初始化项目，由ModelHub XC社区提供模型
Model: OpenLLM-Ro/RoLlama3-8b-Instruct-2024-06-28 Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
759
README.md
Normal file
759
README.md
Normal file
@@ -0,0 +1,759 @@
|
||||
---
|
||||
license: cc-by-nc-4.0
|
||||
language:
|
||||
- ro
|
||||
base_model:
|
||||
- meta-llama/Meta-Llama-3-8B
|
||||
datasets:
|
||||
- OpenLLM-Ro/ro_sft_alpaca
|
||||
- OpenLLM-Ro/ro_sft_alpaca_gpt4
|
||||
- OpenLLM-Ro/ro_sft_dolly
|
||||
- OpenLLM-Ro/ro_sft_selfinstruct_gpt4
|
||||
- OpenLLM-Ro/ro_sft_norobots
|
||||
- OpenLLM-Ro/ro_sft_orca
|
||||
- OpenLLM-Ro/ro_sft_camel
|
||||
model-index:
|
||||
- name: OpenLLM-Ro/RoLlama3-8b-Instruct-2024-06-28
|
||||
results:
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: RoMT-Bench
|
||||
type: RoMT-Bench
|
||||
metrics:
|
||||
- name: Score
|
||||
type: Score
|
||||
value: 5.15
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: RoCulturaBench
|
||||
type: RoCulturaBench
|
||||
metrics:
|
||||
- name: Score
|
||||
type: Score
|
||||
value: 3.71
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: Romanian_Academic_Benchmarks
|
||||
type: Romanian_Academic_Benchmarks
|
||||
metrics:
|
||||
- name: Average accuracy
|
||||
type: accuracy
|
||||
value: 50.56
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: OpenLLM-Ro/ro_arc_challenge
|
||||
type: OpenLLM-Ro/ro_arc_challenge
|
||||
metrics:
|
||||
- name: Average accuracy
|
||||
type: accuracy
|
||||
value: 44.70
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: OpenLLM-Ro/ro_mmlu
|
||||
type: OpenLLM-Ro/ro_mmlu
|
||||
metrics:
|
||||
- name: Average accuracy
|
||||
type: accuracy
|
||||
value: 52.19
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: OpenLLM-Ro/ro_winogrande
|
||||
type: OpenLLM-Ro/ro_winogrande
|
||||
metrics:
|
||||
- name: Average accuracy
|
||||
type: accuracy
|
||||
value: 67.23
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: OpenLLM-Ro/ro_hellaswag
|
||||
type: OpenLLM-Ro/ro_hellaswag
|
||||
metrics:
|
||||
- name: Average accuracy
|
||||
type: accuracy
|
||||
value: 57.69
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: OpenLLM-Ro/ro_gsm8k
|
||||
type: OpenLLM-Ro/ro_gsm8k
|
||||
metrics:
|
||||
- name: Average accuracy
|
||||
type: accuracy
|
||||
value: 30.23
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: OpenLLM-Ro/ro_truthfulqa
|
||||
type: OpenLLM-Ro/ro_truthfulqa
|
||||
metrics:
|
||||
- name: Average accuracy
|
||||
type: accuracy
|
||||
value: 51.34
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: LaRoSeDa_binary
|
||||
type: LaRoSeDa_binary
|
||||
metrics:
|
||||
- name: Average macro-f1
|
||||
type: macro-f1
|
||||
value: 97.52
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: LaRoSeDa_multiclass
|
||||
type: LaRoSeDa_multiclass
|
||||
metrics:
|
||||
- name: Average macro-f1
|
||||
type: macro-f1
|
||||
value: 67.41
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: LaRoSeDa_binary_finetuned
|
||||
type: LaRoSeDa_binary_finetuned
|
||||
metrics:
|
||||
- name: Average macro-f1
|
||||
type: macro-f1
|
||||
value: 94.15
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: LaRoSeDa_multiclass_finetuned
|
||||
type: LaRoSeDa_multiclass_finetuned
|
||||
metrics:
|
||||
- name: Average macro-f1
|
||||
type: macro-f1
|
||||
value: 87.13
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: WMT_EN-RO
|
||||
type: WMT_EN-RO
|
||||
metrics:
|
||||
- name: Average bleu
|
||||
type: bleu
|
||||
value: 24.01
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: WMT_RO-EN
|
||||
type: WMT_RO-EN
|
||||
metrics:
|
||||
- name: Average bleu
|
||||
type: bleu
