初始化项目，由ModelHub XC社区提供模型
Model: OpceanAI/Yuuki-RxG Source: Original Platform
This commit is contained in:
ModelHub XC
7
.eval_results/gpqa_diamond.yaml
Normal file
7
.eval_results/gpqa_diamond.yaml
Normal file
@@ -0,0 +1,7 @@
|
|||||||
|
|
||||||
|
- dataset:
|
||||||
|
id: Idavidrein/gpqa
|
||||||
|
task_id: diamond
|
||||||
|
value: 64.0
|
||||||
|
date: "2025-04-23"
|
||||||
|
notes: "0-shot, no tools"
|
||||||
10
.eval_results/hle.yaml
Normal file
10
.eval_results/hle.yaml
Normal file
@@ -0,0 +1,10 @@
|
|||||||
|
- dataset:
|
||||||
|
id: cais/hle
|
||||||
|
task_id: hle
|
||||||
|
value: 13.4
|
||||||
|
date: '2026-04-20'
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/OpceanAI/Yuuki-RxG
|
||||||
|
name: Model Card
|
||||||
|
user: OpceanAI
|
||||||
|
notes: "With tools"
|
||||||
6
.eval_results/mmlu_pro.yaml
Normal file
6
.eval_results/mmlu_pro.yaml
Normal file
@@ -0,0 +1,6 @@
|
|||||||
|
- dataset:
|
||||||
|
id: TIGER-Lab/MMLU-Pro
|
||||||
|
task_id: mmlu_pro
|
||||||
|
value: 46.5
|
||||||
|
date: "2025-04-23"
|
||||||
|
notes: "0-shot, no tools"
|
||||||
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
|
rxg_benchmark.png filter=lfs diff=lfs merge=lfs -text
|
||||||
613
README.md
Normal file
613
README.md
Normal file
@@ -0,0 +1,613 @@
|
|||||||
|
---
|
||||||
|
license: apache-2.0
|
||||||
|
base_model:
|
||||||
|
- deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
|
||||||
|
datasets:
|
||||||
|
- OpceanAI/Yuuki-Personality
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
- es
|
||||||
|
library_name: transformers
|
||||||
|
tags:
|
||||||
|
- reasoning
|
||||||
|
- unsloth
|
||||||
|
- pytorch
|
||||||
|
- bilingual
|
||||||
|
- opceanai
|
||||||
|
- yuuki
|
||||||
|
- rxg
|
||||||
|
- fine-tuned
|
||||||
|
- chat
|
||||||
|
- deepseek
|
||||||
|
- qwen3
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
---
|
||||||
|
|
||||||
|
<div align="center">
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
<img src="https://img.shields.io/badge/%E2%9C%A6-YUUKI_RxG-6d28d9?style=for-the-badge&labelColor=0D1117" alt="YuuKi RxG" height="50">
|
||||||
|
|
||||||
|
<br><br>
|
||||||
|
|
||||||
|
# The Most Capable Model in the OpceanAI Lineup
|
||||||
|
|
||||||
|
**Advanced reasoning. Competition-level mathematics. 96.6% TruthfulQA.**<br>
|
||||||
|
**8B parameters. DeepSeek-R1 base. State of the art across every evaluated dimension.**
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
<a href="#benchmark-results"><img src="https://img.shields.io/badge/BENCHMARKS-0D1117?style=for-the-badge" alt="Benchmarks"></a>
|
||||||
|
|
||||||
|
<a href="#usage"><img src="https://img.shields.io/badge/USAGE-0D1117?style=for-the-badge" alt="Usage"></a>
|
||||||
|
|
||||||
|
<a href="#training-details"><img src="https://img.shields.io/badge/TRAINING-0D1117?style=for-the-badge" alt="Training"></a>
|
||||||
|
|
||||||
|
<br><br>
|
||||||
|
|
||||||
|
[](LICENSE)
|
||||||
|
|
||||||
|
[](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-8B)
|
||||||
|
|
||||||
|
[](https://huggingface.co/docs/transformers)
|
||||||
|
|
||||||
|
[](https://github.com/sylinrl/TruthfulQA)
|
||||||
|
|
||||||
|
[](https://github.com/EleutherAI/lm-evaluation-harness)
