初始化项目，由ModelHub XC社区提供模型

Model: OpenLLM-Ro/RoLlama2-7b-Instruct
Source: Original Platform

.gitattributes

@@ -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

README.md

@@ -0,0 +1,724 @@
+---
+license: cc-by-nc-4.0
+language:
+- ro
+base_model:
+- OpenLLM-Ro/RoLlama2-7b-Base
+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
+- OpenLLM-Ro/ro_sft_oasst
+- OpenLLM-Ro/ro_sft_ultrachat
+- OpenLLM-Ro/ro_sft_magpie_mt
+- OpenLLM-Ro/ro_sft_magpie_reasoning
+model-index:
+- name: OpenLLM-Ro/RoLlama2-7b-Instruct-2025-04-23
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: RoMT-Bench
+      type: RoMT-Bench
+    metrics:
+    - name: Score
+      type: Score
+      value: 4.97
+  - task:
+      type: text-generation
+    dataset:
+      name: RoCulturaBench
+      type: RoCulturaBench
+    metrics:
+    - name: Score
+      type: Score
+      value: 4.56
+  - task:
+      type: text-generation
+    dataset:
+      name: Romanian_Academic_Benchmarks
+      type: Romanian_Academic_Benchmarks
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 45.51
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_arc_challenge
+      type: OpenLLM-Ro/ro_arc_challenge
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 45.7
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_mmlu
+      type: OpenLLM-Ro/ro_mmlu
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 40.36
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_winogrande
+      type: OpenLLM-Ro/ro_winogrande
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 63.26
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_hellaswag
+      type: OpenLLM-Ro/ro_hellaswag
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 60.25
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_gsm8k
+      type: OpenLLM-Ro/ro_gsm8k
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 18.02
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_truthfulqa
+      type: OpenLLM-Ro/ro_truthfulqa
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 45.48
+  - task:
+      type: text-generation
+    dataset:
+      name: LaRoSeDa_binary
+      type: LaRoSeDa_binary
+    metrics:
+    - name: Average macro-f1
+      type: macro-f1
+      value: 97.6
+  - task:
+      type: text-generation
+    dataset:
+      name: LaRoSeDa_multiclass
+      type: LaRoSeDa_multiclass
+    metrics:
+    - name: Average macro-f1
+      type: macro-f1
+      value: 60.22
+  - task:
+      type: text-generation
+    dataset:
+      name: WMT_EN-RO
+      type: WMT_EN-RO
+    metrics:
+    - name: Average bleu
+      type: bleu
+      value: 27.21
+  - task:
+      type: text-generation
+    dataset:
+      name: WMT_RO-EN
+      type: WMT_RO-EN
+    metrics:
+    - name: Average bleu
+      type: bleu
+      value: 22.15
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD
+      type: XQuAD
+    metrics:
+    - name: Average exact_match
+      type: exact_match
+      value: 47.39
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD
+      type: XQuAD
+    metrics:
+    - name: Average f1
+      type: f1
+      value: 65.77
+  - task:
+      type: text-generation
+    dataset:
+      name: STS
+      type: STS
+    metrics:
+    - name: Average spearman
+      type: spearman
+      value: 59.05
+  - task:
+      type: text-generation
+    dataset:
+      name: STS
+      type: STS
+    metrics:
+    - name: Average pearson
+      type: pearson
+      value: 56.45
+  - task:
+      type: text-generation
+    dataset:
+      name: RoMT-Bench
+      type: RoMT-Bench
+    metrics:
+    - name: First turn
+      type: Score
+      value: 5.56
+    - name: Second turn
+      type: Score
+      value: 4.39
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_arc_challenge
+      type: OpenLLM-Ro/ro_arc_challenge
+    metrics:
+    - name: 0-shot
+      type: accuracy
+      value: 43.02
+    - name: 1-shot
+      type: accuracy
+      value: 45.84
+    - name: 3-shot
+      type: accuracy
+      value: 45.24
+    - name: 5-shot
+      type: accuracy
+      value: 46.19
+    - name: 10-shot
+      type: accuracy
+      value: 46.7
+    - name: 25-shot
+      type: accuracy
+      value: 47.22
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_mmlu
+      type: OpenLLM-Ro/ro_mmlu
+    metrics:
+    - name: 0-shot
+      type: accuracy
+      value: 38.64
+    - name: 1-shot
+      type: accuracy
+      value: 40.77
+    - name: 3-shot
+      type: accuracy
+      value: 41.19
+    - name: 5-shot
+      type: accuracy
+      value: 40.86
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_winogrande
+      type: OpenLLM-Ro/ro_winogrande
+    metrics:
+    - name: 0-shot
+      type: accuracy
+      value: 63.61
+    - name: 1-shot
+      type: accuracy
+      value: 62.75
+    - name: 3-shot
+      type: accuracy
+      value: 63.46
