seedboxai
/

Llama-3-KafkaLM-8B-v0.1

@@ -1,199 +1,119 @@
 ---
 library_name: transformers
-tags: []
 ---
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## 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. -->
-[More Information Needed]
-## Evaluation
-<!-- 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. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]

 ---
 library_name: transformers
+tags:
+- deutsch
+- german
+- seedbox
+- llama3
+- english
+license: llama3
+datasets:
+- seedboxai/multitask_german_examples_32k
+language:
+- de
+- en
+pipeline_tag: text-generation
 ---
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/645ded34a45b4182d7f5c385/fJPPaHpT8T5F-oY27MT3W.png)
+# Llama-3-KafkaLM-8B-v0.1
+**KafkaLM 8b** is a Llama3 8b model which was finetuned on an ensemble of popular high-quality open-source instruction sets (translated from English to German).
+Llama 3 KafkaLM 8b is a [Seedbox](https://huggingface.co/seedboxai) project trained by [Dennis Dickmann](https://huggingface.co/doubledsbv).
+**Why Kafka?**
+The models are proficient, yet creative, and have some tendencies to linguistically push boundaries 😊
+## Model Details
+The purpose of releasing the **KafkaLM series** is to contribute to the German AI community with a set of fine-tuned LLMs that are easy to use in everyday applications across a variety of tasks.
+The main goal is to provide LLMs proficient in German, especially to be used in German-speaking business contexts where English alone is not sufficient.
+### Dataset
+I used a 8k filtered version of the following [seedboxai/multitask_german_examples_32k](https://huggingface.co/datasets/seedboxai/multitask_german_examples_32k)
+### Inference
+Getting started with the model is straightforward
+```python
+import transformers
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+model_id = "seedboxai/Llama-3-Kafka-8B-v0.1"
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16)
+tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)
+pipeline = transformers.pipeline(
+    model=model, tokenizer=tokenizer,
+    return_full_text=True,
+    task='text-generation',
+    device="cuda",
+)
+messages = [
+    {"role": "system", "content": "Du bist ein hilfreicher KI-Assistent."},
+    {"role": "user", "content": "Wer ist eigentlich dieser Kafka?"},
+]
+prompt = pipeline.tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+terminators = [
+    pipeline.tokenizer.eos_token_id,
+    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
+outputs = pipeline(
+    prompt,
+    max_new_tokens=max_new_tokens,
+    num_beams=5,
+    num_return_sequences=1,
+    early_stopping=True,
+    eos_token_id=terminators,
+    do_sample=True,
+    temperature=temperature,
+    top_p=0.9,
+)
+print(outputs[0]["generated_text"][len(prompt):])
+```
+```
+<|start_header_id|>system<|end_header_id|>Du bist ein hilfreicher KI-Assistent.<|eot_id|>
+<|start_header_id|>user<|end_header_id|>Wer ist eigentlich dieser Kafka?<|eot_id|>
+<|start_header_id|>assistant<|end_header_id|>Franz Kafka (1883-1924) war ein tschechisch-österreichischer Schriftsteller,
+der als einer der bedeutendsten Autoren des 20. Jahrhunderts gilt. Seine Werke sind geprägt von existenzieller Angst, Isolation, Verwirrung und Absurdität.
+Kafka wurde in Prag, Österreich-Ungarn (heute Tschechische Republik), geboren und wuchs in einer jüdischen Familie auf.
+Er studierte Rechtswissenschaften und arbeitete als Versicherungsangestellter, bevor er sich dem Schreiben zuwandte.
+Kafkas literarisches Werk umfasst Romane, Erzählungen, Briefe und Tagebücher. Zu seinen bekanntesten Werken gehören "Der Prozess" (1925),
+"Das Schloss" (1926) und "Die Verwandlung" (1915). Seine Geschichten sind geprägt von surrealen, traumähnlichen Szenarien,
+in denen die Charaktere oft in Situationen geraten, die sie nicht verstehen oder kontrollieren können.
+Kafkas Werk hat einen tiefgreifenden Einfluss auf die Literatur und Kultur des 20. Jahrhunderts gehabt.
+Seine Werke wurden in viele Sprachen übersetzt und inspirierten Autoren wie Albert Camus, Jean-Paul Sartre, Samuel Beckett und Thomas Mann.
+Kafka starb 1924 im Alter von 40 Jahren an Tuberkulose. Trotz seines relativ kurzen Lebens hat er einen bleibenden Eindruck auf die Literatur und Kultur hinterlassen.
+```
+## Disclaimer
+The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model.
+This model should only be used for research purposes. The original Llama2 license and all restrictions of datasets used to train this model apply.