EssentialAI/rnj-1
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: EssentialAI/rnj-1
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-11 21:54:12 +08:00
commit ffa422f991
17 changed files with 3289 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

56
.gitattributes vendored Normal file
View File

@@ -0,0 +1,56 @@
*.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
*.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
model-00006-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
model-00007-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
model-00002-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
model-00005-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text
model-00004-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
model-00001-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
model-00003-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text

201
LICENSE Normal file
View File

@@ -0,0 +1,201 @@
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 2025 Essential AI
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.

418
README.md Normal file
View File

@@ -0,0 +1,418 @@
---
license: apache-2.0
library_name: transformers
---
# Rnj-1
<p align="center">
<img src="https://raw.githubusercontent.com/Essential-AI/rnj-1-assets/refs/heads/main/assets/Essential%20Logo%20Color_Color_With%20Space.jpg" width=60% alt="EssentialAI">
</p>
<div align="center" style="line-height: 1;">
<!-- Website -->
<a href="https://essential.ai">
<img alt="Homepage"
style="vertical-align: middle;"
src="https://img.shields.io/badge/%F0%9F%8C%90%20Website-essential.ai-4b9fe1?color=4b9fe1&logoColor=white"/>
</a>
<!-- Blog / Research -->
<a href="https://www.essential.ai/research/rnj-1">
<img alt="Research Blog"
style="vertical-align: middle;"
src="https://img.shields.io/badge/🧠%20Research-rnj--1-7c5cff?color=7c5cff&logoColor=white"/>
</a>
<!-- HuggingFace -->
<a href="https://huggingface.co/collections/EssentialAI/rnj-1">
<img alt="Hugging Face"
style="vertical-align: middle;"
src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-rnj--1-ffc107?color=ffc107&logoColor=white"/>
</a>
<br>
<!-- Discord -->
<a href="https://discord.gg/VPEqUNg6tR">
<img alt="Discord"
style="vertical-align: middle;"
src="https://img.shields.io/badge/Discord-Essential%20AI-7289da?logo=discord&logoColor=white&color=7289da"/>
</a>
<!-- X / Twitter -->
<a href="https://x.com/essential_ai">
<img alt="Twitter Follow"
style="vertical-align: middle;"
src="https://img.shields.io/badge/Twitter-essential__ai-white?logo=x&logoColor=white"/>
</a>
<!-- Together AI -->
<a href="https://www.together.ai/models/rnj-1-instruct">
<img alt="Together AI"
style="vertical-align: middle;"
src="https://img.shields.io/badge/⚡%20TogetherAI-rnj--1--instruct-00c2a8?color=00c2a8&logoColor=white"/>
</a>
<!-- OpenRouter -->
<a href="https://openrouter.ai/essentialai/rnj-1-instruct">
<img alt="OpenRouter"
style="vertical-align: middle;"
src="https://img.shields.io/badge/OpenRouter-rnj--1--instruct-1a4b82?logo=openrouter&color=1a4b82&logoColor=white"/>
</a>
<br>
</div>
Rnj-1 is a family of 8B parameter open-weight, dense models trained from scratch by Essential AI, optimized for code and STEM with capabilities on par with SOTA open-weight models. These models perform well across a range of programming languages and boast strong agentic capabilities (e.g., inside agentic frameworks like mini-SWE-agent), while also excelling at tool-calling. They additionally exhibit strong capabilities in math and science. Herein, `rnj-1` refers to the base model, while `rnj-1-instruct` refers to the post-trained instruction tuned model.
# Capabilities
We evaluate Rnj-1 models against models of comparable size. In addition to accuracy, we also show the FLOPs used in pre-training for each model.
### Benchmark Results
### Base Model `rnj-1`
<p align="center">
<img src="https://raw.githubusercontent.com/Essential-AI/rnj-1-assets/refs/heads/main/assets/Base_Full_Table.png" width="100%" alt="Base Evals"/>
</p>
### Instruct Model `rnj-1-instruct`
`rnj-1-instruct` is strong at code, math, and STEM tasks. It also performs well within agentic frameworks such as mini-swe-agent and has stellar tool use abilities.
