutput:"
```markdown
Instruct: Write a detailed analogy between mathematics and a lighthouse.
Output: Mathematics is like a lighthouse. Just as a lighthouse guides ships safely to shore, mathematics provides a guiding light in the world of numbers and logic. It helps us navigate through complex problems and find solutions. Just as a lighthouse emits a steady beam of light, mathematics provides a consistent framework for reasoning and problem-solving. It illuminates the path to understanding and helps us make sense of the world around us.
```
where the model generates the text after "Output:".
### Chat Format:
```markdown
Alice: I don't know why, I'm struggling to maintain focus while studying. Any suggestions?
Bob: Well, have you tried creating a study schedule and sticking to it?
Alice: Yes, I have, but it doesn't seem to help much.
Bob: Hmm, maybe you should try studying in a quiet environment, like the library.
Alice: ...
```
where the model generates the text after the first "Bob:".
### Code Format:
```python
def print_prime(n):
"""
Print all primes between 1 and n
"""
primes = []
for num in range(2, n+1):
is_prime = True
for i in range(2, int(math.sqrt(num))+1):
if num % i == 0:
is_prime = False
break
if is_prime:
primes.append(num)
print(primes)
```
where the model generates the text after the comments.
**Notes:**
* Phi-2 is intended for QA, chat, and code purposes. The model-generated text/code should be treated as a starting point rather than a definitive solution for potential use cases. Users should be cautious when employing these models in their applications.
* Direct adoption for production tasks without evaluation is out of scope of this project. As a result, the Phi-2 model has not been tested to ensure that it performs adequately for any production-level application. Please refer to the limitation sections of this document for more details.
* If you are using `transformers<4.37.0`, always load the model with `trust_remote_code=True` to prevent side-effects.
## Sample Code
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
torch.set_default_device("cuda")
model = AutoModelForCausalLM.from_pretrained("microsoft/phi-2", torch_dtype="auto", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-2", trust_remote_code=True)
inputs = tokenizer('''def print_prime(n):
"""
Print all primes between 1 and n
"""''', return_tensors="pt", return_attention_mask=False)
outputs = model.generate(**inputs, max_length=200)
text = tokenizer.batch_decode(outputs)[0]
print(text)
```
## Limitations of Phi-2
* Generate Inaccurate Code and Facts: The model may produce incorrect code snippets and statements. Users should treat these outputs as suggestions or starting points, not as definitive or accurate solutions.
* Limited Scope for code: Majority of Phi-2 training data is based in Python and use common packages such as "typing, math, random, collections, datetime, itertools". If the model generates Python scripts that utilize other packages or scripts in other languages, we strongly recommend users manually verify all API uses.
* Unreliable Responses to Instruction: The model has not undergone instruction fine-tuning. As a result, it may struggle or fail to adhere to intricate or nuanced instructions provided by users.
* Language Limitations: The model is primarily designed to understand standard English. Informal English, slang, or any other languages might pose challenges to its comprehension, leading to potential misinterpretations or errors in response.
* Potential Societal Biases: Phi-2 is not entirely free from societal biases despite efforts in assuring training data safety. There's a possibility it may generate content that mirrors these societal biases, particularly if prompted or instructed to do so. We urge users to be aware of this and to exercise caution and critical thinking when interpreting model outputs.
* Toxicity: Despite being trained with carefully selected data, the model can still produce harmful content if explicitly prompted or instructed to do so. We chose to release the model to help the open-source community develop the most effective ways to reduce the toxicity of a model directly after pretraining.
* Verbosity: Phi-2 being a base model often produces irrelevant or extra text and responses following its first answer to user prompts within a single turn. This is due to its training dataset being primarily textbooks, which results in textbook-like responses.
## Training
### Model
* Architecture: a Transformer-based model with next-word prediction objective
* Context length: 2048 tokens
* Dataset size: 250B tokens, combination of NLP synthetic data created by AOAI GPT-3.5 and filtered web data from Falcon RefinedWeb and SlimPajama, which was assessed by AOAI GPT-4.
* Training tokens: 1.4T tokens
* GPUs: 96xA100-80G
* Training time: 14 days
### Software
* [PyTorch](https://github.com/pytorch/pytorch)
* [DeepSpeed](https://github.com/microsoft/DeepSpeed)
* [Flash-Attention](https://github.com/HazyResearch/flash-attention)
### License
The model is licensed under the [MIT license](https://huggingface.co/microsoft/phi-2/resolve/main/LICENSE).
## Trademarks
This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow [Microsoft’s Trademark & Brand Guidelines](https://www.microsoft.com/en-us/legal/intellectualproperty/trademarks). Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party’s policies.

41
SECURITY.md Normal file
View File

@@ -0,0 +1,41 @@
<!-- BEGIN MICROSOFT SECURITY.MD V0.0.9 BLOCK -->
## Security
Microsoft takes the security of our software products and services seriously, which includes all source code repositories managed through our GitHub organizations, which include [Microsoft](https://github.com/Microsoft), [Azure](https://github.com/Azure), [DotNet](https://github.com/dotnet), [AspNet](https://github.com/aspnet) and [Xamarin](https://github.com/xamarin).
If you believe you have found a security vulnerability in any Microsoft-owned repository that meets [Microsoft's definition of a security vulnerability](https://aka.ms/security.md/definition), please report it to us as described below.
## Reporting Security Issues
**Please do not report security vulnerabilities through public GitHub issues.**
Instead, please report them to the Microsoft Security Response Center (MSRC) at [https://msrc.microsoft.com/create-report](https://aka.ms/security.md/msrc/create-report).