|
||||
value: 27.36
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: WMT_EN-RO_finetuned
|
||||
type: WMT_EN-RO_finetuned
|
||||
metrics:
|
||||
- name: Average bleu
|
||||
type: bleu
|
||||
value: 26.53
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: WMT_RO-EN_finetuned
|
||||
type: WMT_RO-EN_finetuned
|
||||
metrics:
|
||||
- name: Average bleu
|
||||
type: bleu
|
||||
value: 40.36
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: XQuAD
|
||||
type: XQuAD
|
||||
metrics:
|
||||
- name: Average exact_match
|
||||
type: exact_match
|
||||
value: 39.43
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: XQuAD
|
||||
type: XQuAD
|
||||
metrics:
|
||||
- name: Average f1
|
||||
type: f1
|
||||
value: 59.50
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: XQuAD_finetuned
|
||||
type: XQuAD_finetuned
|
||||
metrics:
|
||||
- name: Average exact_match
|
||||
type: exact_match
|
||||
value: 44.45
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: XQuAD_finetuned
|
||||
type: XQuAD_finetuned
|
||||
metrics:
|
||||
- name: Average f1
|
||||
type: f1
|
||||
value: 59.76
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: STS
|
||||
type: STS
|
||||
metrics:
|
||||
- name: Average spearman
|
||||
type: spearman
|
||||
value: 77.20
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: STS
|
||||
type: STS
|
||||
metrics:
|
||||
- name: Average pearson
|
||||
type: pearson
|
||||
value: 77.87
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: STS_finetuned
|
||||
type: STS_finetuned
|
||||
metrics:
|
||||
- name: Average spearman
|
||||
type: spearman
|
||||
value: 85.80
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: STS_finetuned
|
||||
type: STS_finetuned
|
||||
metrics:
|
||||
- name: Average pearson
|
||||
type: pearson
|
||||
value: 86.05
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: RoMT-Bench
|
||||
type: RoMT-Bench
|
||||
metrics:
|
||||
- name: First turn
|
||||
type: Score
|
||||
value: 6.03
|
||||
- name: Second turn
|
||||
type: Score
|
||||
value: 4.28
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: OpenLLM-Ro/ro_arc_challenge
|
||||
type: OpenLLM-Ro/ro_arc_challenge
|
||||
metrics:
|
||||
- name: 0-shot
|
||||
type: accuracy
|
||||
value: 41.90
|
||||
- name: 1-shot
|
||||
type: accuracy
|
||||
value: 44.30
|
||||
- name: 3-shot
|
||||
type: accuracy
|
||||
value: 44.56
|
||||
- name: 5-shot
|
||||
type: accuracy
|
||||
value: 45.50
|
||||
- name: 10-shot
|
||||
type: accuracy
|
||||
value: 46.10
|
||||
- name: 25-shot
|
||||
type: accuracy
|
||||
value: 45.84
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: OpenLLM-Ro/ro_mmlu
|
||||
type: OpenLLM-Ro/ro_mmlu
|
||||
metrics:
|
||||
- name: 0-shot
|
||||
type: accuracy
|
||||
value: 50.85
|
||||
- name: 1-shot
|
||||
type: accuracy
|
||||
value: 51.24
|
||||
- name: 3-shot
|
||||
type: accuracy
|
||||
value: 53.30
|
||||
- name: 5-shot
|
||||
type: accuracy
|
||||
value: 53.39
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: OpenLLM-Ro/ro_winogrande
|
||||
type: OpenLLM-Ro/ro_winogrande
|
||||
metrics:
|
||||
- name: 0-shot
|
||||
type: accuracy
|
||||
value: 65.19
|
||||
- name: 1-shot
|
||||
type: accuracy
|
||||
value: 66.54
|
||||
- name: 3-shot
|
||||
type: accuracy
|
||||
value: 67.88
|
||||
- name: 5-shot
|
||||
type: accuracy
|
||||
value: 69.30
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: OpenLLM-Ro/ro_hellaswag
|
||||
type: OpenLLM-Ro/ro_hellaswag
|
||||
metrics:
|
||||
- name: 0-shot
|
||||
type: accuracy
|
||||
value: 56.12
|
||||
- name: 1-shot
|
||||
type: accuracy
|
||||
value: 57.37
|
