Update README.md

README.md

@@ -1,199 +1,355 @@
 ---
-library_name: transformers
-tags: []
+license: cc-by-nc-4.0
+language:
+- ro
+base_model:
+- OpenLLM-Ro/RoLlama3.1-8b-Instruct
+datasets:
+- OpenLLM-Ro/ro_dpo_helpsteer
+model-index:
+  - name: OpenLLM-Ro/RoLlama3.1-8b-Instruct-DPO-4bit
+    results:
+      - task:
+          type: text-generation
+        dataset:
+          name: OpenLLM-Ro/ro_arc_challenge
+          type: OpenLLM-Ro/ro_arc_challenge
+        metrics:
+          - name: Average accuracy
+            type: accuracy
+            value: 42.74
+          - name: 0-shot
+            type: accuracy
+            value: 40.79
+          - name: 1-shot
+            type: accuracy
+            value: 40.36
+          - name: 3-shot
+            type: accuracy
+            value: 43.36
+          - name: 5-shot
+            type: accuracy
+            value: 44.04
+          - name: 10-shot
+            type: accuracy
+            value: 43.87
+          - name: 25-shot
+            type: accuracy
+            value: 44.04
+
+      - task:
+          type: text-generation
+        dataset:
+          name: OpenLLM-Ro/ro_mmlu
+          type: OpenLLM-Ro/ro_mmlu
+        metrics:
+          - name: Average accuracy
+            type: accuracy
+            value: 42.27
+          - name: 0-shot
+            type: accuracy
+            value: 43.23
+          - name: 1-shot
+            type: accuracy
+            value: 42.47
+          - name: 3-shot
+            type: accuracy
+            value: 42.19
+          - name: 5-shot
+            type: accuracy
+            value: 41.19
+
+      - task:
+          type: text-generation
+        dataset:
+          name: OpenLLM-Ro/ro_winogrande
+          type: OpenLLM-Ro/ro_winogrande
+        metrics:
+          - name: Average accuracy
+            type: accuracy
+            value: 64.94
+          - name: 0-shot
+            type: accuracy
+            value: 63.14
+          - name: 1-shot
+            type: accuracy
+            value: 64.64
+          - name: 3-shot
+            type: accuracy
+            value: 65.43
+          - name: 5-shot
+            type: accuracy
+            value: 66.54
+
+      - task:
+          type: text-generation
+        dataset:
+          name: OpenLLM-Ro/ro_hellaswag
+          type: OpenLLM-Ro/ro_hellaswag
+        metrics:
+          - name: Average accuracy
+            type: accuracy
+            value: 52.39
+          - name: 0-shot
+            type: accuracy
+            value: 52.42
+          - name: 1-shot
+            type: accuracy
+            value: 52.30
+          - name: 3-shot
+            type: accuracy
+            value: 52.60
+          - name: 5-shot
+            type: accuracy
+            value: 52.20
+          - name: 10-shot
+            type: accuracy
+            value: 52.42
+
+      - task:
+          type: text-generation
+        dataset:
+          name: OpenLLM-Ro/ro_gsm8k
+          type: OpenLLM-Ro/ro_gsm8k
+        metrics:
+          - name: Average accuracy
+            type: accuracy
+            value: 38.87
+          - name: 1-shot
+            type: accuracy
+            value: 28.13
+          - name: 3-shot
+            type: accuracy
+            value: 42.23
+          - name: 5-shot
+            type: accuracy
+            value: 46.25
+
+      - task:
+          type: text-generation
+        dataset:
+          name: OpenLLM-Ro/ro_truthfulqa
+          type: OpenLLM-Ro/ro_truthfulqa
+        metrics:
+          - name: Average accuracy
+            type: accuracy
+            value: 48.67
+          - name: 0-shot
+            type: accuracy
+            value: 48.67
+
+      - task:
+          type: text-generation
+        dataset:
+          name: LaRoSeDa_binary
+          type: LaRoSeDa_binary
+        metrics:
+          - name: Average macro-f1
+            type: macro-f1
+            value: 97.47
+          - name: 0-shot
+            type: macro-f1
+            value: 97.43
+          - name: 1-shot
+            type: macro-f1
+            value: 97.33
+          - name: 3-shot
+            type: macro-f1
+            value: 97.70
+          - name: 5-shot
+            type: macro-f1
+            value: 97.43
+
+      - task:
+          type: text-generation
+        dataset:
+          name: LaRoSeDa_multiclass
+          type: LaRoSeDa_multiclass
+        metrics:
+          - name: Average macro-f1
+            type: macro-f1
+            value: 64.05
+          - name: 0-shot
+            type: macro-f1
+            value: 65.90
+          - name: 1-shot
+            type: macro-f1
+            value: 64.68
+          - name: 3-shot
+            type: macro-f1
+            value: 62.36
+          - name: 5-shot
+            type: macro-f1
+            value: 63.27
+
+      - task:
+          type: text-generation
+        dataset:
+          name: WMT_EN-RO
+          type: WMT_EN-RO
+        metrics:
+          - name: Average bleu
+            type: bleu
+            value: 20.54
+          - name: 0-shot
+            type: bleu
+            value: 7.20
+          - name: 1-shot
+            type: bleu
+            value: 25.68
+          - name: 3-shot
+            type: bleu
+            value: 24.50
+          - name: 5-shot
+            type: bleu
+            value: 24.78
+
+      - task:
+          type: text-generation
+        dataset:
+          name: WMT_RO-EN
+          type: WMT_RO-EN
+        metrics:
+          - name: Average bleu
+            type: bleu
+            value: 21.16
+          - name: 0-shot
+            type: bleu
+            value: 2.59
+          - name: 1-shot
+            type: bleu
+            value: 17.54
+          - name: 3-shot
+            type: bleu
+            value: 30.82
+          - name: 5-shot
+            type: bleu
+            value: 33.67
+
+      - task:
+          type: text-generation
+        dataset:
+          name: XQuAD
+          type: XQuAD
+        metrics:
+          - name: Average exact_match
+            type: exact_match
+            value: 21.45
+          - name: Average f1
+            type: f1
+            value: 37.73
+          - name: 0-shot exact_match
+            type: exact_match
+            value: 3.45
+          - name: 0-shot f1
+            type: f1
+            value: 12.36
+          - name: 1-shot exact_match
+            type: exact_match
+            value: 32.02
+          - name: 1-shot f1
+            type: f1
+            value: 55.70
+          - name: 3-shot exact_match
+            type: exact_match
+            value: 33.78
+          - name: 3-shot f1
+            type: f1
+            value: 54.15
+          - name: 5-shot exact_match
+            type: exact_match
+            value: 16.55
+          - name: 5-shot f1
+            type: f1
+            value: 28.71
+
+      - task:
+          type: text-generation
+        dataset:
+          name: STS
+          type: STS
+        metrics:
+          - name: Average pearson
+            type: pearson
+            value: 76.93
+          - name: Average spearman
+            type: spearman
+            value: 77.08
+          - name: 1-shot pearson
+            type: pearson
+            value: 77.02
+          - name: 1-shot spearman
+            type: spearman
+            value: 77.80
+          - name: 3-shot pearson
+            type: pearson
+            value: 76.93
+          - name: 3-shot spearman
+            type: spearman
+            value: 77.00
+          - name: 5-shot pearson
+            type: pearson
+            value: 76.85
+          - name: 5-shot spearman
+            type: spearman
+            value: 76.45
 ---
 
