Update README.md

README.md

@@ -2,7 +2,9 @@
 license: llama3.2
 language:
 - en
-base_model: prithivMLmods/Bellatrix-Tiny-1B-R1
+- es
+base_model:
+- meta-llama/Llama-3.2-1B-Instruct
 pipeline_tag: text-generation
 library_name: transformers
 tags:
@@ -10,50 +12,62 @@ tags:
 - Reinforcement learning
 - trl
 - SFT
-- llama-cpp
-- gguf-my-repo
+- uncensored
+- nsfw
+- 1b
+- 4-bit
+- llama 3.2
+- español
+- koboldcpp
+- not-for-all-audiences
+datasets:
+- openerotica/erotiquant3
 ---
+# Bellatrix Erotiquant3 1B R1
 
-# Novaciano/Bellatrix-Tiny-1B-R1-IQ4_XS-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 and combined with the dataset Erotiquant3 of Openerotica. 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 llama.cpp
-Install llama.cpp through brew (works on Mac and Linux)
+# **Use with transformers**
 
-```bash
-brew install llama.cpp
+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.
 
-```
-Invoke the llama.cpp server or the CLI.
+Make sure to update your transformers installation via `pip install --upgrade transformers`.
 
-### CLI:
-```bash
-llama-cli --hf-repo Novaciano/Bellatrix-Tiny-1B-R1-IQ4_XS-GGUF --hf-file bellatrix-tiny-1b-r1-iq4_xs-imat.gguf -p "The meaning to life and the universe is"
-```
+```python
+import torch
+from transformers import pipeline
 
-### Server:
-```bash
-llama-server --hf-repo Novaciano/Bellatrix-Tiny-1B-R1-IQ4_XS-GGUF --hf-file bellatrix-tiny-1b-r1-iq4_xs-imat.gguf -c 2048
+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 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.
+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`](https://github.com/huggingface/huggingface-llama-recipes)
 
-Step 1: Clone llama.cpp from GitHub.
-```
-git clone https://github.com/ggerganov/llama.cpp
-```
+# **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.
 
-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 Novaciano/Bellatrix-Tiny-1B-R1-IQ4_XS-GGUF --hf-file bellatrix-tiny-1b-r1-iq4_xs-imat.gguf -p "The meaning to life and the universe is"
-```
-or 
-```
-./llama-server --hf-repo Novaciano/Bellatrix-Tiny-1B-R1-IQ4_XS-GGUF --hf-file bellatrix-tiny-1b-r1-iq4_xs-imat.gguf -c 2048
-```
+# **Limitations**  
+Despite its capabilities, Bellatrix has some limitations:  
+1. **Domain Specificity**: While it performs well on general tasks, its performance may degrade with highly specialized or niche datasets.  
+2. **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.  
+3. **Computational Resources**: The model’s optimized transformer architecture can be resource-intensive, requiring significant computational power for fine-tuning and inference.  
+4. **Language Coverage**: While multilingual, some languages or dialects may have limited support or lower performance compared to widely used ones.  
+5. **Real-World Contexts**: It may struggle with understanding nuanced or ambiguous real-world scenarios not covered during training.