||||
- name: 3-shot
|
||||
type: accuracy
|
||||
value: 57.92
|
||||
- name: 5-shot
|
||||
type: accuracy
|
||||
value: 58.18
|
||||
- name: 10-shot
|
||||
type: accuracy
|
||||
value: 58.85
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: OpenLLM-Ro/ro_gsm8k
|
||||
type: OpenLLM-Ro/ro_gsm8k
|
||||
metrics:
|
||||
- name: 1-shot
|
||||
type: accuracy
|
||||
value: 29.42
|
||||
- name: 3-shot
|
||||
type: accuracy
|
||||
value: 30.02
|
||||
- name: 5-shot
|
||||
type: accuracy
|
||||
value: 31.24
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: LaRoSeDa_binary
|
||||
type: LaRoSeDa_binary
|
||||
metrics:
|
||||
- name: 0-shot
|
||||
type: macro-f1
|
||||
value: 97.43
|
||||
- name: 1-shot
|
||||
type: macro-f1
|
||||
value: 96.60
|
||||
- name: 3-shot
|
||||
type: macro-f1
|
||||
value: 97.90
|
||||
- name: 5-shot
|
||||
type: macro-f1
|
||||
value: 98.13
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: LaRoSeDa_multiclass
|
||||
type: LaRoSeDa_multiclass
|
||||
metrics:
|
||||
- name: 0-shot
|
||||
type: macro-f1
|
||||
value: 63.77
|
||||
- name: 1-shot
|
||||
type: macro-f1
|
||||
value: 68.91
|
||||
- name: 3-shot
|
||||
type: macro-f1
|
||||
value: 66.36
|
||||
- name: 5-shot
|
||||
type: macro-f1
|
||||
value: 70.61
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: WMT_EN-RO
|
||||
type: WMT_EN-RO
|
||||
metrics:
|
||||
- name: 0-shot
|
||||
type: bleu
|
||||
value: 6.92
|
||||
- name: 1-shot
|
||||
type: bleu
|
||||
value: 29.33
|
||||
- name: 3-shot
|
||||
type: bleu
|
||||
value: 29.79
|
||||
- name: 5-shot
|
||||
type: bleu
|
||||
value: 30.02
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: WMT_RO-EN
|
||||
type: WMT_RO-EN
|
||||
metrics:
|
||||
- name: 0-shot
|
||||
type: bleu
|
||||
value: 4.50
|
||||
- name: 1-shot
|
||||
type: bleu
|
||||
value: 30.30
|
||||
- name: 3-shot
|
||||
type: bleu
|
||||
value: 36.96
|
||||
- name: 5-shot
|
||||
type: bleu
|
||||
value: 37.70
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: XQuAD_EM
|
||||
type: XQuAD_EM
|
||||
metrics:
|
||||
- name: 0-shot
|
||||
type: exact_match
|
||||
value: 4.45
|
||||
- name: 1-shot
|
||||
type: exact_match
|
||||
value: 48.24
|
||||
- name: 3-shot
|
||||
type: exact_match
|
||||
value: 52.03
|
||||
- name: 5-shot
|
||||
type: exact_match
|
||||
value: 53.03
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: XQuAD_F1
|
||||
type: XQuAD_F1
|
||||
metrics:
|
||||
- name: 0-shot
|
||||
type: f1
|
||||
value: 26.08
|
||||
- name: 1-shot
|
||||
type: f1
|
||||
value: 68.40
|
||||
- name: 3-shot
|
||||
type: f1
|
||||
value: 71.92
|
||||
- name: 5-shot
|
||||
type: f1
|
||||
value: 71.60
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: STS_Spearman
|
||||
type: STS_Spearman
|
||||
metrics:
|
||||
- name: 1-shot
|
||||
type: spearman
|
||||
value: 77.76
|
||||
- name: 3-shot
|
||||
type: spearman
|
||||
value: 76.72
|
||||
- name: 5-shot
|
||||
type: spearman
|
||||
value: 77.12
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
name: STS_Pearson
|
||||
type: STS_Pearson
|
||||
metrics:
|
||||
- name: 1-shot
|
||||
type: pearson
|
||||
value: 77.83
|
||||
- name: 3-shot
|
||||
type: pearson
|
||||
value: 77.64
|
||||
- name: 5-shot
|
||||
type: pearson
|
||||
value: 78.13
|
||||
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
*Built with Meta Llama 3*
|
||||
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
RoLlama3 is a family of pretrained and fine-tuned generative text models for Romanian. This is the repository for the **instruct 8B model**. Links to other models can be found at the bottom of this page.