+    - name: 5-shot
+      type: accuracy
+      value: 63.22
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_hellaswag
+      type: OpenLLM-Ro/ro_hellaswag
+    metrics:
+    - name: 0-shot
+      type: accuracy
+      value: 59.79
+    - name: 1-shot
+      type: accuracy
+      value: 59.62
+    - name: 3-shot
+      type: accuracy
+      value: 60.12
+    - name: 5-shot
+      type: accuracy
+      value: 60.71
+    - name: 10-shot
+      type: accuracy
+      value: 61.01
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_gsm8k
+      type: OpenLLM-Ro/ro_gsm8k
+    metrics:
+    - name: 1-shot
+      type: accuracy
+      value: 6.14
+    - name: 3-shot
+      type: accuracy
+      value: 22.52
+    - name: 5-shot
+      type: accuracy
+      value: 25.4
+  - task:
+      type: text-generation
+    dataset:
+      name: LaRoSeDa_binary
+      type: LaRoSeDa_binary
+    metrics:
+    - name: 0-shot
+      type: macro-f1
+      value: 98.17
+    - name: 1-shot
+      type: macro-f1
+      value: 96.3
+    - name: 3-shot
+      type: macro-f1
+      value: 97.8
+    - 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: 49.8
+    - name: 1-shot
+      type: macro-f1
+      value: 56.03
+    - name: 3-shot
+      type: macro-f1
+      value: 65.33
+    - name: 5-shot
+      type: macro-f1
+      value: 69.7
+  - task:
+      type: text-generation
+    dataset:
+      name: WMT_EN-RO
+      type: WMT_EN-RO
+    metrics:
+    - name: 0-shot
+      type: bleu
+      value: 19.34
+    - name: 1-shot
+      type: bleu
+      value: 29.89
+    - name: 3-shot
+      type: bleu
+      value: 29.99
+    - name: 5-shot
+      type: bleu
+      value: 29.62
+  - task:
+      type: text-generation
+    dataset:
+      name: WMT_RO-EN
+      type: WMT_RO-EN
+    metrics:
+    - name: 0-shot
+      type: bleu
+      value: 2.29
+    - name: 1-shot
+      type: bleu
+      value: 14.74
+    - name: 3-shot
+      type: bleu
+      value: 34.82
+    - name: 5-shot
+      type: bleu
+      value: 36.75
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD_EM
+      type: XQuAD_EM
+    metrics:
+    - name: 0-shot
+      type: exact_match
+      value: 42.86
+    - name: 1-shot
+      type: exact_match
+      value: 47.82
+    - name: 3-shot
+      type: exact_match
+      value: 48.32
+    - name: 5-shot
+      type: exact_match
+      value: 50.59
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD_F1
+      type: XQuAD_F1
+    metrics:
+    - name: 0-shot
+      type: f1
+      value: 63.66
+    - name: 1-shot
+      type: f1
+      value: 65.27
+    - name: 3-shot
+      type: f1
+      value: 66.04
+    - name: 5-shot
+      type: f1
+      value: 68.12
+  - task:
+      type: text-generation
+    dataset:
+      name: STS_Spearman
+      type: STS_Spearman
+    metrics:
+    - name: 1-shot
+      type: spearman
+      value: 54.51
+    - name: 3-shot
+      type: spearman
+      value: 60.98
+    - name: 5-shot
+      type: spearman
+      value: 61.65
+  - task:
+      type: text-generation
+    dataset:
+      name: STS_Pearson
+      type: STS_Pearson
+    metrics:
+    - name: 1-shot
+      type: pearson
+      value: 54.35
+    - name: 3-shot
+      type: pearson
+      value: 57.88
+    - name: 5-shot
+      type: pearson
+      value: 57.13
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+This model points/is identical to [RoLlama2-7b-Instruct-2025-04-23](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Instruct-2025-04-23).
+
+
+RoLlama2 is a family of pretrained and fine-tuned generative text models for Romanian. This is the repository for the **instruct 7B 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 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:** [RoLlama2-7b-Base](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Base)
+- **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), [RoOpenAssistant](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_oasst), [RoUltraChat](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_ultrachat), [RoMagpiePro](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_magpie_mt), [RoMagpieReasoning](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_magpie_reasoning)
+
+
+### 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
+
+RoLlama2 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/RoLlama2-7b-Instruct")
+model = AutoModelForCausalLM.from_pretrained("OpenLLM-Ro/RoLlama2-7b-Instruct")
+
+instruction = "Care este cel mai înalt vârf muntos din România?"
+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)
+
