license, language, library_name, base_model, pipeline_tag, model-index, tags

license	language	library_name	base_model	pipeline_tag	model-index	tags
apache-2.0	en	transformers	Qwen/Qwen2.5-1.5B-Instruct	text-generation	name results Bellatrix-1.5B-xElite task dataset metrics source type name text-generation Text Generation name type split args IFEval (0-Shot) wis-k/instruction-following-eval train num_few_shot 0 type value name inst_level_strict_acc and prompt_level_strict_acc 19.64 averaged accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FBellatrix-1.5B-xElite Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type split args BBH (3-Shot) SaylorTwift/bbh test num_few_shot 3 type value name acc_norm 9.49 normalized accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FBellatrix-1.5B-xElite Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type split args MATH Lvl 5 (4-Shot) lighteval/MATH-Hard test num_few_shot 4 type value name exact_match 12.61 exact match url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FBellatrix-1.5B-xElite Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type split args GPQA (0-shot) Idavidrein/gpqa train num_few_shot 0 type value name acc_norm 3.8 acc_norm url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FBellatrix-1.5B-xElite Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args MuSR (0-shot) TAUR-Lab/MuSR num_few_shot 0 type value name acc_norm 4.44 acc_norm url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FBellatrix-1.5B-xElite Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU-PRO (5-shot) TIGER-Lab/MMLU-Pro main test num_few_shot 5 type value name acc 7.3 accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FBellatrix-1.5B-xElite Open LLM Leaderboard	qwen qwq

 ____  ____  __    __      __   ____  ____  ____  _  _ 
(  _ \( ___)(  )  (  )    /__\ (_  _)(  _ \(_  _)( \/ )
 ) _ < )__)  )(__  )(__  /(__)\  )(   )   / _)(_  )  ( 
(____/(____)(____)(____)(__)(__)(__) (_)\_)(____)(_/\_)

Bellatrix-1.5B-xElite

Bellatrix-1.5B-xElite is based on a reasoning-based model designed for the QWQ synthetic dataset entries. The pipeline's instruction-tuned, text-only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks. These models outperform many of the available open-source options. Bellatrix is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions utilize supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF).

Quickstart with Transformers

Here provides a code snippet with apply_chat_template to show you how to load the tokenizer and model and how to generate contents.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "prithivMLmods/Bellatrix-1.5B-xElite"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "Give me a short introduction to large language model."
messages = [
    {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

Intended Use:

1. Multilingual Dialogue Systems:

   • Designed for conversational AI applications, capable of handling dialogue across multiple languages.
   • Useful in customer service, chatbots, and other dialogue-centric use cases.

2. Reasoning and QWQ Dataset Applications:

   • Optimized for tasks requiring logical reasoning and contextual understanding, particularly in synthetic datasets like QWQ.

3. Agentic Retrieval:

   • Supports retrieval-augmented generation tasks, helping systems fetch and synthesize information effectively.

4. Summarization Tasks:

   • Excels in summarizing long or complex text while maintaining coherence and relevance.

5. Instruction-Following Tasks:

   • Can execute tasks based on specific user instructions due to instruction-tuning during training.

6. Language Generation:

   • Suitable for generating coherent and contextually relevant text in various domains and styles.

Limitations:

1. Synthetic Dataset Bias:

   • Optimization for QWQ and similar datasets may make the model less effective on real-world or less structured data.

2. Data Dependency:

   • Performance may degrade on tasks or languages not well-represented in the training dataset.

3. Computational Requirements:

   • The optimized transformer architecture may demand significant computational resources, especially for fine-tuning or large-scale deployments.

4. Potential Hallucinations:

   • Like most auto-regressive models, it may generate plausible-sounding but factually incorrect or nonsensical outputs.

5. RLHF-Specific Biases:

   • Reinforcement Learning with Human Feedback (RLHF) can introduce biases based on the preferences of the annotators involved in the feedback process.

6. Limited Domain Adaptability:

   • While effective in reasoning and dialogue tasks, it may struggle with highly specialized domains or out-of-distribution tasks.

7. Multilingual Limitations:

   • Although optimized for multilingual use, certain low-resource languages may exhibit poorer performance compared to high-resource ones.

8. Ethical Concerns:

   • May inadvertently generate inappropriate or harmful content if safeguards are not applied, particularly in sensitive applications.

9. Real-Time Usability:

   • Latency in inference time could limit its effectiveness in real-time applications or when scaling to large user bases.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here! Summarized results can be found here!

Metric	Value (%)
Average	9.55
IFEval (0-Shot)	19.64
BBH (3-Shot)	9.49
MATH Lvl 5 (4-Shot)	12.61
GPQA (0-shot)	3.80
MuSR (0-shot)	4.44
MMLU-PRO (5-shot)	7.30