<p align="center">
<img src="https://raw.githubusercontent.com/Essential-AI/rnj-1-assets/refs/heads/main/assets/Instruct_Full_Table.png" width="100%" alt="Instrcut Evals"/>
<sub><i>We report published numbers when possible, and when unavailable they are internal reproductions.
Pre-training FLOPs were estimated using 6nt, where n is the number of parameters and t is the token budget.
All Evals under the Env bucket were evaluated using mini-swe-agent (bash only) scaffolding.
GPT OSS 20B was evaluated with reasoning_effort=low.
Qwen 3 8B was evaluated with thinking turned off.</i></sub></p>
### Rnj-1 models are designed to be extended
Both `rnj-1` and `rnj-1-instruct` models are being made available for the community to extend and build upon. We deliberately kept post-training limited to allow for further specialization by the community. As an indicator of the untapped potential of the models we report `pass@{1,2,4,8}` (with T=0.2, n=8 generations) for hard codegen, agentic, and math benchmarks on `rnj-1-instruct`. These illustrate the model’s potential for test-time scaling and for further domain-specialization. The base model is similarly capable of specialization to other domains different from our post-training if needed.
<p align="center">
<img src="https://raw.githubusercontent.com/Essential-AI/rnj-1-assets/refs/heads/main/assets/rnj-1-pass-at-k.png" width="80%" alt="Pass at k evals"/>
</p>
Sidenote: Here is a [screen recording](https://vimeo.com/1143712958/c66dda13f3?share=copy&fl=sv&fe=ci) of `rnj-1-instruct` helping us make an early version of this chart.
### Highlights of abilities
- **Code generation:** Both `rnj-1-instruct` and `rnj-1` demonstrate strong code generation abilities as measured on tasks like HumanEval+, MBPP+, BigCodeBench, and LiveCodeBench v6. Both models compete with the strongest open weight models, sometimes outperforming even larger models such as GPT OSS 20B. We measured code comprehension abilities using the task of predicting inputs given outputs and vice-versa, Crux-IO. We find our models outperform comparable baselines. For multi-lingual code generation capabilities across programming languages we measure MultiPL-E on 6 languages (C++, TypeScript, Java, JavaScript, Shell, PHP) and we find performance close to the strongest model.
- **Agentic and Tool Use:** `rnj-1-instruct` dominates the pack on agentic coding, one of our target abilities. SWE-bench performance is indicative of the model’s ability to tackle everyday software engineering tasks. The model is an order of magnitude stronger than comparably sized models on SWE-bench and approaches the capabilities available in much larger models. It scores `20.8%` on SWE-bench Verified in bash-only mode, which is higher than Gemini 2.0 flash and Qwen2.5-Coder 32B Instruct under the same agentic framework ([leaderboard](https://www.swebench.com/bash-only.html)).<br><br>
There is a surge of interest in developing models’ abilities to write performant code. `rnj-1-instruct` is able to use a profiler to iteratively improve the performance of the code it writes. For instance, on [Enamel](https://github.com/q-rz/enamel/tree/main), which measures abilities to write efficient solutions to algorithmic problems, the model outperforms all other models under the same setting.<br><br>
Furthermore, `rnj-1-instruct` surpasses comparable models in tool use performance as measured by the Berkeley Functional Calling Leaderboard (BFCL).
- **Code Infilling** : Having specifically been trained on FIM-ed pre-training data, `rnj-1` exhibits strong infilling abilities, which have been further enhanced during post-training. The base model `rnj-1` scores highly on HE-FIM-Python (avg) at 82.49% and `rnj-1-instruct` achieves 86.21%.
- **Mathematical Problem Solving:** `rnj-1-instruct` shows strong mathematical abilities across several levels of difficulty from elementary math (GSM8k), high school and undergraduate math (Minerva-MATH), and competition math (AIME ‘24 and ‘25). On harder subjects, it outcompetes or is on par with the strongest model in the pack.
- **Scientific Reasoning:** `rnj-1-instruct` exhibits long-context reasoning abilities that are needed to solve hard science and technical questions in GPQA-Diamond and SuperGPQA.
### Demos: Rnj-1 models generalize to unseen tasks
We show a few examples of end-to-end capabilities that are usually expected of larger models.
- **Coding assistant:** `rnj-1-instruct` can operate in agentic mode to create a playable game in a single shot inside of Cline: [screen recording](https://vimeo.com/1143853378/8df3376a1a?share=copy&fl=sv&fe=ci).
