driaforall/Dria-Agent-a-7B
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: driaforall/Dria-Agent-a-7B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-29 22:56:15 +08:00
commit b345d12442
16 changed files with 455758 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View File

@@ -0,0 +1,35 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text

202
LICENSE Normal file
View File

@@ -0,0 +1,202 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) 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 Work and assume any
risks associated with Your exercise of permissions under this License.
8. 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, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (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 such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright 2024 Alibaba Cloud
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.

241
README.md Normal file
View File

@@ -0,0 +1,241 @@
---
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct/blob/main/LICENSE
language:
- en
base_model:
- Qwen/Qwen2.5-Coder-7B-Instruct
pipeline_tag: text-generation
library_name: transformers
tags:
- code
- chat
- qwen
- qwen-coder
- agent
---
# Dria-Agent-α-7B
## Introduction
***Dria-Agent-α*** are series of large language models trained on top of the [Qwen2.5-Coder](https://huggingface.co/collections/Qwen/qwen25-coder-66eaa22e6f99801bf65b0c2f) series, specifically on top of the [Qwen/Qwen2.5-Coder-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct) and [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) models to be used in agentic applications. These models are the first instalment of agent-focused LLMs (hence the **α** in the naming) we hope to improve with better and more elaborate techniques in subsequent releases.
Dria-Agent-α employs ***Pythonic function calling***, which is LLMs using blocks of Python code to interact with provided tools and output actions. This method was inspired by many previous work, including but not limited to [DynaSaur](https://arxiv.org/pdf/2411.01747), [RLEF](https://arxiv.org/pdf/2410.02089), [ADAS](https://arxiv.org/pdf/2408.08435) and [CAMEL](https://arxiv.org/pdf/2303.17760). This way of function calling has a few advantages over traditional JSON-based function calling methods:
1. **One-shot Parallel Multiple Function Calls:** The model can can utilise many synchronous processes in one chat turn to arrive to a solution, which would require other function calling models multiple turns of conversation.
2. **Free-form Reasoning and Actions:** The model provides reasoning traces freely in natural language and the actions in between \`\`\`python \`\`\` blocks, as it already tends to do without special prompting or tuning. This tries to mitigate the possible performance loss caused by imposing specific formats on LLM outputs discussed in [Let Me Speak Freely?](https://arxiv.org/pdf/2408.02442)
3. **On-the-fly Complex Solution Generation:** The solution provided by the model is essentially a Python program with the exclusion of some "risky" builtins like `exec`, `eval` and `compile` (see full list in **Quickstart** below). This enables the model to implement custom complex logic with conditionals and synchronous pipelines (using the output of one function in the next function's arguments) which would not be possible with the current JSON-based function calling methods (as far as we know).
## Quickstart
````python
import json
from typing import Any, Dict, List
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "driaforall/Dria-Agent-a-7B"
model = AutoModelForCausalLM.from_pretrained(
model_name, device_map="auto", torch_dtype="auto", trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
# Please use our provided prompt for best performance
SYSTEM_PROMPT = """
You are an expert AI assistant that specializes in providing Python code to solve the task/problem at hand provided by the user.
You can use Python code freely, including the following available functions:
<|functions_schema|>
{{functions_schema}}
<|end_functions_schema|>
The following dangerous builtins are restricted for security:
- exec
- eval
- execfile
- compile
- importlib
- input
- exit
Think step by step and provide your reasoning, outside of the function calls.
You can write Python code and use the available functions. Provide all your python code in a SINGLE markdown code block like the following:
```python
result = example_function(arg1, "string")
result2 = example_function2(result, arg2)
```
DO NOT use print() statements AT ALL. Avoid mutating variables whenever possible.
""".strip()
get_sample_data = """
def check_availability(day: str, start_time: str, end_time: str) -> bool:
\"\"\"
Check if a time slot is available on a given day.
Args:
- day: The day to check in YYYY-MM-DD format
- start_time: Start time in HH:MM format
- end_time: End time in HH:MM format
Returns:
- True if slot is available, False otherwise
\"\"\"
pass
def make_appointment(day: str, start_time: str, end_time: str) -> dict:
\"\"\"
Make an appointment for a given time slot.
Args:
- day: The day to make appointment in YYYY-MM-DD format
- start_time: Start time in HH:MM format
- end_time: End time in HH:MM format
- title: The title of the appointment
Returns:
- A dictionary with the appointment details and if it's made or not.
dict keys:
- day (str): The day the appointment is on, in YYYY-MM-DD format
- start_time (str): Start time in HH:MM format
- end_time (str): End time in HH:MM format
- appointment_made (bool): Whether the appointment is successfully made or not.
\"\"\"
pass
def add_to_reminders(reminder_text: str) -> bool:
\"\"\"
Add a text to reminders.
Args:
- reminder_text: The text to add to reminders
Returns:
- Whether the reminder was successfully created or not.
\"\"\"
pass
"""
# Helper function to create the system prompt for our model
def format_prompt(tools: str):
return SYSTEM_PROMPT.format(functions_schema=tools)
system_prompt = SYSTEM_PROMPT.replace("{{functions_schema}}", get_sample_data)
USER_QUERY = """
Can you check if I have tomorrow 10:00-12:00 available and make an appointment for a meeting
with my thesis supervisor if so? If you made the appointment, please add it to my reminders.
"""
messages = [
{"role": "system", "content": system_prompt},
{"role": "user", "content": USER_QUERY},
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
generated_ids = model.generate(
**model_inputs,
max_new_tokens=2048
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)
````
The output should be something like:
````
To accomplish this task, we need to follow these steps:
1. Check if the time slot from 10:00 to 12:00 on tomorrow is available using the `check_availability` function.
2. If the slot is available, proceed to make an appointment using the `make_appointment` function.
3. If the appointment is successfully made, add it to the reminders using the `add_to_reminders` function.
Let's break down the code into these steps:
```python
from datetime import datetime, timedelta
# Get tomorrow's date
tomorrow = (datetime.now() + timedelta(days=1)).strftime("%Y-%m-%d")
# Define the time slots
start_time = "10:00"
end_time = "12:00"
# Step 1: Check availability
is_available = check_availability(tomorrow, start_time, end_time)
if is_available:
# Step 2: Make the appointment
appointment_details = make_appointment(tomorrow, start_time, end_time, "Meeting with thesis supervisor")
if appointment_details['appointment_made']:
# Step 3: Add to reminders
reminder_text = f"Appointment with thesis supervisor scheduled for {tomorrow} from {start_time} to {end_time}."
add_to_reminders(reminder_text)
else:
appointment_details = {"day": tomorrow, "start_time": start_time, "end_time": end_time, "appointment_made": False}
```
This code will first determine if the specified time slot is available tomorrow. If it is, it will attempt to make the appointment and then add it to the reminders if successful.
````
## Evaluation & Performance
We evaluate the model on the following benchmarks:
1. Berkeley Function Calling Leaderboard (BFCL)
2. MMLU-Pro
3. **Dria-Pythonic-Agent-Benchmark (DPAB):** The benchmark we curated with a synthetic data generation +model-based validation + filtering and manual selection to evaluate LLMs on their Pythonic function calling ability, spanning multiple scenarios and tasks. More detailed information about the benchmark and the Github repo will be released soon.
Below are the BFCL results: evaluation results for ***Qwen2.5-Coder-3B-Instruct***, ***Dria-Agent-α-3B***, ***Dria-Agent-α-7B***, and ***gpt-4o-2024-11-20***
| Metric | Qwen/Qwen2.5-3B-Instruct | Dria-Agent-a-3B | Dria-Agent-7B | gpt-4o-2024-11-20 (Prompt) |
|---------------------------------------|----------------------------|-------------------|-------------------|---------------------------|
| **Non-Live Simple AST** | 75.50% | 75.08% | 77.58% | 79.42% |
| **Non-Live Multiple AST** | 90.00% | 93.00% | 94.00% | 95.50% |
| **Non-Live Parallel AST** | 80.00% | 85.00% | 93.50% | 94.00% |
| **Non-Live Parallel Multiple AST** | 78.50% | 79.00% | 89.50% | 83.50% |
| **Non-Live Simple Exec** | 82.07% | 87.57% | 93.29% | 100.00% |
| **Non-Live Multiple Exec** | 86.00% | 85.14% | 88.00% | 94.00% |
| **Non-Live Parallel Exec** | 82.00% | 90.00% | 88.00% | 86.00% |
| **Non-Live Parallel Multiple Exec** | 80.00% | 88.00% | 72.50% | 77.50% |
| **Live Simple AST** | 68.22% | 70.16% | 81.40% | 83.72% |
| **Live Multiple AST** | 66.00% | 67.14% | 78.73% | 79.77% |
| **Live Parallel AST** | 62.50% | 50.00% | 75.00% | 87.50% |
| **Live Parallel Multiple AST** | 66.67% | 70.83% | 62.50% | 70.83% |
| **Relevance Detection** | 88.89% | 100.00% | 100.00% | 83.33% |
and the MMLU-Pro and DPAB results:
| Benchmark Name | Qwen2.5-Coder-7B-Instruct | Dria-Agent-α-7B |
|----------------|---------------------------|-----------------|
| MMLU-Pro | 45.6 ([Self Reported](https://arxiv.org/pdf/2409.12186)) | 42.54 |
| DPAB (Pythonic, Strict) | 44.0 | 70.0 |
**\*Note:** The model tends to use Pythonic function calling for a lot of the test cases in STEM-related fields (math, physics, chemistry, etc.) in the MMLU-Pro benchmark, which isn't captured by the evaluation framework and scripts provided in their [Github repository](https://github.com/TIGER-AI-Lab/MMLU-Pro/tree/main). We haven't modified the script for evaluation, and leave it for the future iterations of this model. However, by performing qualitative analysis on the model responses, we suspect that the model's score will increase instead of suffering a ~3% decrease.
#### Citation
```
@misc{Dria-Agent-a,
url={https://huggingface.co/blog/andthattoo/dria-agent-a},
title={Dria-Agent-a},
author={"andthattoo", "Atakan Tekparmak"}
}
```