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
OpenLLM-Ro represents the first open-source effort to build a LLM specialized for Romanian. OpenLLM-Ro developed and publicly releases a collection of Romanian LLMs, both in the form of foundational model and instruct and chat variants.
|
||||
|
||||
|
||||
- **Developed by:** OpenLLM-Ro
|
||||
<!-- - **Funded by [optional]:** [More Information Needed] -->
|
||||
<!-- - **Shared by [optional]:** [More Information Needed] -->
|
||||
<!-- - **Model type:** [More Information Needed] -->
|
||||
- **Language(s):** Romanian
|
||||
- **License:** cc-by-nc-4.0
|
||||
- **Finetuned from model:** [Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B)
|
||||
- **Trained using:** [RoAlpaca](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_alpaca), [RoAlpacaGPT4](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_alpaca_gpt4), [RoDolly](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_dolly), [RoSelfInstruct](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_selfinstruct_gpt4), [RoNoRobots](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_norobots), [RoOrca](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_orca), [RoCamel](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_camel)
|
||||
|
||||
|
||||
### Model Sources
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** https://github.com/OpenLLM-Ro/LLaMA-Factory
|
||||
- **Paper:** https://arxiv.org/abs/2406.18266
|
||||
|
||||
## Intended Use
|
||||
|
||||
### Intended Use Cases
|
||||
|
||||
RoLlama3 is intented for research use in Romanian. Base models can be adapted for a variety of natural language tasks while instruction and chat tuned models are intended for assistant-like chat.
|
||||
|
||||
### Out-of-Scope Use
|
||||
|
||||
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||
|
||||
Use in any manner that violates the license, any applicable laws or regluations, use in languages other than Romanian.
|
||||
|
||||
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
Use the code below to get started with the model.
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained("OpenLLM-Ro/RoLlama3-8b-Instruct-2024-06-28")
|
||||
model = AutoModelForCausalLM.from_pretrained("OpenLLM-Ro/RoLlama3-8b-Instruct-2024-06-28")
|
||||
|
||||
instruction = "Ce jocuri de societate pot juca cu prietenii mei?"