- **Agentic use:** `rnj-1-instruct` functions seamlessy within the agentic framework of mini-swe-agent. Given a task such as fixing an issue described in a pull request (PR), fixing a security vulnerability, or writing performant code, it is able to reason across its full context across multiple turns to solve the task. These lead to “trajectories” which are pairs of “Assistant” and “User” turns. Here are a few recordings that show the model’s reasoning abilities across these turns: 1) a SWE task of identifying coding convention violation: [screen recording](https://vimeo.com/1143841317/44adfbd044?share=copy&fl=sv&fe=ci), 2) fixing a security vulnerability: [screen recording](https://vimeo.com/1143843598/6fca2fe0bb?share=copy&fl=sv&fe=ci), 3) diagnosing code performance bottlenecks by running a profiler in the environment and iteratively improving the code: [screen recording](https://vimeo.com/1143828123/11e4d22ac7?share=copy&fl=sv&fe=ci).
- **Data analysis in an interactive chat:** `rnj-1-instruct` can work in interactive chat mode to solve a data analysis and visualization task: [screen recording](https://vimeo.com/1143831950/0e7d9c3edc?share=copy&fl=sv&fe=ci).
# Architecture
Rnj-1's architecture is similar to Gemma 3, except that it uses only global attention, and YaRN for long-context extension.
| Hyperparameter | Value |
|:---:|:---:|
| **Total Parameters** | 8.3B |
| **Number of Layers** | 32 |
| **Model Dimension** | 4096 |
| **MLP Dimension** | 16384 |
| **Number of Attention Heads** | 32 |
| **Number of Key-Value Heads** | 8 |
| **Attention Head Dimension** | 128 |
| **Vocabulary Size** | 128K |
| **Pretrain Context Length** | 8K |
| **Context Length** | 32K |
| **Activation Function** | GeGLU |
| **Tied Embeddings?** | Yes |
### Training Dynamics
`rnj-1` was pre-trained on 8.4T tokens with an 8K context length, after which the model’s context window was extended to **32K** through an additional 380B-token mid-training stage. A final 150B-token SFT stage completed the training to produce `rnj-1-instruct`.
We used the Muon optimizer throughout all phases. Pre-training followed the WSD learning-rate schedule, consisting of:
- Warmup: Linear ramp-up from 0 to 2e-3 over the first 5K steps.
- Stable phase: Constant learning rate of 2e-3 from 5K → 230K steps.
- Decay: Cosine decay from 2e-3 → 2e-5 from 230K → 380K steps.
- Final stable phase: Constant 2e-5 learning rate from 380K → 443.5K steps, concluding pre-training.
Both the mid-training (context-extension phase) and SFT were trained at a fixed learning rate of 2e-5.
The global batch sizes used were:
- 18M tokens for pre-training.
- 24M tokens for mid-training.
- 16M tokens for SFT.
# Recommendations
### Temperature
We recommend using temperatures in the range [0, 0.6] for `rnj-1-instruct`.
### Propensity to write code
Rnj-1 models have a strong inclination to write code, even for non-code tasks. This is especially true for `rnj-1-instruct` if the system prompt is omitted. Provide an appropriate system prompt, e.g., “You are a helpful assistant”, along with global task needs to steer the model’s responses in the desired direction.
# How to use
## Serverless API and online playgrounds
- Together.AI: Rnj-1 Instruct is available via API on the [Together.ai](http://Together.ai) model platform for serverless inference. It’s also available in the Together.ai playground for quick and easy experimentation.
- HuggingFace: Rnj-1 Instruct is also hosted via [Hugging Face Spaces](https://huggingface.co/spaces/EssentialAI/rnj-1-instruct-space).
## Running Rnj-1 locally
### Running Rnj-1 on your laptop with llama.cpp
The easiest way to run Rnj-1 on a laptop is via [llama.cpp](https://github.com/ggml-org/llama.cpp). A pre-quantized checkpoint is available [here](https://huggingface.co/EssentialAI/rnj-1-instruct-GGUF) as well as instructions to get started.