+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-2-7b-chat</td><td><center>36.84</center></td><td><center>37.03</center></td><td><center>33.80</center></td><td><center>55.87</center></td><td><center>45.36</center></td><td><center>4.90</center></td><td><center>44.09</center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-2024-05-14</td><td><center>45.71</center></td><td><center>43.66</center></td><td><center>39.70</center></td><td><center><strong>70.34</strong></center></td><td><center>57.36</center></td><td><center><strong>18.78</strong></center></td><td><center>44.44</center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-2024-10-09</td><td><center>44.50</center></td><td><center>44.73</center></td><td><center>40.39</center></td><td><center>63.67</center></td><td><center>59.12</center></td><td><center>13.29</center></td><td><center>45.78</center></td>
+</tr>
+<tr>
+<td><em>RoLlama2-7b-Instruct-2025-04-23</em></td><td><center><em>45.51</em></center></td><td><center><em>45.70</em></center></td><td><center><em>40.36</em></center></td><td><center><em>63.26</em></center></td><td><center><em>60.25</em></center></td><td><center><em>18.02</em></center></td><td><center><em>45.48</em></center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-DPO-2024-10-09</td><td><center>43.20</center></td><td><center>44.24</center></td><td><center>38.39</center></td><td><center>62.57</center></td><td><center>59.20</center></td><td><center>15.72</center></td><td><center>39.07</center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-DPO-2025-04-23</td><td><center><strong>46.77</strong></center></td><td><center><strong>48.16</strong></center></td><td><center><strong>41.38</strong></center></td><td><center>64.15</center></td><td><center><strong>61.37</strong></center></td><td><center>18.35</center></td><td><center><strong>47.20</strong></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-2-7b-chat</td><td><center>87.78</center></td><td><center>52.81</center></td><td><center>97.27</center></td><td><center>82.02</center></td><td><center>15.55</center></td><td><center><strong>28.53</strong></center></td><td><center>19.99</center></td><td><center>31.48</center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-2024-05-14</td><td><center>97.48</center></td><td><center><strong>65.26</strong></center></td><td><center><strong>98.83</strong></center></td><td><center><strong>87.28</strong></center></td><td><center><strong>27.38</strong></center></td><td><center>10.32</center></td><td><center>27.59</center></td><td><center><strong>40.13</strong></center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-2024-10-09</td><td><center>97.66</center></td><td><center>62.41</center></td><td><center>97.97</center></td><td><center>60.89</center></td><td><center>27.13</center></td><td><center>19.39</center></td><td><center><strong>27.63</strong></center></td><td><center>39.75</center></td>
+</tr>
+<tr>
+<td><em>RoLlama2-7b-Instruct-2025-04-23</em></td><td><center><em>97.60</em></center></td><td><center><em>60.22</em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td><td><center><em>27.21</em></center></td><td><center><em>22.15</em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-DPO-2024-10-09</td><td><center>97.31</center></td><td><center>60.56</center></td><td><center>-</center></td><td><center>-</center></td><td><center>26.56</center></td><td><center>21.68</center></td><td><center>-</center></td><td><center>-</center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-DPO-2025-04-23</td><td><center><strong>97.77</strong></center></td><td><center>65.21</center></td><td><center>-</center></td><td><center>-</center></td><td><center>25.48</center></td><td><center>22.75</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-2-7b-chat</td><td><center>32.35</center></td><td><center>54.00</center></td><td><center><strong>60.34</strong></center></td><td><center><strong>75.98</strong></center></td><td><center>32.56</center></td><td><center>31.99</center></td><td><center>74.08</center></td><td><center>72.64</center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-2024-05-14</td><td><center>44.52</center></td><td><center>64.75</center></td><td><center>54.96</center></td><td><center>70.20</center></td><td><center>65.50</center></td><td><center><strong>67.79</strong></center></td><td><center>84.44</center></td><td><center>84.76</center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-2024-10-09</td><td><center>45.71</center></td><td><center>65.08</center></td><td><center>59.24</center></td><td><center>74.25</center></td><td><center>59.69</center></td><td><center>57.16</center></td><td><center><strong>84.66</strong></center></td><td><center><strong>85.07</strong></center></td>
+</tr>
+<tr>