|
||||
chat = [
|
||||
{"role": "system", "content": "Ești un asistent folositor, respectuos și onest. Încearcă să ajuți cât mai mult prin informațiile oferite, excluzând răspunsuri toxice, rasiste, sexiste, periculoase și ilegale."},
|
||||
{"role": "user", "content": instruction},
|
||||
]
|
||||
prompt = tokenizer.apply_chat_template(chat, tokenize=False, system_message="")
|
||||
|
||||
inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
|
||||
outputs = model.generate(input_ids=inputs, max_new_tokens=128)
|
||||
print(tokenizer.decode(outputs[0]))
|
||||
```
|
||||
|
||||
## Academic Benchmarks
|
||||
|
||||
<table>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td><strong>Model</strong></td>
|
||||
<td><strong><center>Average</center></strong></td>
|
||||
<td><strong><center>ARC</center></strong></td>
|
||||
<td><strong><center>MMLU</center></strong></td>
|
||||
<td><strong><center>Winogrande</center></strong></td>
|
||||
<td><strong><center>Hellaswag</center></strong></td>
|
||||
<td><strong><center>GSM8k</center></strong></td>
|
||||
<td><strong><center>TruthfulQA</center></strong></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Llama-3-8B-Instruct</td><td><center>50.62</center></td><td><center>43.69</center></td><td><center>52.04</center></td><td><center>59.33</center></td><td><center>53.19</center></td><td><center><strong>43.87</strong></center></td><td><center><strong>51.59</strong></center></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><em>RoLlama3-8b-Instruct-2024-06-28</em></td><td><center><em>50.56</em></center></td><td><center><em>44.70</em></center></td><td><center><em>52.19</em></center></td><td><center><em><strong>67.23</strong></em></center></td><td><center><em>57.69</em></center></td><td><center><em>30.23</em></center></td><td><center><em>51.34</em></center></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>RoLlama3-8b-Instruct-2024-10-09</td><td><center><strong>52.21</strong></center></td><td><center><strong>47.94</strong></center></td><td><center><strong>53.50</strong></center></td><td><center>66.06</center></td><td><center><strong>59.72</strong></center></td><td><center>40.16</center></td><td><center>45.90</center></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>RoLlama3-8b-Instruct-DPO-2024-10-09</td><td><center>49.96</center></td><td><center>46.29</center></td><td><center>53.29</center></td><td><center>65.57</center></td><td><center>58.15</center></td><td><center>34.77</center></td><td><center>41.70</center></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
|
||||
|
||||
## Downstream tasks
|
||||
|
||||
<table>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td></td>
|
||||
<td colspan="4"><center><strong>LaRoSeDa</strong></center></td>
|
||||
<td colspan="4"><center><strong>WMT</strong></center></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td></td>
|
||||
<td colspan="2"><center><strong>Few-shot</strong></center></td>
|
||||
<td colspan="2"><center><strong>Finetuned</strong></center></td>
|
||||
<td colspan="2"><center><strong>Few-shot</strong></center></td>
|
||||
<td colspan="2"><center><strong>Finetuned</strong></center></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><strong>Model</strong></td>
|
||||
<td><center><strong>Binary<br>(Macro F1)</strong></center></td>
|
||||
<td><center><strong>Multiclass<br>(Macro F1)</strong></center></td>
|
||||
<td><center><strong>Binary<br>(Macro F1)</strong></center></td>
|
||||
<td><center><strong>Multiclass<br>(Macro F1)</strong></center></td>
|
||||
<td><center><strong>EN-RO<br>(Bleu)</strong></center></td>
|
||||
<td><center><strong>RO-EN<br>(Bleu)</strong></center></td>
|
||||
<td><center><strong>EN-RO<br>(Bleu)</strong></center></td>
|
||||
<td><center><strong>RO-EN<br>(Bleu)</strong></center>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Llama-3-8B-Instruct</td><td><center>95.88</center></td><td><center>56.21</center></td><td><center><strong>98.53</strong></center></td><td><center>86.19</center></td><td><center>18.88</center></td><td><center><strong>30.98</strong></center></td><td><center><strong>28.02</strong></center></td><td><center>40.28</center></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><em>RoLlama3-8b-Instruct-2024-06-28</em></td><td><center><em><strong>97.52</strong></em></center></td><td><center><em><strong>67.41</strong></em></center></td><td><center><em>94.15</em></center></td><td><center><em>87.13</em></center></td><td><center><em><strong>24.01</strong></em></center></td><td><center><em>27.36</em></center></td><td><center><em>26.53</em></center></td><td><center><em>40.36</em></center></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>RoLlama3-8b-Instruct-2024-10-09</td><td><center>95.58</center></td><td><center>61.20</center></td><td><center>96.46</center></td><td><center><strong>87.26</strong></center></td><td><center>22.92</center></td><td><center>24.28</center></td><td><center>27.31</center></td><td><center><strong>40.52</strong></center></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>RoLlama3-8b-Instruct-DPO-2024-10-09</td><td><center>97.48</center></td><td><center>54.00</center></td><td><center>-</center></td><td><center>-</center></td><td><center>22.09</center></td><td><center>23.00</center></td><td><center>-</center></td><td><center>-</center></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