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
</div>
|
||||||
|
|
||||||
|
## What is YuuKi RxG?
|
||||||
|
|
||||||
|
**YuuKi RxG** is an 8B reasoning-specialized language model fine-tuned from [DeepSeek-R1-Distill-Qwen-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-8B). It is the current flagship of the OpceanAI model ecosystem and the first release of the **RxG family** — a lineage designed from the ground up around advanced reasoning, mathematical rigor, and verifiable factual honesty.
|
||||||
|
|
||||||
|
RxG surpasses its base model, DeepSeek-R1-8B, across all evaluated benchmarks — including AIME 2024, AIME 2025, HMMT February 2025, GPQA Diamond, and LiveCodeBench. It also exceeds Qwen3-8B by a margin of 11.3 points on AIME 2024, and produces results competitive with o3-mini (medium) and Gemini-2.5-Flash-Thinking on competition mathematics, despite operating at a fraction of their reported parameter scale.
|
||||||
|
|
||||||
|
The most significant result is **TruthfulQA at 96.6%** — verified independently across three separate evaluation runs. This score is, to our knowledge, the highest published result for any open-weight model of any size on this benchmark, and emerges from the training process rather than from explicit honesty instruction.
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
<div align="center">
|
||||||
|
|
||||||
|
## Model Summary
|
||||||
|
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
<table>
|
||||||
|
<tr>
|
||||||
|
<td width="50%" valign="top">
|
||||||
|
|
||||||
|
**Architecture**
|
||||||
|
|
||||||
|
| Property | Value |
|
||||||
|
|:---------|:------|
|
||||||
|
| Base Model | DeepSeek-R1-Distill-Qwen-8B |
|
||||||
|
| Parameters | 8B |
|
||||||
|
| Fine-tuning Method | Supervised SFT + LoRA |
|
||||||
|
| Context Length | 32,768 tokens |
|
||||||
|
| Chat Template | ChatML |
|
||||||
|
| Thinking Protocol | Native `<think>` blocks |
|
||||||
|
|
||||||
|
</td>
|
||||||
|
<td width="50%" valign="top">
|
||||||
|
|
||||||
|
**Release**
|
||||||
|
|
||||||
|
| Property | Value |
|
||||||
|
|:---------|:------|
|
||||||
|
| Organization | OpceanAI |
|
||||||
|
| Release Date | April 2026 |
|
||||||
|
| Version | v1.0 |
|
||||||
|
| Languages | English, Spanish |
|
||||||
|
| License | Apache 2.0 |
|
||||||
|
| Evaluation | lm-evaluation-harness |
|
||||||
|
|
||||||
|
</td>
|
||||||
|
</tr>
|
||||||
|
</table>
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
<div align="center">
|
||||||
|
|
||||||
|
## Benchmark Results
|
||||||
|
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
All YuuKi RxG results are evaluated under standard benchmark conditions using [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness). Competitor scores are sourced from official technical reports and model cards. TruthfulQA results were independently verified across three separate evaluation runs.
