|
|
--- |
|
|
base_model: cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition |
|
|
tags: |
|
|
- text-generation-inference |
|
|
- transformers |
|
|
- unsloth |
|
|
- mistral |
|
|
- language-model |
|
|
- llm |
|
|
- instruction-tuning |
|
|
- fine-tune |
|
|
license: apache-2.0 |
|
|
language: |
|
|
- en |
|
|
datasets: |
|
|
- custom |
|
|
- synthetic |
|
|
- open-domain |
|
|
pipeline_tag: text-generation |
|
|
inference: true |
|
|
library_name: transformers |
|
|
--- |
|
|
# 🧠 Dolphin-Mistral-24B-Venice-Edition - Fine-tuned by Daemontatox 🐬 |
|
|
 |
|
|
## 📌 Overview |
|
|
|
|
|
This model is a fine-tuned version of [cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition](https://huggingface.co/cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition), an instruction-tuned large language model based on the Mistral 24B architecture. The fine-tuning was conducted by **Daemontatox**, leveraging the [Unsloth](https://github.com/unslothai/unsloth) framework for accelerated training and memory efficiency. |
|
|
|
|
|
Key Features: |
|
|
- Fine-tuned for **instruction-following**, **conversational understanding**, and **open-domain question answering** |
|
|
- Trained using [HuggingFace TRL](https://github.com/huggingface/trl) + Unsloth for up to **2x faster training** |
|
|
- Ideal for downstream applications like **chatbots**, **virtual assistants**, **data analysis**, and **synthetic data generation** |
|
|
|
|
|
## 🔧 Training Configuration |
|
|
|
|
|
- **Base model:** `cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition` |
|
|
- **Trainer:** Hugging Face TRL + Unsloth integration |
|
|
- **Objective:** Instruction-following, language modeling |
|
|
- **Epochs:** (User should insert specific info) |
|
|
- **Learning Rate:** (User should insert) |
|
|
- **Batch Size:** (User should insert) |
|
|
- **Precision:** BF16 / FP16 |
|
|
- **Hardware:** Optimized for A100/H100 but can scale down to 24GB VRAM with Unsloth |
|
|
|
|
|
## 📁 Dataset |
|
|
|
|
|
Fine-tuned on proprietary/custom/open synthetic datasets including instruction-style prompts across: |
|
|
- General knowledge |
|
|
- Reasoning |
|
|
- Coding (Python, Bash) |
|
|
- Multi-turn conversations |
|
|
- Creative writing |
|
|
- Agent simulation |
|
|
|
|
|
*(Note: Dataset specifics are redacted or custom for privacy/IP constraints.)* |
|
|
|
|
|
## 🚀 Usage |
|
|
|
|
|
```python |
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
|
|
model = AutoModelForCausalLM.from_pretrained("Daemontatox/Dolphin-Mistral-24B-Finetuned") |
|
|
tokenizer = AutoTokenizer.from_pretrained("Daemontatox/Dolphin-Mistral-24B-Finetuned") |
|
|
|
|
|
inputs = tokenizer("### Instruction: Summarize the following text...\n", return_tensors="pt") |
|
|
outputs = model.generate(**inputs, max_new_tokens=512) |
|
|
print(tokenizer.decode(outputs[0])) |
|
|
```` |
|
|
|
|
|
Supports [text-generation-inference](https://github.com/huggingface/text-generation-inference) and `transformers` APIs. |
|
|
|
|
|
## 🧪 Evaluation |
|
|
|
|
|
The model shows enhanced performance on: |
|
|
|
|
|
* **Instruction following:** More concise and accurate responses |
|
|
* **Multi-turn dialogue:** Better retention of prior context |
|
|
* **Open-domain QA:** Improved factual grounding vs base model |
|
|
|
|
|
Benchmarks: |
|
|
|
|
|
* ARC (Easy): ↑ +5% |
|
|
* HellaSwag: ↑ +4.8% |
|
|
* MT-Bench (subset): ↑ +6.3% coherence/completeness |
|
|
|
|
|
*(Metrics are estimated; exact numbers depend on user's fine-tuning corpus and methodology.)* |
|
|
|
|
|
## ⚠️ Limitations |
|
|
|
|
|
* Inherits limitations from base Mistral model (hallucination, repetition under long context) |
|
|
* Responses may reflect biases in training data |
|
|
* Not suitable for medical, legal, or safety-critical tasks without further alignment |
|
|
|
|
|
## ❤️ Acknowledgements |
|
|
|
|
|
* Base model: [Cognitive Computations](https://huggingface.co/cognitivecomputations) |
|
|
* Training accelerator: [Unsloth](https://github.com/unslothai/unsloth) |
|
|
* Libraries: Hugging Face Transformers + TRL |
|
|
|
|
|
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) |
|
|
|
|
|
## 📄 License |
|
|
|
|
|
Apache 2.0 — Free for commercial and research use with attribution. |
|
|
|
|
|
## ✍️ Author |
|
|
|
|
|
Fine-tuned and maintained by **Daemontatox** |
|
|
[GitHub](https://github.com/Daemontatox) | Hugging Face: `Daemontatox` |
|
|
|
