Update README.md

README.md

@@ -1,207 +1,268 @@
 ---
-library_name: transformers
-tags: []
----
-
-# Model Card for Model ID
-
-Prelim scores \
-Testi: mt_bench, score 4.642857142857143 \
-Testi: reasoning, score 3.8 \
-Testi: humanities, score 5.5 \
-Testi: roleplay, score 5.3 \
-Testi: math, score 3.4 \
-Testi: extraction, score 2.4 \
-Testi: stem, score 5.4 \
-Testi: writing, score 6.7 \
-Testi: wibe, score 5.621621621621622
-
-
-## 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]
+language:
+- fi
+license: apache-2.0
+tags:
+- finnish
+- llama
+inference: false
+pipeline_tag: text-generation
+base_model: Finnish-NLP/Ahma-3B
 
-<!-- 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]
+# Ahma-3B-Instruct for Finnish
 
-### Training Procedure
+Ahma-3B-Instruct is a instruct/chat-tuned version of [Ahma-3B](https://huggingface.co/Finnish-NLP/Ahma-3B) trained to follow instructions in Finnish. The base Ahma 3B parameter model is decoder-only transformer model based on Meta's Llama (v1) architecture pretrained from scratch on Finnish language. Original Llama model architecture was introduced in
+[this paper](https://arxiv.org/abs/2302.13971)
+and first released at [this page](https://github.com/facebookresearch/llama).
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+What does Ahma mean? Ahma is the Finnish word for wolverine! In the Finnish Lapland, wolverines are the biggest cause of reindeer damage. 
 
-#### Preprocessing [optional]
+There are two different sized base Ahma models, all pretrained from scratch for 139B tokens:
 
-[More Information Needed]
+| Model                                                                           | Context length | Layers | Dim  | Heads | Params |
+|:--------------------------------------------------------------------------------|:---------------|:-------|:-----|:------|:-------|
+| [Ahma-3B](https://huggingface.co/Finnish-NLP/Ahma-3B)                           | 2048           | 26     | 3200 | 32    | 3.6B   |
+| [Ahma-7B](https://huggingface.co/Finnish-NLP/Ahma-7B)                           | 2048           | 32     | 4096 | 32    | 7.0B   |
 
+And two instruct-tuned versions:
 
-#### Training Hyperparameters
+| Model                                                                           | Context length | Layers | Dim  | Heads | Params |
+|:--------------------------------------------------------------------------------|:---------------|:-------|:-----|:------|:-------|
+| [Ahma-3B-Instruct](https://huggingface.co/Finnish-NLP/Ahma-3B-Instruct)         | 2048           | 26     | 3200 | 32    | 3.6B   |
+| [Ahma-7B-Instruct](https://huggingface.co/Finnish-NLP/Ahma-7B-Instruct)         | 2048           | 32     | 4096 | 32    | 7.0B   |
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+## Intended uses & limitations
 
-#### Speeds, Sizes, Times [optional]
+This model was fine-tuned for instruction following. Instruction-tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
 
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+### How to use
 
-[More Information Needed]
+If you want to use this model for instruction-following, you need to use the same prompt format we used in the fine-tuning process (basically the same format what Meta used in their Llama2 models). **Note: do not use "LlamaTokenizer" from transformers library but always use the AutoTokenizer instead, or use the plain sentencepiece tokenizer.** Here is an example using the instruction-following prompt format, with some generation arguments you can modify for your use:
 
-## Evaluation
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
-<!-- This section describes the evaluation protocols and provides the results. -->
+system_prompt = "Olet tekoälyavustaja. Vastaat aina mahdollisimman avuliaasti. Vastauksesi eivät saa sisältää mitään haitallista, epäeettistä, rasistista, seksististä, vaarallista tai laitonta sisältöä. Jos kysymyksessä ei ole mitään järkeä tai se ei ole asiasisällöltään johdonmukainen, selitä miksi sen sijaan, että vastaisit jotain väärin. Jos et tiedä vastausta kysymykseen, älä kerro väärää tietoa."
 