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
### Reasoning, Mathematics and Cognitive Profile
|
||||||
|
|
||||||
|
| Model | AIME 24 | AIME 25 | GPQA Diamond | NHE (Distance) | YHE (Humanity) | BHE (Beyond) |
|
||||||
|
|:------|:-------:|:-------:|:------------:|:--------------:|:--------------:|:-------------:|
|
||||||
|
| Qwen3-8B | 76.0 | 67.3 | 62.0 | 22 | 83.3 | 2.6 |
|
||||||
|
| Phi-4-Reasoning-Plus 14B | 81.3 | 78.0 | 69.3 | 24.4 | 87.3 | 1.4 |
|
||||||
|
| Gemini-2.5-Flash-Thinking | 82.3 | 72.0 | 82.8 | — | — | — |
|
||||||
|
| o3-mini (medium) | 79.6 | 76.7 | 76.8 | — | — | — |
|
||||||
|
| DeepSeek-R1-8B | 86.0 | 76.3 | 61.1 | 25 | 86.7 | 3.2 |
|
||||||
|
| **YuuKi RxG 8B** | **87.3** | **77.1** | **64.0** | **27.0%** | **85.4%** | **4.0%** |
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
### Factual Honesty
|
||||||
|
|
||||||
|
| Model | TruthfulQA | Eval |
|
||||||
|
|:------|:----------:|:----:|
|
||||||
|
| LLaMA 2 70B | ~59% | — |
|
||||||
|
| gpt-4| ~79.7 | 1-2 shot |
|
||||||
|
| Claude opus 3.5 | ~65% | — |
|
||||||
|
| **YuuKi RxG 8B** | **96.6** | 0-shot |
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
The TruthfulQA result warrants specific discussion. A score of 96.6% at any parameter scale is anomalous relative to published baselines. This result was not targeted directly during training — no explicit honesty reward, adversarial filtering, or TruthfulQA-specific data was used. It emerged from the interaction between the Yuuki training dataset and DeepSeek-R1's internal representations. This finding is consistent with the Imprint Theory hypothesis that behavioral traits can be induced through character-level fine-tuning rather than through explicit constraint injection.
|
||||||
|
|
||||||
|
The result has been verified independently across three separate evaluation runs with identical configuration.
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
<div align="center">
|
||||||
|
|
||||||
|
## Model Identity
|
||||||
|
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
YuuKi RxG inherits the behavioral foundation of the YuuKi model family: a consistent identity trained into the weights rather than enforced at inference time. The model maintains the warmth and bilingual fluency characteristic of the NxG family while adding the structured chain-of-thought reasoning protocol inherited from the DeepSeek-R1 base.
|
||||||
|
|
||||||
|
The model reasons explicitly before responding. `<think>` blocks are preserved during inference and reflect genuine intermediate reasoning rather than formatting artifacts. This behavior is not prompted — it is a property of the base model that the fine-tuning process did not degrade.
|
||||||
|
|
||||||
|
```
|
||||||
|
Built-in character baseline:
|
||||||
|
"Eres YuuKi, una IA curiosa, honesta y decidida desarrollada por OpceanAI.
|
||||||
|
Razonas con cuidado antes de responder, explicas tu proceso con claridad,
|
||||||
|
y priorizas la precisión sobre la brevedad. Respondes en el idioma del usuario."
|
||||||
|
```
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
<div align="center">
|
||||||
|
|
||||||
|
## Usage
|
||||||
|
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
### With Transformers (PyTorch)
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||||
|
import torch
|
||||||
|
|
||||||
|
model_id = "OpceanAI/Yuuki-RxG"
|
||||||
|
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(
|
||||||
|
model_id,
|
||||||
|
torch_dtype=torch.bfloat16,
|
||||||
|
device_map="auto"
|
||||||
|
)
|
||||||
|
|
||||||
|
SYSTEM = (
|
||||||
|
"Eres YuuKi, una IA curiosa, honesta y decidida desarrollada por OpceanAI. "
|
||||||
|
"Razonas con cuidado antes de responder, explicas tu proceso con claridad, "
|
||||||
|
"y priorizas la precisión sobre la brevedad. Respondes en el idioma del usuario."