### Use with transformers
Rnj-1 is supported starting from transformers `4.51.2`
1. Example code for querying model without tools
```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
import os
model_id = "EssentialAI/rnj-1-instruct"
os.environ["HF_TOKEN"] = <YOUR-HF-TOKEN>
print(f"Loading model: {model_id}...")
model = AutoModelForCausalLM.from_pretrained(
model_id,
dtype=torch.bfloat16,
device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained(model_id)
print("Model and tokenizer loaded successfully.")
messages = [
{"role": "system", "content": "You are a helpful AI assistant."}, # Optional system message
{"role": "user", "content": "Who are you?"}
]
input_ids = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
return_tensors="pt"
).to(model.device)
# --- Generate Prediction --- #
print("Generating prediction...")
output_ids = model.generate(
input_ids,
max_new_tokens=50,
pad_token_id=tokenizer.eos_token_id,
do_sample=True,
temperature=0.2,
top_p=0.95
)
response = tokenizer.decode(output_ids[0][input_ids.shape[-1]:], skip_special_tokens=True)
print(response)
```
1. Example code for querying with tools
Rnj-1 supports tool-calling which can be parsed by `hermes` tool-call parser. The tool calls are formatted inside `<tool_call>` and `</tool_call>` tags.
An example usage is as follows:
```python
tools = [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {"type": "string", "description": "City and state, e.g., 'San Francisco, CA'"},
"unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}
},
"required": ["location", "unit"],
},
},
},
]
messages = [
{"role": "system", "content": "You are a helpful AI assistant."}, # Optional system message
{"role": "user", "content": "What is the weather in San Francisco, CA in Celsius?"}
]
input_ids = tokenizer.apply_chat_template(
messages,
tools=tools,
add_generation_prompt=True,
return_tensors="pt"
).to(model.device)
# --- Generate Prediction --- #
print("Generating prediction...")
output_ids = model.generate(
input_ids,
max_new_tokens=200,
pad_token_id=tokenizer.eos_token_id,
do_sample=True,
temperature=0.2,
top_p=0.95
)
response = tokenizer.decode(output_ids[0][input_ids.shape[-1]:], skip_special_tokens=False)
# NOTE: skip_special_tokens is set to False.
print(response)
```
1. Example code for fill-in-the-middle (FIM)
Rnj-1 supports FIM, we show an example payload to trigger FIM mode for Rnj-1 below:
```python
PRE = "<|pre_fim|>"
MID = "<|mid_fim|>"
SUF = "<|suf_fim|>"
prefix = """def binary_search(arr, target):
lo = 0
hi = len(arr) - 1
while lo <= hi:
"""
suffix = """
return -1
"""
input = PRE + prefix + SUF + suffix + MID
messages = [
{"role": "system", "content": "You are a helpful AI assistant."},
{"role": "user", "content": input}
]
input_ids = tokenizer.apply_chat_template(
messages,
tools=tools,
add_generation_prompt=True,
return_tensors="pt"
).to(model.device)
# --- Generate Prediction --- #
print("Generating prediction...")
output_ids = model.generate(
input_ids,
max_new_tokens=100,
pad_token_id=tokenizer.eos_token_id,
do_sample=True,
temperature=0.2,
top_p=0.95
)
response = tokenizer.decode(output_ids[0][input_ids.shape[-1]:], skip_special_tokens=False)
print(response)
```
### Serving Rnj-1 on GPUs
### **vLLM**
On machines that run vLLM, it’s as easy as:
```bash
vllm serve EssentialAI/rnj-1-instruct
```
To launch a vLLM server with tool-calling support enabled:
```python
vllm serve EssentialAI/rnj-1-instruct --enable-auto-tool-choice --tool-call-parser hermes
```
### SGLang
On machines that run SGLang, it’s as easy as:
```bash
python3 -m sglang.launch_server --model EssentialAI/rnj-1-instruct
```
## IDEs and Agents: Claude Code, Cline, Mini-SWE-Agent
### Use with Cline
Rnj-1 works great with Cline, an open source AI coding agent, and is very easy to set up.
The Cline extension is available for VS Code / Cursor, JetBrains IDEs (IntelliJ, PyCharm, WebStorm, etc.) and VSCodium / Windsurf.
Simply add the Cline extension to your favorite IDE (see instructions [here](https://docs.cline.bot/getting-started/installing-cline)) and then enter the details for your Rnj-1 endpoint (instructions [here](https://docs.cline.bot/getting-started/selecting-your-model)).