-### Testing Data, Factors & Metrics
 
-#### Testing Data
+def format_prompt(prompt: str) -> str:
+    prompt = f" [INST] <<SYS>>\n{system_prompt.strip()}\n<</SYS>>\n\n{prompt.strip()} [/INST] "
+    return prompt
 
-<!-- This should link to a Dataset Card if possible. -->
 
-[More Information Needed]
+tokenizer = AutoTokenizer.from_pretrained("Finnish-NLP/Ahma-3B-Instruct")
+model = AutoModelForCausalLM.from_pretrained("Finnish-NLP/Ahma-3B-Instruct")
+model = model.to("cuda")
 
-#### Factors
+# use the custom prompt format function or the chat template feature in the tokenizer to format your inputs
 
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+# prompt = format_prompt("Kerro kolme hyötyä, joita pienet avoimen lähdekoodin kielimallit tuovat?")
+# inputs = tokenizer(prompt, return_tensors="pt")
 
-[More Information Needed]
+messages = [
+    {
+        "role": "system",
+        "content": system_prompt,
+    },
+    {"role": "user", "content": "Kerro kolme hyötyä, joita pienet avoimen lähdekoodin kielimallit tuovat?"},
+]
+inputs = tokenizer.apply_chat_template(
+    messages, tokenize=True, add_generation_prompt=True, return_tensors="pt"
+)
+inputs = inputs.to("cuda")
 
-#### Metrics
+generated_ids = model.generate(
+    inputs,
+    temperature=0.6,
+    penalty_alpha=0.6,
+    top_k=4,
+    do_sample=True,
+    repetition_penalty=1.2,
+    min_length=5,
+    max_length=2048,
+)
+generated_text = tokenizer.batch_decode(
+    generated_ids, skip_special_tokens=False
+)[0]
 
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+'''
+1) Parantuneet keskustelutaidot: Pienet, hyvin koulutetut kielimallit voidaan kouluttaa ymmärtämään ja tuottamaan ihmisen kaltaista kieltä, mikä johtaa luonnollisempaan keskusteluun. Tämä voi olla erityisen hyödyllistä sovelluksissa, kuten chat-roboteissa, virtuaaliavustajissa ja kielenkääntämisessä.
 
-[More Information Needed]
+2) Lisääntynyt luovuus kirjoittamisessa: Kielimallit voivat auttaa kirjoittajia tuottamalla ideoita, lauseita ja virkkeitä, jotka ovat hiottuja ja merkityksellisiä. Tämä voi johtaa parempaan kirjoituslaatuun, parempaan organisointiin ja tehokkaampaan viestintään.
 
-### Results
+3) Parempi tietojenkäsittely ja -tallennus: Pienemmät ja edullisemmat kielimallit voivat mullistaa tietojenkäsittelyn ja tallennuksen. Ne voivat säästää tilaa ja resursseja, koska ne pystyvät suorittamaan tiettyjä tehtäviä tehokkaammin kuin perinteiset koneoppimisalgoritmit. Lisäksi kielimallien avoimen lähdekoodin luonne mahdollistaa sen, että tutkijat, kehittäjät ja yritykset voivat tehdä niihin parannuksia ja lisäyksiä, mikä voi johtaa entistä kehittyneempiin ja monipuolisempiin ratkaisuihin.
+'''
+```
 
-[More Information Needed]
+You may experiment with different system prompt instructions too if you like.
 
-#### Summary
+### Limitations and bias
 
+The training data used for this model contains a lot of content from the internet, which is far from neutral. Therefore, the model can have biased predictions. This bias will also affect all fine-tuned versions of this model.
 
+## Training data
 
-## Model Examination [optional]
+To better reflect the data distribution of the training set and balance the common samples and rare samples during training, we implemented the "ClusterClip Sampling" method by [Shao et al. (2024)](https://arxiv.org/abs/2402.14526) using [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) embeddings and KMeans clustering of 30 clusters. The training datasets mentioned below were created using this sampling method.
 
-<!-- Relevant interpretability work for the model goes here -->
+There has also been some indication that gradually increasing the training example lengths during the training could be beneficial. Thus, the training dataset was splitted to 4 bins based on example lengths, and then examples were sampled from the bins so that the example lengths are gradually increasing towards the end of the training while a little amount of the shorter examples are still present too.
 