+<td><em>RoLlama2-7b-Instruct-2025-04-23</em></td><td><center><em><strong>47.39</strong></em></center></td><td><center><em><strong>65.77</strong></em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td><td><center><em>59.05</em></center></td><td><center><em>56.45</em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-DPO-2024-10-09</td><td><center>35.78</center></td><td><center>59.31</center></td><td><center>-</center></td><td><center>-</center></td><td><center>61.22</center></td><td><center>58.41</center></td><td><center>-</center></td><td><center>-</center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-DPO-2025-04-23</td><td><center>38.28</center></td><td><center>60.88</center></td><td><center>-</center></td><td><center>-</center></td><td><center><strong>66.76</strong></center></td><td><center>64.72</center></td><td><center>-</center></td><td><center>-</center></td>
+</tr>
+</tbody>
+</table>
+
+
+## Romanian 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-2-7b-chat</td><td><center>1.08</center></td><td><center>1.44</center></td><td><center>0.73</center></td><td><center>45/160</center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-2024-05-14</td><td><center>3.86</center></td><td><center>4.67</center></td><td><center>3.04</center></td><td><center><strong>160/160</strong></center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-2024-10-09</td><td><center>4.43</center></td><td><center>4.92</center></td><td><center>3.94</center></td><td><center><strong>160/160</strong></center></td>
+</tr>
+<tr>
+<td><em>RoLlama2-7b-Instruct-2025-04-23</em></td><td><center><em>4.97</em></center></td><td><center><em>5.56</em></center></td><td><center><em>4.39</em></center></td><td><center><em><strong>160/160</strong></em></center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-DPO-2024-10-09</td><td><center>4.61</center></td><td><center>5.15</center></td><td><center>4.06</center></td><td><center><strong>160/160</strong></center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-DPO-2025-04-23</td><td><center><strong>5.55</strong></center></td><td><center><strong>5.84</strong></center></td><td><center><strong>5.26</strong></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-2-7b-chat</td><td><center>1.21</center></td><td><center>33/100</center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-2024-05-14</td><td><center>3.77</center></td><td><center><strong>100/100</strong></center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-2024-10-09</td><td><center>4.08</center></td><td><center><strong>100/100</strong></center></td>
+</tr>
+<tr>
+<td><em>RoLlama2-7b-Instruct-2025-04-23</em></td><td><center><em>4.56</em></center></td><td><center><em><strong>100/100</strong></em></center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-DPO-2024-10-09</td><td><center>4.80</center></td><td><center><strong>100/100</strong></center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-DPO-2025-04-23</td><td><center><strong>5.24</strong></center></td><td><center><strong>100/100</strong></center></td>
+</tr>
+</tbody>
+</table>
+
+
+
+
+
+## RoLlama2 Model Family
+
+| Model              | Link  |
+|--------------------|:--------:|
+|RoLlama2-7b-Base-2024-05-14 | [link](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Base-2024-05-14)    |
+|RoLlama2-7b-Instruct-2024-05-14 | [link](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Instruct-2024-05-14)    |
+|RoLlama2-7b-Instruct-2024-10-09| [link](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Instruct-2024-10-09) |
+|*RoLlama2-7b-Instruct-2025-04-23*| [link](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Instruct-2025-04-23) |
+|RoLlama2-7b-Instruct-DPO-2024-10-09| [link](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Instruct-DPO-2024-10-09) |
+|RoLlama2-7b-Instruct-DPO-2025-04-23| [link](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Instruct-DPO-2025-04-23) |
+
+
+
+## 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]  -->

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "./saves/llama2/instruct-v4/checkpoint-6214",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.44.0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0a58972e12188bddf6100147c737baa3a28b540d599d58196d13c072f5b01e4
+size 4938985352

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cf299d2772e27afacf5637ba1ba9cd23ab0e7d3d2bd447bb0e6118711e24653
+size 4947390880

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a23140400e985e4772640948d3824c05c0959174e36ebfb8d148627cf198406f
+size 3590488816

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13476831232
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% set system_message = 'Ești un asistent folositor, respectuos și onest. Încearcă să ajuți cât mai mult prin informațiile oferite, excluzând răspunsuri toxice, rasiste, sexiste, periculoase și ilegale.' %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if loop.index0 == 0 and system_message is defined %}{% set content = '<<SYS>>\n' + system_message + '\n<</SYS>>\n\n' + message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ '<s>' + '[INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}