### Use with Claude Code
To use Rnj-1 with Claude Code, you can use https://github.com/musistudio/claude-code-router. Follow the instructions to set up Claude Code and Claude Code Router at https://github.com/musistudio/claude-code-router/blob/main/README.md.
### Agentic mode with Mini-SWE-Agent
Clone the EssentialAI fork of mini-swe-agent ([github](https://github.com/Essential-AI/eai-mini-swe-agent#)). Inside the repo, run the following inside a `virtualenv`:
```python
git checkout eai
pip install -e .
export TOGETHER_API_KEY="..." # set this to your Together.AI access key
# use EssentialAI/rnj-1-instruct to solve a performance optimization task
mini-extra perf-single [--instance <k>]
# use EssentialAI/rnj-1-instruct to resolve a SWE PR description
mini-extra swebench-single [--instance <k>]
```
# Known limitations
### Hallucinations and factual inaccuracies
Rnj-1 is primarily a coding and STEM model. Hence, it is not optimized for factual recovery.
### Identity and knowledge cutoff
Rnj-1 is trained on online web data, and we have observed that it sometimes confuses its identity with other model providers. We believe this is due to a variety of reasons, including references to language models from other providers, model generated data, etc. We hope to rectify this in our follow-up release.
Additionally, Rnj-1 has not been trained or provided with a knowledge cutoff date and may therefore respond with information coming from its training data. If specifically asked for its knowledge cutoff date, the model may hallucinate a date.
# **License**
This repository and the model weights are licensed under [**the Apache License, Version 2.0 (Apache 2.0)**](https://huggingface.co/EssentialAI/rnj-1-instruct/blob/main/LICENSE).
# **Contact**
We welcome your questions and feedback. You can contact us at info@essential.ai.
# **Citation**
```bibtex
@misc{rnj1_base,
title = {{Rnj-1}},
author = {Ashish Vaswani and Mike Callahan and Adarsh Chaluvaraju and Aleksa Gordić and Devaansh Gupta and Yash Jain and Divya Mansingka and Philip Monk and Khoi Nguyen and Mohit Parmar and Michael Pust and Tim Romanski and Peter Rushton and Ali Shehper and Divya Shivaprasad and Somanshu Singla and Kurt Smith and Saurabh Srivastava and Anil Thomas and Alok Tripathy and Yash Vanjani and Ameya Velingker and {{Essential AI}}},
year = {2025},
url = {https://huggingface.co/EssentialAI/rnj-1},
note = {base model release}
}

77
config.json Normal file
View File

@@ -0,0 +1,77 @@
{
"architectures": [
"Gemma3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"attn_logit_softcapping": null,
"bos_token_id": 2,
"cache_implementation": "hybrid",
"eos_token_id": 1,
"final_logit_softcapping": 30.0,
"head_dim": 128,
"hidden_act": "gelu_pytorch_tanh",
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 16384,
"layer_type": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 32768,
"model_type": "gemma3_text",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pad_token_id": 0,
"query_pre_attn_scalar": 128,
"rms_norm_eps": 1e-06,
"rope_local_base_freq": 10000,
"rope_scaling": {
"attn_factor": 1.0,
"beta_fast": 64.0,
"beta_slow": 1.0,
"extrapolation_factor": 1.0,
"factor": 4.0,
"original_max_position_embeddings": 8192,
"rope_type": "yarn"
},
"rope_theta": 10000,
"sliding_window": 32768,
"sliding_window_pattern": 1,
"torch_dtype": "float32",
"transformers_version": "4.51.2",
"use_cache": true,
"vocab_size": 128256
}

1
configuration.json Normal file
View File

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

8
generation_config.json Normal file
View File

@@ -0,0 +1,8 @@
{
"_from_model_config": true,
"bos_token_id": 128000,
"cache_implementation": "hybrid",
"eos_token_id": 128009,
"pad_token_id": 128001,
"transformers_version": "4.51.2"
}

3
model-00001-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1f80f344285f7347c8be2f1b4fd5fe8cc293ab75e83b811bea6adf1a2d033845
size 4752284616

3
model-00002-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9d01d3cff37c4cb14d40557eebf8e3f2eb97f66fbe1250979d73208620da7f7e
size 4865732920

3
model-00003-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7c71779467e57a280a65c6fbcf1b21397ae36440d700a3e9d62b2e50eb91115c
size 4865732944

3
model-00004-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:134ae850099a642887de6f0b88fac654aa7fdf4c03e8a16f60428cd2f44ebf19
size 4865732984

3
model-00005-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e077dd2d1463edf9f7d5b0fbca9c766d0d43c34164d6db8fc302ab5f5e627294
size 4865732984

3
model-00006-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c42b75ec9f356289768243fe9ba0ed9c7a86074691f4f4b3a7843237fc8270ac
size 4865732984

3
model-00007-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1dedd2e5ae577f13f4332312d8381dd7e7f2d6adc0e1e6684842af977162a116
size 4161104448

425
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,425 @@
{
"metadata": {
"total_size": 33242005504
},
"weight_map": {
"model.embed_tokens.weight": "model-00001-of-00007.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.10.post_feedforward_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.10.pre_feedforward_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.10.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.10.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.11.post_feedforward_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.11.pre_feedforward_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.11.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.11.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.12.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.12.post_feedforward_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.12.pre_feedforward_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.12.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.12.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.13.post_feedforward_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.13.pre_feedforward_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.13.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.13.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.14.post_feedforward_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.14.pre_feedforward_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.14.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.14.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.15.post_feedforward_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.15.pre_feedforward_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.15.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.15.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.16.post_feedforward_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.16.pre_feedforward_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.16.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.16.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.17.input_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.17.post_feedforward_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.17.pre_feedforward_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.17.