27
config.json Normal file
View File

@@ -0,0 +1,27 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 32768,
"max_window_layers": 28,
"model_type": "qwen2",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.44.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 152064
}

1
configuration.json Normal file
View File

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

3
ft-model-00001-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:83991b95599894ea0c252b1556083d913ee9ad4f6b41adfa358666d24fc68474
size 4877660776

3
ft-model-00002-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5ec202b7565c7f6a380075677f31fd5cbfba24d37f0551157e01d6dcff682d08
size 4932751008

3
ft-model-00003-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ea194d8997b94d2942613fa68b097e6c245a1bc908de8729c48aa4e2500ebe5a
size 4330865200

3
ft-model-00004-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7e1ffb2479850197bf0024127b7255897c5d4c77841c9197420aeec5c6ec468d
size 1089994880

14
generation_config.json Normal file
View File

@@ -0,0 +1,14 @@
{
"bos_token_id": 151643,
"pad_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_p": 0.8,
"top_k": 20,
"transformers_version": "4.44.0"
}

151387
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

346
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,346 @@
{
"metadata": {
"total_size": 15231233024
},
"weight_map": {
"model.embed_tokens.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.0.input_layernorm.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.0.mlp.down_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.0.mlp.gate_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.0.mlp.up_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.0.post_attention_layernorm.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.0.self_attn.k_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.0.self_attn.k_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.0.self_attn.o_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.0.self_attn.q_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.0.self_attn.q_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.0.self_attn.v_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.0.self_attn.v_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.1.input_layernorm.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.1.mlp.down_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.1.mlp.gate_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.1.mlp.up_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.1.post_attention_layernorm.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.1.self_attn.k_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.1.self_attn.k_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.1.self_attn.o_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.1.self_attn.q_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.1.self_attn.q_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.1.self_attn.v_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.1.self_attn.v_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.2.input_layernorm.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.2.mlp.down_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.2.mlp.gate_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.2.mlp.up_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.2.post_attention_layernorm.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.2.self_attn.k_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.2.self_attn.k_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.2.self_attn.o_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.2.self_attn.q_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.2.self_attn.q_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.2.self_attn.v_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.2.self_attn.v_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.3.input_layernorm.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.3.mlp.down_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.3.mlp.gate_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.3.mlp.up_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.3.post_attention_layernorm.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.3.self_attn.k_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.3.self_attn.k_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.3.self_attn.o_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.3.self_attn.q_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.3.self_attn.q_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.3.self_attn.v_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.3.self_attn.v_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.4.input_layernorm.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.4.mlp.down_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.4.mlp.gate_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.4.mlp.up_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.4.post_attention_layernorm.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.4.self_attn.k_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.4.self_attn.k_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.4.self_attn.o_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.4.self_attn.q_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.4.self_attn.q_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.4.self_attn.v_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.4.self_attn.v_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.5.input_layernorm.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.5.mlp.down_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.5.mlp.gate_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.5.mlp.up_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.5.post_attention_layernorm.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.5.self_attn.k_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.5.self_attn.k_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.5.self_attn.o_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.5.self_attn.q_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.5.self_attn.q_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.5.self_attn.v_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.5.self_attn.v_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.6.input_layernorm.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.6.mlp.down_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.6.mlp.gate_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.6.mlp.up_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.6.post_attention_layernorm.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.6.self_attn.k_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.6.self_attn.k_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.6.self_attn.o_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.6.self_attn.q_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.6.self_attn.q_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.6.self_attn.v_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.6.self_attn.v_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.7.input_layernorm.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.7.mlp.down_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.7.mlp.gate_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.7.mlp.up_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.7.post_attention_layernorm.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.7.self_attn.k_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.7.self_attn.k_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.7.self_attn.o_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.7.self_attn.q_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.7.self_attn.q_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.7.self_attn.v_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.7.self_attn.v_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.8.self_attn.k_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.8.self_attn.k_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.8.self_attn.o_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.8.self_attn.q_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.8.self_attn.q_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.8.self_attn.v_proj.bias": "ft-model-00001-of-00004.safetensors",