-[More Information Needed]
+This model was first supervised fine-tuned (SFT) on the combination of the following datasets:
 
-## Environmental Impact
+| Dataset                                          | Dataset type           | Upsampling | Words      | Ratio    | Average words per example |
+|:-------------------------------------------------|:-----------------------|:-----------|:-----------|:---------|:--------------------------|
+| Aya Finnish                                      | Finnish single-turn    | 2.9X       | 55K        | 0.54%    | 83                        |
+| OASST                                            | Translated single-turn | 2.9X       | 507K       | 5.01%    | 139                       |
+| ai2_arc                                          | Translated single-turn | 2.9X       | 12K        | 0.12%    | 39                        |
+| chatbot_arena                                    | Translated single-turn | 2.8X       | 554K       | 5.48%    | 147                       |
+| dibt10k                                          | Translated single-turn | 2.9X       | 363K       | 3.58%    | 262                       |
+| dolly                                            | Translated single-turn | 2.9X       | 221K       | 2.19%    | 71                        |
+| Aya Dutch                                        | Translated single-turn | 2.9X       | 13K        | 0.12%    | 36                        |
+| Aya English                                      | Translated single-turn | 2.9X       | 97K        | 0.96%    | 61                        |
+| Aya French                                       | Translated single-turn | 3.7X       | 75K        | 0.74%    | 58                        |
+| intel_dpo                                        | Translated single-turn | 2.9X       | 539K       | 5.33%    | 163                       |
+| lmsys_1m                                         | Translated single-turn | 2.8X       | 2187K      | 21.61%   | 246                       |
+| news_qa                                          | Translated single-turn | 2.9X       | 297K       | 2.94%    | 152                       |
+| orca_math                                        | Translated single-turn | 2.9X       | 1165K      | 11.51%   | 196                       |
+| Aya Portuguese                                   | Translated single-turn | 2.9X       | 97K        | 0.96%    | 27                        |
+| Aya Spanish                                      | Translated single-turn | 2.8X       | 52K        | 0.51%    | 54                        |
+| Aya Swedish                                      | Translated single-turn | 2.9X       | 5K         | 0.05%    | 41                        |
+| ultrachat                                        | Translated single-turn | 2.8X       | 2199K      | 21.73%   | 221                       |
+| lmsys_multiturn                                  | Translated multi-turn  | 2.9X       | 490K       | 4.84%    | 379                       |
+| oaast2_multiturn                                 | Translated multi-turn  | 2.8X       | 593K       | 5.86%    | 307                       |
+| suomitrivia_synthetic                            | Synthetic single-turn  | 1.0X       | 4K         | 0.04%    | 16                        |
+| wikipedia_multitask_synthetic_qa                 | Synthetic single-turn  | 1.0X       | 206K       | 2.03%    | 499                       |
+| wikipedia_synthetic_qa_reasoning                 | Synthetic single-turn  | 1.0X       | 201K       | 1.98%    | 477                       |
+| wikipedia_synthetic_person_discussions_multiturn | Synthetic multi-turn   | 1.0X       | 188K       | 1.85%    | 194                       |
+| **TOTAL**                                        |                        |            | **10121K** | **100%** | **168**                   |
 
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+After tokenization, the SFT training dataset had 23 million tokens and 5% of the dataset was splitted for evaluation during the training.
 
-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]
+The SFT model was then further fine-tuned with Direct Preference Optimization (DPO) on the combination of the following datasets:
+
+| Dataset         | Dataset type           | Upsampling | Words     | Ratio    | Average words per example |
+|:----------------|:-----------------------|:-----------|:----------|:---------|:--------------------------|
+| intel_dpo       | Translated single-turn | 1.3X       | 467K      | 39.75%   | 153                       |
+| ultrachat       | Translated single-turn | 1.2X       | 1017K     | 57.24%   | 220                       |
+| suomitrivia_dpo | Synthetic single-turn  | 1.0X       | 5K        | 3.01%    | 16                        |
+| **TOTAL**       |                        |            | **1489K** | **100%** | **130**                   |
+
+After tokenization, the DPO training dataset had 3 million tokens and 5% of the dataset was splitted for evaluation during the training.
+
+## Training procedure
+
+### Preprocessing
+
+Texts are tokenized using Byte Pair Encoding (BPE) using the implementation from SentencePiece splitting all numbers into individual digits and using bytes to decompose unknown UTF-8 characters. The total
+vocabulary size is 64k tokens. Inputs are sequences of 2048 consecutive tokens. Texts are not lower cased so this model is case-sensitive: it makes a difference between finnish and Finnish. Both BOS and EOS tokens were used in the fine-tuning.
+
+### Supervised fine-tuning (SFT)
+
+This model was first supervised fine-tuned (SFT) using the [unsloth](https://github.com/unslothai/unsloth) framework with a single NVIDIA GeForce RTX 4080 GPU. The model was fine-tuned for 1 epoch with a learning rate of 5e-05, weight decay of 5e-03, learning rate warmup ratio of 0.1 with cosine decay, batch size of 4 and gradient accumulation of 8 totalling the batch size to 32, max sequence lenght of 2048, and with NEFTune noise alpha of 5. The used optimizer was "paged_adamw_8bit" and the model was loaded with 4bit quantization. Training was done using the Rank-Stabilized LoRA (RSLora) with a rank of 256 and alpha of 128, LoRA dropout of 0.02, and target modules of "q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj".
+
+### Direct Preference Optimization (DPO) fine-tuning
+
+The SFT model was then further fine-tuned with Direct Preference Optimization (DPO) using the [unsloth](https://github.com/unslothai/unsloth) framework with a single NVIDIA GeForce RTX 4080 GPU. The model was fine-tuned for 1 epoch with a learning rate of 2e-05, weight decay of 0.0, learning rate warmup ratio of 0.1 with cosine decay, batch size of 2 and gradient accumulation of 8 totalling the batch size to 16, and with max sequence lenght of 2048. The used optimizer was "paged_adamw_8bit". Training was done using the Rank-Stabilized LoRA (RSLora) with a rank of 64 and alpha of 32, LoRA dropout of 0.05, and target modules of "q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj".
+
+## Evaluation results
 