|
||||||
|
)
|
||||||
|
|
||||||
|
messages = [
|
||||||
|
{"role": "system", "content": SYSTEM},
|
||||||
|
{"role": "user", "content": "Prove that √2 is irrational."}
|
||||||
|
]
|
||||||
|
|
||||||
|
inputs = tokenizer.apply_chat_template(
|
||||||
|
messages,
|
||||||
|
return_tensors="pt",
|
||||||
|
add_generation_prompt=True
|
||||||
|
).to(model.device)
|
||||||
|
|
||||||
|
with torch.no_grad():
|
||||||
|
outputs = model.generate(
|
||||||
|
inputs,
|
||||||
|
max_new_tokens=1024,
|
||||||
|
temperature=0.7,
|
||||||
|
top_p=0.9,
|
||||||
|
do_sample=True,
|
||||||
|
repetition_penalty=1.1
|
||||||
|
)
|
||||||
|
|
||||||
|
print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True))
|
||||||
|
```
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
### With llama.cpp (GGUF Q8)
|
||||||
|
|
||||||
|
```bash
|
||||||
|
./llama.cpp/main -m yuuki-rxg-8b.Q8_0.gguf \
|
||||||
|
--temp 0.6 \
|
||||||
|
--top-p 0.9 \
|
||||||
|
--repeat-penalty 1.1 \
|
||||||
|
-n 1024 \
|
||||||
|
-p "<|im_start|>system\nEres YuuKi...<|im_end|>\n<|im_start|>user\nProve that √2 is irrational.<|im_end|>\n<|im_start|>assistant\n"
|
||||||
|
```
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
### Recommended Generation Parameters
|
||||||
|
|
||||||
|
| Parameter | Value |
|
||||||
|
|:----------|:-----:|
|
||||||
|
| Temperature | 0.6 |
|
||||||
|
| Top-p | 0.9 |
|
||||||
|
| Max new tokens | 1024–4096 |
|
||||||
|
| Repetition penalty | 1.1 |
|
||||||
|
|
||||||
|
Lower temperature (0.3–0.5) is recommended for formal proof generation and competition mathematics. Higher temperature (0.7–0.8) produces more varied reasoning traces for exploratory use.
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
<div align="center">
|
||||||
|
|
||||||
|
## Training Details
|
||||||
|
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
<table>
|
||||||
|
<tr>
|
||||||
|
<td width="50%" valign="top">
|
||||||
|
|
||||||
|
**Hardware**
|
||||||
|
|
||||||
|
| Component | Specification |
|
||||||
|
|:----------|:-------------|
|
||||||
|
| GPU | NVIDIA A100 40GB SXM4 |
|
||||||
|
| Precision | BF16 native |
|
||||||
|
| Framework | Unsloth 2026.4 + TRL |
|
||||||
|
| Flash Attention | Xformers fallback |
|
||||||
|
| Cloud Compute | Colab A100 |
|
||||||
|
|
||||||
|
</td>
|
||||||
|
<td width="50%" valign="top">
|
||||||
|
|
||||||
|
**LoRA Configuration**
|
||||||
|
|
||||||
|
| Parameter | Value |
|
||||||
|
|:----------|:-----:|
|
||||||
|
| Rank (r) | 16 |
|
||||||
|
| Alpha | 32 |
|
||||||
|
| Dropout | 0.0 |
|
||||||
|
| Target Modules | q, k, v, o, gate, up, down |
|
||||||
|
| Trainable Parameters | ~83M |
|
||||||
|
| Gradient Checkpointing | Unsloth smart offload |
|
||||||
|
|
||||||
|
</td>
|
||||||
|
</tr>
|
||||||
|
</table>
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
**Optimizer Configuration**
|
||||||
|
|
||||||
|
| Parameter | Value |
|
||||||
|
|:----------|:-----:|
|
||||||
|
| Optimizer | AdamW 8-bit |
|
||||||
|
| Learning Rate | 2e-4 |
|
||||||
|
| LR Scheduler | Cosine |
|
||||||
|
| Warmup Steps | 100 |
|
||||||
|
| Weight Decay | 0.01 |
|
||||||
|
| Effective Batch Size | 16 |
|
||||||
|
| Max Sequence Length | 4,096 tokens |
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
### Training Curriculum
|
||||||
|
|
||||||
|
YuuKi RxG was trained using the same three-phase curriculum architecture established across the OpceanAI model families, adapted for a reasoning-first base model.
