README.md

---
license: llama3.2
language:
- en
base_model: prithivMLmods/Bellatrix-Tiny-1B-R1
pipeline_tag: text-generation
library_name: transformers
tags:
- GRPO
- Reinforcement learning
- trl
- SFT
- llama-cpp
- gguf-my-repo
---

# Triangle104/Bellatrix-Tiny-1B-R1-Q4_K_S-GGUF
This model was converted to GGUF format from [`prithivMLmods/Bellatrix-Tiny-1B-R1`](https://huggingface.co/prithivMLmods/Bellatrix-Tiny-1B-R1) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/prithivMLmods/Bellatrix-Tiny-1B-R1) for more details on the model.

---
Bellatrix is based on a reasoning-based model designed for the DeepSeek-R1 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).
Use with transformers

Starting with transformers >= 4.43.0 onward, you can run conversational inference using the Transformers pipeline abstraction or by leveraging the Auto classes with the generate() function.

Make sure to update your transformers installation via pip install --upgrade transformers.

import torch
from transformers import pipeline

model_id = "prithivMLmods/Bellatrix-Tiny-1B-R1"
pipe = pipeline(
    "text-generation",
    model=model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]
outputs = pipe(
    messages,
    max_new_tokens=256,
)
print(outputs[0]["generated_text"][-1])

Note: You can also find detailed recipes on how to use the model locally, with torch.compile(), assisted generations, quantised and more at huggingface-llama-recipes
Intended Use

Bellatrix is designed for applications that require advanced reasoning and multilingual dialogue capabilities. It is particularly suitable for:

    Agentic Retrieval: Enabling intelligent retrieval of relevant information in a dialogue or query-response system.
    Summarization Tasks: Condensing large bodies of text into concise summaries for easier comprehension.
    Multilingual Use Cases: Supporting conversations in multiple languages with high accuracy and coherence.
    Instruction-Based Applications: Following complex, context-aware instructions to generate precise outputs in a variety of scenarios.

Limitations

Despite its capabilities, Bellatrix has some limitations:

    Domain Specificity: While it performs well on general tasks, its performance may degrade with highly specialized or niche datasets.
    Dependence on Training Data: It is only as good as the quality and diversity of its training data, which may lead to biases or inaccuracies.
    Computational Resources: The model’s optimized transformer architecture can be resource-intensive, requiring significant computational power for fine-tuning and inference.
    Language Coverage: While multilingual, some languages or dialects may have limited support or lower performance compared to widely used ones.
    Real-World Contexts: It may struggle with understanding nuanced or ambiguous real-world scenarios not covered during training.

---
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)

```bash
brew install llama.cpp

```
Invoke the llama.cpp server or the CLI.

### CLI:
```bash
llama-cli --hf-repo Triangle104/Bellatrix-Tiny-1B-R1-Q4_K_S-GGUF --hf-file bellatrix-tiny-1b-r1-q4_k_s.gguf -p "The meaning to life and the universe is"
```

### Server:
```bash
llama-server --hf-repo Triangle104/Bellatrix-Tiny-1B-R1-Q4_K_S-GGUF --hf-file bellatrix-tiny-1b-r1-q4_k_s.gguf -c 2048
```

Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```

Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```

Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Triangle104/Bellatrix-Tiny-1B-R1-Q4_K_S-GGUF --hf-file bellatrix-tiny-1b-r1-q4_k_s.gguf -p "The meaning to life and the universe is"
```
or 
```
./llama-server --hf-repo Triangle104/Bellatrix-Tiny-1B-R1-Q4_K_S-GGUF --hf-file bellatrix-tiny-1b-r1-q4_k_s.gguf -c 2048
```