-## Technical Specifications [optional]
+### FIN-bench
 
-### Model Architecture and Objective
+This Ahma-3B-Instruct model was evaluated using [FIN-bench by TurkuNLP](https://github.com/TurkuNLP/FIN-bench), and the same evaluation was carried out for other relevant Finnish models for comparison: [FinGPT 8B by TurkuNLP](https://huggingface.co/TurkuNLP/gpt3-finnish-8B), [Viking 7B by TurkuNLP, SiloGen and HPLT](https://huggingface.co/LumiOpen/Viking-7B), and [Poro 34B by SiloGen, TurkuNLP and HPLT](https://huggingface.co/LumiOpen/Poro-34B). Below are the results with 0-shot and 3-shot settings in FIN-bench.
 
-[More Information Needed]
+0-shot results:
 
-### Compute Infrastructure
+| Benchmark                  | Ahma 3B base (instruct prompt format) | Ahma 3B Instruct (instruct prompt format) | Ahma 7B base (instruct prompt format) | Ahma 7B Instruct (instruct prompt format) | FinGPT 8B | Viking 7B | Poro 34B (8bit quant) |
+|:---------------------------|:--------------------------------------|:------------------------------------------|:--------------------------------------|:------------------------------------------|:----------|:----------|:----------------------|
+| Analogies                  | 50.77                                 | 48.46                                     | TBA                                   | TBA                                       | 49.23     | 40.00     | 54.62                 |
+| Arithmetic                 | 27.64                                 | 22.14                                     | TBA                                   | TBA                                       | 33.15     | 30.16     | 30.34                 |
+| Cause and Effect           | 59.48                                 | 58.82                                     | TBA                                   | TBA                                       | 66.01     | 58.82     | 62.74                 |
+| Emotions                   | 36.25                                 | 28.12                                     | TBA                                   | TBA                                       | 22.50     | 26.25     | 35.63                 |
+| Empirical Judgements       | 33.33                                 | 35.35                                     | TBA                                   | TBA                                       | 27.27     | 33.33     | 49.49                 |
+| General Knowledge          | 44.29                                 | 48.57                                     | TBA                                   | TBA                                       | 40.00     | 24.29     | 51.43                 |
+| HHH Alignment              | 42.09                                 | 41.66                                     | TBA                                   | TBA                                       | 41.81     | 42.51     | 42.92                 |
+| Intent Recognition         | 24.42                                 | 26.16                                     | TBA                                   | TBA                                       | 17.49     | 22.40     | 68.35                 |
+| Misconceptions             | 46.27                                 | 47.01                                     | TBA                                   | TBA                                       | 53.73     | 53.73     | 52.24                 |
+| Paraphrase                 | 59.50                                 | 73.00                                     | TBA                                   | TBA                                       | 51.00     | 50.00     | 51.00                 |
+| Sentence Ambiguity         | 53.33                                 | 65.00                                     | TBA                                   | TBA                                       | 51.67     | 48.33     | 50.00                 |
+| Similarities Abstraction   | 65.79                                 | 68.42                                     | TBA                                   | TBA                                       | 60.53     | 65.79     | 60.53                 |
+| **Non-Arithmetic Average** | **47.55**                             | **48.95**                                 | TBA                                   | TBA                                       | **46.17** | **44.42** | **52.08**             |
+| **Overall Average**        | **36.49**                             | **34.06**                                 | TBA                                   | TBA                                       | **38.93** | **36.50** | **40.00**             |
 