-# Model Card for Model ID
 
-<!-- Provide a quick summary of what the model is/does. -->
+# Model Card for 4-bit RoLlama3.1-8b-Instruct-DPO
 
+*Built from [RoLlama3.1-8b-Instruct-DPO](https://huggingface.co/OpenLLM-Ro/RoLlama3.1-8b-Instruct-DPO), quantized to 4-bit.*
 
+This variant of **RoLlama3.1-8b-Instruct-DPO** provides a reduced footprint through 4-bit quantization, aimed at enabling usage on resource-constrained GPUs while preserving a high fraction of the model’s capabilities.
 
 ## Model Details
 
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+## Comparison to 16 bit 
 
-[More Information Needed]
+It loooks that the effects of the quantization are minimal :
 
-## Evaluation
+| **Task**                 | **Metric**            | **FP16 Original** | **4-bit**       | **Absolute Diff.** | **% Change**       |
+|--------------------------|-----------------------|-------------------|-----------------|---------------------|--------------------|
+| **ARC Challenge**        | Avg. Accuracy         | 44.84             | 42.74           | -2.10              | -4.68%             |
+| **MMLU**                 | Avg. Accuracy         | 55.06             | 42.27           | -12.79             | -23.23%            |
+| **Winogrande**           | Avg. Accuracy         | 65.87             | 64.94           | -0.93              | -1.41%             |
+| **Hellaswag**            | Avg. Accuracy         | 58.67             | 52.39           | -6.28              | -10.70%            |
+| **GSM8K**                | Avg. Accuracy         | 44.17             | 38.87           | -5.30              | -11.99%            |
+| **TruthfulQA**           | Avg. Accuracy         | 47.82             | 48.67           | +0.85              | +1.78%             |
+| **LaRoSeDa (binary)**    | Macro-F1              | 96.10             | 97.47           | +1.37              | +1.43%             |
+| **LaRoSeDa (multiclass)**| Macro-F1              | 55.37             | 64.05           | +8.68              | +15.68%            |
+| **WMT EN-RO**            | BLEU                  | 21.29             | 20.54           | -0.75              | -3.52%             |
+| **WMT RO-EN**            | BLEU                  | 21.86             | 21.16           | -0.70              | -3.20%             |
+| **XQuAD (avg)**          | EM / F1               | 21.58 / 36.54     | 21.45 / 37.73   | ~-0.13 / +1.19     | -0.60% / +3.26%    |
+| **STS (avg)**            | Spearman / Pearson    | 78.01 / 77.98     | 77.08 / 76.93   | -0.93 / -1.05      | -1.19% / -1.35%    |
 
-<!-- This section describes the evaluation protocols and provides the results. -->
 
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+### Model Description
 
-[More Information Needed]
+- **Developed by:** OpenLLM-Ro
+- **Language(s):** Romanian
+- **License:** cc-by-nc-4.0
+- **Quantized from model:** [RoLlama3.1-8b-Instruct-DPO](https://huggingface.co/OpenLLM-Ro/RoLlama3.1-8b-Instruct-DPO)
+- **Quantization:** 4-bit
 
-## More Information [optional]
+Quantization reduces model size and improves inference speed but can lead to small drops in performance. Below is a comprehensive table of the main benchmarks comparing the original full-precision version with the new 4-bit variant.
 
-[More Information Needed]
+## How to Use
 
-## Model Card Authors [optional]
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
-[More Information Needed]
+model_id = "OpenLLM-Ro/RoLlama3.1-8b-Instruct-DPO-4bit"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=True, device_map="auto")
 
-## Model Card Contact
+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="")
 
-[More Information Needed]
+inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt").to("cuda")
+outputs = model.generate(input_ids=inputs, max_new_tokens=128)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))