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.17.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.18.post_feedforward_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.18.pre_feedforward_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.18.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.18.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.19.post_feedforward_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.19.pre_feedforward_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.19.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.19.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.2.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.2.post_feedforward_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.2.pre_feedforward_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.20.post_feedforward_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.20.pre_feedforward_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.20.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.20.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.21.post_feedforward_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.21.pre_feedforward_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.21.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.21.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.22.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.22.post_feedforward_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.22.pre_feedforward_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.22.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.22.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.23.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.23.post_feedforward_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.23.pre_feedforward_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.23.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.23.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.24.post_feedforward_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.24.pre_feedforward_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.24.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.24.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.25.post_feedforward_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.25.pre_feedforward_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.25.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.25.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.26.post_feedforward_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.26.pre_feedforward_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.26.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.26.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.27.input_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.27.post_feedforward_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.27.pre_feedforward_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.27.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.27.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.28.input_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.28.post_feedforward_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.28.pre_feedforward_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.28.self_attn.k_norm.weight": "model-00007-of-00007.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.28.self_attn.q_norm.weight": "model-00007-of-00007.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.29.input_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.29.post_feedforward_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.29.pre_feedforward_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.29.self_attn.k_norm.weight": "model-00007-of-00007.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.29.self_attn.q_norm.weight": "model-00007-of-00007.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.3.post_feedforward_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.3.pre_feedforward_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.3.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.3.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.30.input_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.30.post_feedforward_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.30.pre_feedforward_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.30.self_attn.k_norm.weight": "model-00007-of-00007.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.30.self_attn.q_norm.weight": "model-00007-of-00007.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.31.post_feedforward_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.31.pre_feedforward_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.31.self_attn.k_norm.weight": "model-00007-of-00007.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.31.self_attn.q_norm.weight": "model-00007-of-00007.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.4.post_feedforward_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.4.pre_feedforward_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.4.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.4.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.5.post_feedforward_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.5.pre_feedforward_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.5.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.5.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.6.post_feedforward_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.6.pre_feedforward_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.6.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.6.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.7.input_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.7.post_feedforward_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.7.pre_feedforward_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.7.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.7.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.8.post_feedforward_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.8.pre_feedforward_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.8.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.8.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.9.post_feedforward_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.9.pre_feedforward_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.9.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.9.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
"model.norm.weight": "model-00007-of-00007.safetensors"
}
}

16
special_tokens_map.json Normal file
View File

@@ -0,0 +1,16 @@
{
"bos_token": {
"content": "<|begin_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|end_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:050a14faefc0c4f12075579c1676a9a6ca207801b4218c64f69cd7553bdda1b8
size 17209796

2063
tokenizer_config.json Normal file
View File

File diff suppressed because one or more lines are too long