-[More Information Needed]
 
-#### Hardware
+3-shot results:
 
-[More Information Needed]
+| Benchmark                  | Ahma 3B base (instruct prompt format) | Ahma 3B Instruct (instruct prompt format) | Ahma 7B base (instruct prompt format) | Ahma 7B Instruct (instruct prompt format) | FinGPT 8B | Viking 7B | Poro 34B (8bit quant) |
+|:---------------------------|:--------------------------------------|:------------------------------------------|:--------------------------------------|:------------------------------------------|:----------|:----------|:----------------------|
+| Analogies                  | 50.77                                 | 49.23                                     | TBA                                   | TBA                                       | 40.77     | 54.62     | 76.92                 |
+| Arithmetic                 | 38.38                                 | 43.89                                     | TBA                                   | TBA                                       | 43.63     | 45.78     | 53.68                 |
+| Cause and Effect           | 60.78                                 | 64.71                                     | TBA                                   | TBA                                       | 64.05     | 58.17     | 67.32                 |
+| Emotions                   | 30.00                                 | 41.25                                     | TBA                                   | TBA                                       | 44.37     | 48.13     | 56.87                 |
+| Empirical Judgements       | 46.46                                 | 44.44                                     | TBA                                   | TBA                                       | 32.32     | 43.43     | 63.64                 |
+| General Knowledge          | 47.14                                 | 40.00                                     | TBA                                   | TBA                                       | 54.29     | 28.57     | 74.29                 |
+| HHH Alignment              | 43.53                                 | 44.80                                     | TBA                                   | TBA                                       | 45.39     | 44.80     | 46.07                 |
+| Intent Recognition         | 20.52                                 | 44.22                                     | TBA                                   | TBA                                       | 51.45     | 58.82     | 83.67                 |
+| Misconceptions             | 50.75                                 | 52.24                                     | TBA                                   | TBA                                       | 52.99     | 46.27     | 52.99                 |
+| Paraphrase                 | 50.50                                 | 58.50                                     | TBA                                   | TBA                                       | 53.00     | 54.50     | 55.00                 |
+| Sentence Ambiguity         | 53.33                                 | 48.33                                     | TBA                                   | TBA                                       | 51.67     | 53.33     | 66.67                 |
+| Similarities Abstraction   | 69.74                                 | 72.37                                     | TBA                                   | TBA                                       | 64.47     | 73.68     | 75.00                 |
+| **Non-Arithmetic Average** | **48.48**                             | **51.49**                                 | TBA                                   | TBA                                       | **51.19** | **50.94** | **61.96**             |
+| **Overall Average**        | **42.87**                             | **47.27**                                 | TBA                                   | TBA                                       | **46.99** | **48.07** | **57.36**             |
+
+As we can see, Ahma-3B-Instruct model outperforms 2X larger models like the FinGPT 8B and Viking 7B, especially in non-arithmetic tasks in 0-shot usage. Even the 10X larger Poro 34B model, which is generally better, doesn't show a huge performance difference considering its size, and Ahma-3B-Instruct actually surpasses it in some tasks.
 
-#### Software
+In a 3-shot setting, we can see that the Ahma-3B-Instruct model has better few-shot example following performance compared to the base Ahma 3B model. This could be due to the inclusion of multi-turn examples in the fine-tuning dataset.
 
-[More Information Needed]
+### MTBench Finnish
 
-## Citation [optional]
+This Ahma-3B-Instruct model was primarily evaluated using [MTBench Finnish by LumiOpen](https://github.com/LumiOpen/FastChat/tree/main/fastchat/llm_judge) since this model is fine-tuned for chat and instruction following. Since the MTBench evaluates also multi-turn chats while Ahma base models were only pretrained with single-turn instruction following examples, we have reported MTBench Finnish results separately for their single-turn and multi-turn evaluation examples. This enables us to evaluate how well this Ahma-3B-Instruct model improves on multi-turn chats since its fine-tuning dataset included some multi-turn examples too. [Poro 34B Chat by SiloGen, TurkuNLP and HPLT](https://huggingface.co/LumiOpen/Poro-34B-chat) model's presumably multi-turn results are copied from their model card for the comparison.
 