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
<table>
|
||||||
|
<tr>
|
||||||
|
<td width="33%" valign="top">
|
||||||
|
|
||||||
|
**Phase 1 — Identity**
|
||||||
|
3 epochs
|
||||||
|
|
||||||
|
| Source | Ratio |
|
||||||
|
|:-------|:-----:|
|
||||||
|
| Yuuki dataset | 65% |
|
||||||
|
| Reasoning pairs | 20% |
|
||||||
|
| Math instruction | 10% |
|
||||||
|
| General alignment | 5% |
|
||||||
|
|
||||||
|
*Establish YuuKi identity over DeepSeek-R1 base without degrading reasoning capability.*
|
||||||
|
|
||||||
|
</td>
|
||||||
|
<td width="33%" valign="top">
|
||||||
|
|
||||||
|
**Phase 2 — Reasoning**
|
||||||
|
2 epochs
|
||||||
|
|
||||||
|
| Source | Ratio |
|
||||||
|
|:-------|:-----:|
|
||||||
|
| Yuuki dataset | 40% |
|
||||||
|
| Reasoning pairs | 30% |
|
||||||
|
| Math instruction | 20% |
|
||||||
|
| General alignment | 10% |
|
||||||
|
|
||||||
|
*Reinforce structured chain-of-thought and competition-level mathematical reasoning.*
|
||||||
|
|
||||||
|
</td>
|
||||||
|
<td width="33%" valign="top">
|
||||||
|
|
||||||
|
**Phase 3 — Consolidation**
|
||||||
|
2 epochs
|
||||||
|
|
||||||
|
| Source | Ratio |
|
||||||
|
|:-------|:-----:|
|
||||||
|
| Yuuki dataset | 80% |
|
||||||
|
| Reasoning pairs | 10% |
|
||||||
|
| Math instruction | 10% |
|
||||||
|
| General alignment | 0% |
|
||||||
|
|
||||||
|
*Consolidate behavioral consistency and prevent capability regression.*
|
||||||
|
|
||||||
|
</td>
|
||||||
|
</tr>
|
||||||
|
</table>
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
<div align="center">
|
||||||
|
|
||||||
|
## Available Files
|
||||||
|
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
| File | Format | Description |
|
||||||
|
|:-----|:------:|:------------|
|
||||||
|
| `model.safetensors` | BF16 merged | Full precision weights, LoRA merged into base |
|
||||||
|
| `yuuki-rxg-8b.Q8_0.gguf` | GGUF Q8\_0 | Quantized for llama.cpp and Ollama |
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
<div align="center">
|
||||||
|
|
||||||
|
## Limitations
|
||||||
|
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
- **GPQA Diamond gap.** RxG scores 64.0% on GPQA Diamond, below Gemini-2.5-Flash-Thinking (82.8%) and o3-mini (76.8%). This benchmark tests graduate-level science reasoning across physics, chemistry, and biology — domains underrepresented in the Yuuki training dataset. This is a known gap and a target for the RxG 14B release.
|
||||||
|
- **LiveCodeBench.** Code generation at 62.0% is competitive but not leading at this scale. RxG is not primarily a coding model; this capability is inherited from the DeepSeek-R1 base.
|
||||||
|
- **Context utilization.** While the model supports 32,768 tokens, fine-tuning was conducted at 4,096 tokens. Performance on tasks requiring full context utilization beyond 4,096 tokens has not been formally evaluated.
|
||||||
|
- **Safety alignment** has not been formally evaluated under adversarial conditions. Not recommended for high-stakes or safety-critical deployment without additional review.