"model.layers.8.self_attn.v_proj.weight": "ft-model-00001-of-00004.safetensors",
"model.layers.10.input_layernorm.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.10.mlp.down_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.10.mlp.gate_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.10.mlp.up_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.10.post_attention_layernorm.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.10.self_attn.k_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.10.self_attn.k_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.10.self_attn.o_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.10.self_attn.q_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.10.self_attn.q_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.10.self_attn.v_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.10.self_attn.v_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.11.input_layernorm.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.11.mlp.down_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.11.mlp.gate_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.11.mlp.up_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.11.post_attention_layernorm.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.11.self_attn.k_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.11.self_attn.k_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.11.self_attn.o_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.11.self_attn.q_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.11.self_attn.q_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.11.self_attn.v_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.11.self_attn.v_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.12.input_layernorm.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.12.mlp.down_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.12.mlp.gate_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.12.mlp.up_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.12.post_attention_layernorm.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.12.self_attn.k_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.12.self_attn.k_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.12.self_attn.o_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.12.self_attn.q_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.12.self_attn.q_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.12.self_attn.v_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.12.self_attn.v_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.13.input_layernorm.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.13.mlp.down_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.13.mlp.gate_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.13.mlp.up_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.13.post_attention_layernorm.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.13.self_attn.k_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.13.self_attn.k_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.13.self_attn.o_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.13.self_attn.q_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.13.self_attn.q_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.13.self_attn.v_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.13.self_attn.v_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.14.input_layernorm.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.14.mlp.down_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.14.mlp.gate_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.14.mlp.up_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.14.post_attention_layernorm.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.14.self_attn.k_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.14.self_attn.k_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.14.self_attn.o_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.14.self_attn.q_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.14.self_attn.q_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.14.self_attn.v_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.14.self_attn.v_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.15.input_layernorm.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.15.mlp.down_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.15.mlp.gate_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.15.mlp.up_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.15.post_attention_layernorm.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.15.self_attn.k_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.15.self_attn.k_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.15.self_attn.o_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.15.self_attn.q_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.15.self_attn.q_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.15.self_attn.v_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.15.self_attn.v_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.16.input_layernorm.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.16.mlp.down_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.16.mlp.gate_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.16.mlp.up_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.16.post_attention_layernorm.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.16.self_attn.k_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.16.self_attn.k_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.16.self_attn.o_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.16.self_attn.q_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.16.self_attn.q_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.16.self_attn.v_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.16.self_attn.v_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.17.input_layernorm.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.17.mlp.down_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.17.mlp.gate_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.17.mlp.up_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.17.post_attention_layernorm.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.17.self_attn.k_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.17.self_attn.k_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.17.self_attn.o_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.17.self_attn.q_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.17.self_attn.q_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.17.self_attn.v_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.17.self_attn.v_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.18.mlp.gate_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.18.mlp.up_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.18.self_attn.k_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.18.self_attn.k_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.18.self_attn.o_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.18.self_attn.q_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.18.self_attn.q_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.18.self_attn.v_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.18.self_attn.v_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.8.input_layernorm.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.8.mlp.down_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.8.mlp.gate_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.8.mlp.up_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.8.post_attention_layernorm.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.9.input_layernorm.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.9.mlp.down_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.9.mlp.gate_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.9.mlp.up_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.9.post_attention_layernorm.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.9.self_attn.k_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.9.self_attn.k_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.9.self_attn.o_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.9.self_attn.q_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.9.self_attn.q_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.9.self_attn.v_proj.bias": "ft-model-00002-of-00004.safetensors",