|
||||
<table>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td></td>
|
||||
<td colspan="4"><center><strong>XQuAD</strong></center></td>
|
||||
<td colspan="4"><center><strong>STS</strong></center></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td></td>
|
||||
<td colspan="2"><center><strong>Few-shot</strong></center></td>
|
||||
<td colspan="2"><center><strong>Finetuned</strong></center></td>
|
||||
<td colspan="2"><center><strong>Few-shot</strong></center></td>
|
||||
<td colspan="2"><center><strong>Finetuned</strong></center></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><strong>Model</strong></td>
|
||||
<td><center><strong>(EM)</strong></center></td>
|
||||
<td><center><strong>(F1)</strong></center></td>
|
||||
<td><center><strong>(EM)</strong></center></td>
|
||||
<td><center><strong>(F1)</strong></center></td>
|
||||
<td><center><strong>(Spearman)</strong></center></td>
|
||||
<td><center><strong>(Pearson)</strong></center></td>
|
||||
<td><center><strong>(Spearman)</strong></center></td>
|
||||
<td><center><strong>(Pearson)</strong></center></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Llama-3-8B-Instruct</td><td><center><strong>39.47</strong></center></td><td><center>58.67</center></td><td><center><strong>67.65</strong></center></td><td><center><strong>82.77</strong></center></td><td><center>73.04</center></td><td><center>72.36</center></td><td><center>83.49</center></td><td><center>84.06</center></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><em>RoLlama3-8b-Instruct-2024-06-28</em></td><td><center><em>39.43</em></center></td><td><center><em><strong>59.50</strong></em></center></td><td><center><em>44.45</em></center></td><td><center><em>59.76</em></center></td><td><center><em>77.20</em></center></td><td><center><em>77.87</em></center></td><td><center><em>85.80</em></center></td><td><center><em>86.05</em></center></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>RoLlama3-8b-Instruct-2024-10-09</td><td><center>18.89</center></td><td><center>31.79</center></td><td><center>50.84</center></td><td><center>65.18</center></td><td><center>77.60</center></td><td><center>76.86</center></td><td><center><strong>86.70</strong></center></td><td><center><strong>87.09</strong></center></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>RoLlama3-8b-Instruct-DPO-2024-10-09</td><td><center>26.05</center></td><td><center>42.77</center></td><td><center>-</center></td><td><center>-</center></td><td><center><strong>79.64</strong></center></td><td><center><strong>79.52</strong></center></td><td><center>-</center></td><td><center>-</center></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
|
||||
## MT-Bench
|
||||
|
||||
<table>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td><strong>Model</strong></td>
|
||||
<td><strong><center>Average</center></strong></td>
|
||||
<td><strong><center>1st turn</center></strong></td>
|
||||
<td><strong><center>2nd turn</center></strong></td>
|
||||
<td><strong><center>Answers in Ro</center></strong></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Llama-3-8B-Instruct</td><td><center><strong>5.96</strong></center></td><td><center>6.16</center></td><td><center><strong>5.76</strong></center></td><td><center>158/160</center></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><em>RoLlama3-8b-Instruct-2024-06-28</em></td><td><center><em>5.15</em></center></td><td><center><em>6.03</em></center></td><td><center><em>4.28</em></center></td><td><center><em><strong>160/160</strong></em></center></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>RoLlama3-8b-Instruct-2024-10-09</td><td><center>5.38</center></td><td><center>6.09</center></td><td><center>4.67</center></td><td><center><strong>160/160</strong></center></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>RoLlama3-8b-Instruct-DPO-2024-10-09</td><td><center>5.87</center></td><td><center><strong>6.22</strong></center></td><td><center>5.49</center></td><td><center><strong>160/160</strong></center></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
|
||||
## RoCulturaBench
|
||||
|
||||
<table>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td><strong>Model</strong></td>
|
||||
<td><strong><center>Average</center></strong></td>
|
||||
<td><strong><center>Answers in Ro</center></strong></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Llama-3-8B-Instruct</td><td><center><strong>4.62</strong></center></td><td><center><strong>100/100</strong></center></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><em>RoLlama3-8b-Instruct-2024-06-28</em></td><td><center><em>3.71</em></center></td><td><center><em><strong>100/100</strong></em></center></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>RoLlama3-8b-Instruct-2024-10-09</td><td><center>3.81</center></td><td><center><strong>100/100</strong></center></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>RoLlama3-8b-Instruct-DPO-2024-10-09</td><td><center>4.40</center></td><td><center><strong>100/100</strong></center></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