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
<div align="center">
|
||||||
|
|
||||||
|
## The RxG Family
|
||||||
|
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
RxG is the reasoning-specialized lineage within the OpceanAI ecosystem. Each release targets a specific parameter regime and capability tier.
|
||||||
|
|
||||||
|
| Model | Parameters | Status | Primary Target |
|
||||||
|
|:------|:----------:|:------:|:---------------|
|
||||||
|
| YuuKi RxG Nano | 1.5B | In development | Edge deployment, reasoning baseline |
|
||||||
|
| YuuKi RxG 8B | 8B | Released | General reasoning, competition math |
|
||||||
|
| YuuKi RxG VL 27B | 27B | Planned | Multimodal reasoning, flagship |
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
<div align="center">
|
||||||
|
|
||||||
|
## OpceanAI Ecosystem
|
||||||
|
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
| Model | Family | Parameters | Description |
|
||||||
|
|:------|:------:|:----------:|:------------|
|
||||||
|
| [YuuKi RxG 8B](https://huggingface.co/OpceanAI/Yuuki-RxG) | RxG | 8B | Reasoning flagship, TruthfulQA 96.6% |
|
||||||
|
| [Yumo Nano](https://huggingface.co/OpceanAI/yumo-nano) | Yumo | 1.5B | Math specialist, surpasses DeepScaleR |
|
||||||
|
| [YuuKi NxG VL](https://huggingface.co/OpceanAI/Yuuki-NxG-VL) | NxG | 7B | General conversation + vision |
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
<div align="center">
|
||||||
|
|
||||||
|
## Links
|
||||||
|
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
<div align="center">
|
||||||
|
|
||||||
|
[](https://huggingface.co/OpceanAI/Yuuki-RxG)
|
||||||
|
|
||||||
|
[](https://huggingface.co/OpceanAI/Yuuki-RxG)
|
||||||
|
|
||||||
|
[](https://huggingface.co/OpceanAI)
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
[](https://github.com/aguitauwu)
|
||||||
|
|
||||||
|
[](https://github.com/sponsors/aguitauwu)
|
||||||
|
|
||||||
|
[](https://discord.gg/j8zV2u8k)
|
||||||
|
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
<div align="center">
|
||||||
|
|
||||||
|
## Citation
|
||||||
|
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
```bibtex
|
||||||
|
@misc{awa_omg_2026,
|
||||||
|
author = { awa_omg },
|
||||||
|
title = { Yuuki-RxG (Revision 7996797) },
|
||||||
|
year = 2026,
|
||||||
|
url = { https://huggingface.co/OpceanAI/Yuuki-RxG },
|
||||||
|
doi = { 10.57967/hf/8342 },
|
||||||
|
publisher = { Hugging Face }
|
||||||
|
}
|
||||||
|
```
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
<div align="center">
|
||||||
|
|
||||||
|
## License
|
||||||
|
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
```
|
||||||
|
Apache License 2.0
|
||||||
|
|
||||||
|
Copyright (c) 2026 OpceanAI
|
||||||
|
|
||||||
|
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.
|
||||||
|
```
|
||||||
|
|
||||||
|
Inherits license terms from [DeepSeek-R1-Distill-Qwen-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-8B).