"model.layers.9.self_attn.v_proj.weight": "ft-model-00002-of-00004.safetensors",
"model.layers.18.input_layernorm.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.18.mlp.down_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.18.post_attention_layernorm.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.19.input_layernorm.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.19.mlp.down_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.19.mlp.gate_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.19.mlp.up_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.19.post_attention_layernorm.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.19.self_attn.k_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.19.self_attn.k_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.19.self_attn.o_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.19.self_attn.q_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.19.self_attn.q_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.19.self_attn.v_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.19.self_attn.v_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.20.input_layernorm.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.20.mlp.down_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.20.mlp.gate_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.20.mlp.up_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.20.post_attention_layernorm.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.20.self_attn.k_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.20.self_attn.k_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.20.self_attn.o_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.20.self_attn.q_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.20.self_attn.q_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.20.self_attn.v_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.20.self_attn.v_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.21.input_layernorm.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.21.mlp.down_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.21.mlp.gate_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.21.mlp.up_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.21.post_attention_layernorm.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.21.self_attn.k_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.21.self_attn.k_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.21.self_attn.o_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.21.self_attn.q_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.21.self_attn.q_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.21.self_attn.v_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.21.self_attn.v_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.22.input_layernorm.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.22.mlp.down_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.22.mlp.gate_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.22.mlp.up_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.22.post_attention_layernorm.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.22.self_attn.k_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.22.self_attn.k_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.22.self_attn.o_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.22.self_attn.q_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.22.self_attn.q_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.22.self_attn.v_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.22.self_attn.v_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.23.input_layernorm.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.23.mlp.down_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.23.mlp.gate_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.23.mlp.up_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.23.post_attention_layernorm.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.23.self_attn.k_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.23.self_attn.k_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.23.self_attn.o_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.23.self_attn.q_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.23.self_attn.q_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.23.self_attn.v_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.23.self_attn.v_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.24.input_layernorm.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.24.mlp.down_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.24.mlp.gate_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.24.mlp.up_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.24.post_attention_layernorm.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.24.self_attn.k_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.24.self_attn.k_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.24.self_attn.o_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.24.self_attn.q_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.24.self_attn.q_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.24.self_attn.v_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.24.self_attn.v_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.25.input_layernorm.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.25.mlp.down_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.25.mlp.gate_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.25.mlp.up_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.25.post_attention_layernorm.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.25.self_attn.k_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.25.self_attn.k_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.25.self_attn.o_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.25.self_attn.q_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.25.self_attn.q_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.25.self_attn.v_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.25.self_attn.v_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.26.input_layernorm.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.26.mlp.down_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.26.mlp.gate_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.26.mlp.up_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.26.post_attention_layernorm.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.26.self_attn.k_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.26.self_attn.k_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.26.self_attn.o_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.26.self_attn.q_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.26.self_attn.q_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.26.self_attn.v_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.26.self_attn.v_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.27.input_layernorm.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.27.mlp.down_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.27.mlp.gate_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.27.mlp.up_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.27.post_attention_layernorm.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.27.self_attn.k_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.27.self_attn.k_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.27.self_attn.o_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.27.self_attn.q_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.27.self_attn.q_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.layers.27.self_attn.v_proj.bias": "ft-model-00003-of-00004.safetensors",
"model.layers.27.self_attn.v_proj.weight": "ft-model-00003-of-00004.safetensors",
"model.norm.weight": "ft-model-00003-of-00004.safetensors",
"lm_head.weight": "ft-model-00004-of-00004.safetensors"
}
}

3
original_repo_id.json Normal file
View File

@@ -0,0 +1,3 @@
{
"repo_id": "Qwen/Qwen2.5-Coder-7B-Instruct"
}

303282
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

207
tokenizer_config.json Normal file
View File

@@ -0,0 +1,207 @@
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"bos_token": null,
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"model_max_length": 32768,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long