|
||||
|
||||
## RoLlama3 Model Family
|
||||
|
||||
| Model | Link |
|
||||
|--------------------|:--------:|
|
||||
|*RoLlama3-8b-Instruct-2024-06-28*| [link](https://huggingface.co/OpenLLM-Ro/RoLlama3-8b-Instruct-2024-06-28) |
|
||||
|RoLlama3-8b-Instruct-2024-10-09| [link](https://huggingface.co/OpenLLM-Ro/RoLlama3-8b-Instruct-2024-10-09) |
|
||||
|RoLlama3-8b-Instruct-DPO-2024-10-09| [link](https://huggingface.co/OpenLLM-Ro/RoLlama3-8b-Instruct-DPO-2024-10-09) |
|
||||
|
||||
|
||||
## Citation
|
||||
|
||||
```
|
||||
@inproceedings{masala-etal-2024-vorbesti,
|
||||
title = "``Vorbe\c{s}ti Rom{\^a}ne\c{s}te?'' A Recipe to Train Powerful {R}omanian {LLM}s with {E}nglish Instructions",
|
||||
author = "Masala, Mihai and Ilie-Ablachim, Denis and Dima, Alexandru and Corlatescu, Dragos Georgian and Zavelca, Miruna-Andreea and Olaru, Ovio and Terian, Simina-Maria and Terian, Andrei and Leordeanu, Marius and Velicu, Horia and Popescu, Marius and Dascalu, Mihai and Rebedea, Traian",
|
||||
editor = "Al-Onaizan, Yaser and Bansal, Mohit and Chen, Yun-Nung",
|
||||
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
|
||||
month = nov,
|
||||
year = "2024",
|
||||
address = "Miami, Florida, USA",
|
||||
publisher = "Association for Computational Linguistics",
|
||||
url = "https://aclanthology.org/2024.findings-emnlp.681/",
|
||||
doi = "10.18653/v1/2024.findings-emnlp.681",
|
||||
pages = "11632--11647"
|
||||
}
|
||||
```
|
||||
<!-- **APA:**
|
||||
|
||||
[More Information Needed] -->
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"_name_or_path": "meta-llama/Meta-Llama-3-8B",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"eos_token_id": 128001,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 8192,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 500000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.40.1",
|
||||
"use_cache": false,
|
||||
"vocab_size": 128256
|
||||
}
|
||||
9
generation_config.json
Normal file
9
generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"bos_token_id": 128000,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 128001,
|
||||
"max_length": 4096,
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.9,
|
||||
"transformers_version": "4.40.1"
|
||||
}
|
||||
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 sha256:89fe0a62527233df9717c0df83377095dafa2fef88387a58fade7be1af1685bb
|
||||
size 4976698672
|
||||
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:f3502b0efe365feb6deae483dfbd9eeeb092345dd0c62a6848637fce3876f21e
|
||||
size 4999802720
|
||||
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 sha256:1d72d8d6db34a2ef639d69083410a1ae57f2575ffe87a3adb5b38b1a8a52f0de
|
||||
size 4915916176
|
||||
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:dede4b0572ceed8bfd6a44b01d34bfe468e991e51c03bc88871b7b2296773f9c
|
||||
size 1168138808
|
||||
298
model.safetensors.index.json
Normal file
298
model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 16060522496
|
||||
},
|
||||
"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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-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_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-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-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_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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-00004-of-00004.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00004-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-00004-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_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.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_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_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_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_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_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_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_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_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_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_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-00002-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_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00004-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
17
special_tokens_map.json
Normal file
17
special_tokens_map.json
Normal file
@@ -0,0 +1,17 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<|eot_id|>"
|
||||
}
|
||||
410563
tokenizer.json
Normal file
410563
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
2065
tokenizer_config.json
Normal file
2065
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user