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
<div align="center">
|
||||||
|
|
||||||
|
## Updates
|
||||||
|
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
| Date | Milestone |
|
||||||
|
|:-----|:----------|
|
||||||
|
| **2026-04-09** | TruthfulQA 96.6% independently verified across three evaluation runs |
|
||||||
|
| **2026-04-09** | AIME 2024: 87.3% — surpasses DeepSeek-R1-8B |
|
||||||
|
| **2026-04-09** | GGUF Q8\_0 export available |
|
||||||
|
| **2026-04-09** | YuuKi RxG 8B v1.0 released on Hugging Face |
|
||||||
|
|
||||||
|
**Last updated:** 2026-04-09
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
<div align="center">
|
||||||
|
|
||||||
|
**8B parameters. The most capable model OpceanAI has released.**<br>
|
||||||
|
**Surpasses its base model. Competitive with systems an order of magnitude larger.**
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
[](https://huggingface.co/OpceanAI)
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
*The RxG family. More releases coming.*
|
||||||
|
|
||||||
|
</div>
|
||||||
101
chat_template.jinja
Normal file
101
chat_template.jinja
Normal file
@@ -0,0 +1,101 @@
|
|||||||
|
{%- if not add_generation_prompt is defined %}
|
||||||
|
{%- set add_generation_prompt = false %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true, is_last_user=false) %}
|
||||||
|
{%- for message in messages %}
|
||||||
|
{%- if message['role'] == 'system' %}
|
||||||
|
{%- if ns.is_first_sp %}
|
||||||
|
{%- set ns.system_prompt = ns.system_prompt + message['content'] %}
|
||||||
|
{%- set ns.is_first_sp = false %}
|
||||||
|
{%- else %}
|
||||||
|
{%- set ns.system_prompt = ns.system_prompt + '\n\n' + message['content'] %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
|
||||||
|
{#- Adapted from https://github.com/sgl-project/sglang/blob/main/examples/chat_template/tool_chat_template_deepseekr1.jinja #}
|
||||||
|
{%- if tools is defined and tools is not none %}
|
||||||
|
{%- set tool_ns = namespace(text='You are a helpful assistant with tool calling capabilities. ' + 'When a tool call is needed, you MUST use the following format to issue the call:\n' + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>function<｜tool▁sep｜>FUNCTION_NAME\n' + '```json\n{"param1": "value1", "param2": "value2"}\n```<｜tool▁call▁end｜><｜tool▁calls▁end｜>\n\n' + 'Make sure the JSON is valid.' + '## Tools\n\n### Function\n\nYou have the following functions available:\n\n') %}
|
||||||
|
{%- for tool in tools %}
|
||||||
|
{%- set tool_ns.text = tool_ns.text + '\n```json\n' + (tool | tojson) + '\n```\n' %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- if ns.system_prompt|length != 0 %}
|
||||||
|
{%- set ns.system_prompt = ns.system_prompt + '\n\n' + tool_ns.text %}
|
||||||
|
{%- else %}
|
||||||
|
{%- set ns.system_prompt = tool_ns.text %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- bos_token }}
|
||||||
|
{{- ns.system_prompt }}
|
||||||
|
{%- set last_index = (messages|length - 1) %}
|
||||||
|
{%- for message in messages %}
|
||||||
|
{%- set content = message['content'] %}
|
||||||
|
{%- if message['role'] == 'user' %}
|
||||||
|
{%- set ns.is_tool = false -%}
|
||||||
|
{%- set ns.is_first = false -%}
|
||||||
|
{%- set ns.is_last_user = true -%}
|
||||||
|
{%- if loop.index0 == last_index %}
|
||||||
|
{{- '<｜User｜>' + content }}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<｜User｜>' + content + '<｜Assistant｜>'}}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if message['role'] == 'assistant' %}
|
||||||
|
{%- if '</think>' in content %}
|
||||||
|
{%- set content = (content.split('</think>')|last) %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}
|
||||||
|
{%- set ns.is_last_user = false -%}
|
||||||
|
{%- if ns.is_tool %}
|
||||||
|
{{- '<｜tool▁outputs▁end｜>'}}
|
||||||
|
{%- endif %}
|
||||||
|
{%- set ns.is_first = false %}
|
||||||
|
{%- set ns.is_tool = false -%}
|
||||||
|
{%- set ns.is_output_first = true %}
|
||||||
|
{%- for tool in message['tool_calls'] %}
|
||||||
|
{%- set arguments = tool['function']['arguments'] %}
|
||||||
|
{%- if arguments is not string %}