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+Single-turn results:
 
-**BibTeX:**
+| Benchmark           | Ahma 3B base (instruct prompt format) | Ahma 3B Instruct | Ahma 7B base (instruct prompt format) | Ahma 7B Instruct |
+|:--------------------|:--------------------------------------|:-----------------|:--------------------------------------|:-----------------|
+| Coding              | 1.00                                  | 1.00             | TBA                                   | TBA              |
+| Extraction          | 2.00                                  | 1.30             | TBA                                   | TBA              |
+| Humanities          | 4.05                                  | 6.20             | TBA                                   | TBA              |
+| Math                | 3.00                                  | 3.20             | TBA                                   | TBA              |
+| Reasoning           | 2.90                                  | 4.60             | TBA                                   | TBA              |
+| Roleplay            | 4.80                                  | 6.50             | TBA                                   | TBA              |
+| STEM                | 5.10                                  | 5.95             | TBA                                   | TBA              |
+| Writing             | 6.60                                  | 9.00             | TBA                                   | TBA              |
+| **Overall Average** | **3.68**                              | **4.72**         | TBA                                   | TBA              |
 
-[More Information Needed]
+Multi-turn results:
 
-**APA:**
+| Benchmark           | Ahma 3B base (instruct prompt format) | Ahma 3B Instruct | Ahma 7B base (instruct prompt format) | Ahma 7B Instruct | Poro 34B Chat |
+|:--------------------|:--------------------------------------|:-----------------|:--------------------------------------|:-----------------|:--------------|
+| Coding              | 1.00                                  | 1.00             | TBA                                   | TBA              | 3.70          |
+| Extraction          | 1.55                                  | 1.15             | TBA                                   | TBA              | 6.37          |
+| Humanities          | 3.25                                  | 6.20             | TBA                                   | TBA              | 9.25          |
+| Math                | 2.20                                  | 2.70             | TBA                                   | TBA              | 1.20          |
+| Reasoning           | 2.45                                  | 3.50             | TBA                                   | TBA              | 4.35          |
+| Roleplay            | 4.90                                  | 6.40             | TBA                                   | TBA              | 7.35          |
+| STEM                | 4.20                                  | 4.78             | TBA                                   | TBA              | 7.80          |
+| Writing             | 3.80                                  | 6.65             | TBA                                   | TBA              | 8.50          |
+| **Overall Average** | **2.92**                              | **4.05**         | TBA                                   | TBA              | **6.06**      |
 
-[More Information Needed]
 
-## Glossary [optional]
+As we can see, the Ahma-3B-Instruct model significantly improves upon the base Ahma-3B model, especially in tasks like writing. It's also worth noting that the Ahma-3B-Instruct model shows enhanced performance in multi-turn tasks compared to the base model, which highlights the value of the multi-turn training examples used in the fine-tuning process. The Ahma-3B-Instruct model lost 14% of its single-turn overall score in a multi-turn setting, while the base Ahma-3B model lost 21%. Therefore, this instruct model might be better suited for chat use cases as well. As expected, coding performance was poor since the Ahma models aren't trained on code data.
 
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+Ahma models also seemed to have problems with the fact that they started to constantly repeat the generated text in some evaluation examples, which affected the scoring. With the addition of a repetition penalty setting to the evaluation script generation method, the scores already improved significantly, so Ahma models should be used with better generation settings in real-world use compared to the settings used in this benchmark.
 
-[More Information Needed]
+## Acknowledgements
 
-## More Information [optional]
+This project would not have been possible without compute generously provided by Google through the
+[TPU Research Cloud](https://sites.research.google/trc/).
 
-[More Information Needed]
+## Team Members
 
-## Model Card Authors [optional]
+- Aapo Tanskanen, [Hugging Face profile](https://huggingface.co/aapot), [LinkedIn profile](https://www.linkedin.com/in/aapotanskanen/)
+- Rasmus Toivanen, [Hugging Face profile](https://huggingface.co/RASMUS), [LinkedIn profile](https://www.linkedin.com/in/rasmustoivanen/)
 
-[More Information Needed]
+Feel free to contact us for more details 🤗
 
-## Model Card Contact
 
-[More Information Needed]
+![Ahma](ahma.jpg)