If you prefer to submit without logging in, send email to [secure@microsoft.com](mailto:secure@microsoft.com). If possible, encrypt your message with our PGP key; please download it from the [Microsoft Security Response Center PGP Key page](https://aka.ms/security.md/msrc/pgp).
You should receive a response within 24 hours. If for some reason you do not, please follow up via email to ensure we received your original message. Additional information can be found at [microsoft.com/msrc](https://www.microsoft.com/msrc).
Please include the requested information listed below (as much as you can provide) to help us better understand the nature and scope of the possible issue:
* Type of issue (e.g. buffer overflow, SQL injection, cross-site scripting, etc.)
* Full paths of source file(s) related to the manifestation of the issue
* The location of the affected source code (tag/branch/commit or direct URL)
* Any special configuration required to reproduce the issue
* Step-by-step instructions to reproduce the issue
* Proof-of-concept or exploit code (if possible)
* Impact of the issue, including how an attacker might exploit the issue
This information will help us triage your report more quickly.
If you are reporting for a bug bounty, more complete reports can contribute to a higher bounty award. Please visit our [Microsoft Bug Bounty Program](https://aka.ms/security.md/msrc/bounty) page for more details about our active programs.
## Preferred Languages
We prefer all communications to be in English.
## Policy
Microsoft follows the principle of [Coordinated Vulnerability Disclosure](https://aka.ms/security.md/cvd).
<!-- END MICROSOFT SECURITY.MD BLOCK -->

40
added_tokens.json Normal file
View File

@@ -0,0 +1,40 @@
{
"\t\t": 50294,
"\t\t\t": 50293,
"\t\t\t\t": 50292,
"\t\t\t\t\t": 50291,
"\t\t\t\t\t\t": 50290,
"\t\t\t\t\t\t\t": 50289,
"\t\t\t\t\t\t\t\t": 50288,
"\t\t\t\t\t\t\t\t\t": 50287,
" ": 50286,
" ": 50285,
" ": 50284,
" ": 50283,
" ": 50282,
" ": 50281,
" ": 50280,
" ": 50279,
" ": 50278,
" ": 50277,
" ": 50276,
" ": 50275,
" ": 50274,
" ": 50273,
" ": 50272,
" ": 50271,
" ": 50270,
" ": 50269,
" ": 50268,
" ": 50267,
" ": 50266,
" ": 50265,
" ": 50264,
" ": 50263,
" ": 50262,
" ": 50261,
" ": 50260,
" ": 50259,
" ": 50258,
" ": 50257
}

30
config.json Normal file
View File

@@ -0,0 +1,30 @@
{
"_name_or_path": "microsoft/phi-2",
"architectures": [
"PhiForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 50256,
"embd_pdrop": 0.0,
"eos_token_id": 50256,
"hidden_act": "gelu_new",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 10240,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 2048,
"model_type": "phi",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"partial_rotary_factor": 0.4,
"qk_layernorm": false,
"resid_pdrop": 0.1,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.37.0",
"use_cache": true,
"vocab_size": 51200
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

6
generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"transformers_version": "4.37.0.dev0",
"eos_token_id": 50256,
"bos_token_id": 50256
}

50001
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
model-00001-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7fbcdefa72edf7527bf5da40535b57d9f5bd3d16829b94a9d25d2b457df62e84
size 4995584424

3
model-00002-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:17b98759e4b7953cbcf63ec49be7edbc9b863b57c207d84a52f5d2f5bcfcf6b4
size 563832976

3
model.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ba97c47bf9dd8f44244f12f8b46ff26f57351f930860f6304395bfa8f7bbba16
size 5559452174

460
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,460 @@
{
"metadata": {
"total_size": 5559367680
},
"weight_map": {
"lm_head.bias": "model-00002-of-00002.safetensors",
"lm_head.weight": "model-00002-of-00002.safetensors",
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
"model.final_layernorm.bias": "model-00002-of-00002.safetensors",
"model.final_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.24.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.25.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.26.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.27.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.28.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.28.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.28.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.29.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.29.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.29.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.30.input_layernorm.bias": "model-00002-of-00002.safetensors",
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
"model.layers.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
"model.layers.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
"model.layers.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.dense.bias": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.dense.weight": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
"model.layers.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
"model.layers.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
"model.layers.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.dense.bias": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.dense.weight": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors"
}
}

5
special_tokens_map.json Normal file
View File

@@ -0,0 +1,5 @@
{
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"unk_token": "<|endoftext|>"
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:337da36be7a71a6e88aa9148967a7bc8736f4b47c7de8e19ba92b89e80734cfc
size 2114924

323
tokenizer_config.json Normal file
View File

@@ -0,0 +1,323 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50257": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50258": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50259": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50260": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50261": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50262": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50263": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50264": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50265": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50266": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50267": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50268": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50269": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50270": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50271": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50272": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50273": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50274": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50275": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50276": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50277": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50278": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50279": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50280": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50281": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50282": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50283": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50284": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50285": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50286": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50287": {
"content": "\t\t\t\t\t\t\t\t\t",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50288": {
"content": "\t\t\t\t\t\t\t\t",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50289": {
"content": "\t\t\t\t\t\t\t",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50290": {
"content": "\t\t\t\t\t\t",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50291": {
"content": "\t\t\t\t\t",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50292": {
"content": "\t\t\t\t",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50293": {
"content": "\t\t\t",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50294": {
"content": "\t\t",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"model_max_length": 2048,
"tokenizer_class": "CodeGenTokenizer",
"unk_token": "<|endoftext|>"
}

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long