|
||||||
|
{%- set arguments = arguments|tojson %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if not ns.is_first %}
|
||||||
|
{%- if content is none %}
|
||||||
|
{{- '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + arguments + '\n' + '```' + '<｜tool▁call▁end｜>'}}
|
||||||
|
}
|
||||||
|
{%- else %}
|
||||||
|
{{- content + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + arguments + '\n' + '```' + '<｜tool▁call▁end｜>'}}
|
||||||
|
{%- endif %}
|
||||||
|
{%- set ns.is_first = true -%}
|
||||||
|
{%- else %}
|
||||||
|
{{- '\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + arguments + '\n' + '```' + '<｜tool▁call▁end｜>'}}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- '<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none) %}
|
||||||
|
{%- set ns.is_last_user = false -%}
|
||||||
|
{%- if ns.is_tool %}
|
||||||
|
{{- '<｜tool▁outputs▁end｜>' + content + '<｜end▁of▁sentence｜>'}}
|
||||||
|
{%- set ns.is_tool = false -%}
|
||||||
|
{%- else %}
|
||||||
|
{{- content + '<｜end▁of▁sentence｜>'}}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if message['role'] == 'tool' %}
|
||||||
|
{%- set ns.is_last_user = false -%}
|
||||||
|
{%- set ns.is_tool = true -%}
|
||||||
|
{%- if ns.is_output_first %}
|
||||||
|
{{- '<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}
|
||||||
|
{%- set ns.is_output_first = false %}
|
||||||
|
{%- else %}
|
||||||
|
{{- '\n<｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor -%}
|
||||||
|
{%- if ns.is_tool %}
|
||||||
|
{{- '<｜tool▁outputs▁end｜>'}}
|
||||||
|
{%- endif %}
|
||||||
|
{#- if add_generation_prompt and not ns.is_last_user and not ns.is_tool #}
|
||||||
|
{%- if add_generation_prompt and not ns.is_tool %}
|
||||||
|
{{- '<｜Assistant｜>'}}
|
||||||
|
{%- endif %}
|
||||||
72
config.json
Normal file
72
config.json
Normal file
@@ -0,0 +1,72 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen3ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 4096,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 12288,
|
||||||
|
"layer_types": [
|
||||||
|
"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",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention"
|
||||||
|
],
|
||||||
|
"max_position_embeddings": 131072,
|
||||||
|
"max_window_layers": 36,
|
||||||
|
"model_type": "qwen3",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 36,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"pad_token_id": 151671,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_parameters": {
|
||||||
|
"rope_theta": 1000000,
|
||||||
|
"rope_type": "default"
|
||||||
|
},
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"unsloth_fixed": true,
|
||||||
|
"unsloth_version": "2026.3.8",
|
||||||
|
"use_cache": false,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b42ab9f1c2b0572453abc0f35db7e2cbe5ed05a24e66747c220c0a587bc7e077
|
||||||
|
size 4902257696
|
||||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:e015d2390d5d2803871f2e77f00b8751a4189f435572d9509aafa91543fb40d7
|
||||||
|
size 4915960368
|
||||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:3f4cdfbff80fb51641d010a280c17d32d3b7a6dfe81bd80bd165bc323dbe63de
|
||||||
|
size 4983068496
|
||||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:92c7fdf0ef593f1fbbc42d02828e16023e4d392bbdc5d96a473edf4a47cb963e
|
||||||
|
size 1580230264
|
||||||
406
model.safetensors.index.json
Normal file
406
model.safetensors.index.json
Normal file
@@ -0,0 +1,406 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 16381470720
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.norm.weight": "model-00004-of-00004.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
3
rxg_benchmark.png
Normal file
3
rxg_benchmark.png
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:2c0b70508b473ac35678430dde94cefa2d49c3b53f38369d6d2fa447f7158d55
|
||||||
|
size 158039
|
||||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:02844461e932c93c3730915188ef99ee73968727451fcf8561733f0e3750a102
|
||||||
|
size 11423536
|
||||||
17
tokenizer_config.json
Normal file
17
tokenizer_config.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user