Downloads · 30 days
27
5% of all-time downloads
RatanRohith_-_NeuralPizza-7B-V0.2-gguf
RichardErkhov/RatanRohith_-_NeuralPizza-7B-V0.2-gguf
RatanRohith_-_NeuralPizza-7B-V0.2-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
493
Public
Repo size
82.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf95.2 GB · 100%
At a glance
- Access
- Public
- Created
- Sep 3, 2024
- Updated
- Sep 3, 2024
- SHA
- 6ae694c2
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
NeuralPizza-7B-V0.2 - GGUF
- Model creator: https://huggingface.co/RatanRohith/
- Original model: https://huggingface.co/RatanRohith/NeuralPizza-7B-V0.2/
| Name | Quant method | Size |
|---|---|---|
| NeuralPizza-7B-V0.2.Q2_K.gguf | Q2_K | 2.53GB |
| NeuralPizza-7B-V0.2.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| NeuralPizza-7B-V0.2.IQ3_S.gguf | IQ3_S | 2.96GB |
| NeuralPizza-7B-V0.2.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| NeuralPizza-7B-V0.2.IQ3_M.gguf | IQ3_M | 3.06GB |
| NeuralPizza-7B-V0.2.Q3_K.gguf | Q3_K | 3.28GB |
| NeuralPizza-7B-V0.2.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| NeuralPizza-7B-V0.2.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| NeuralPizza-7B-V0.2.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| NeuralPizza-7B-V0.2.Q4_0.gguf | Q4_0 | 3.83GB |
| NeuralPizza-7B-V0.2.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| NeuralPizza-7B-V0.2.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| NeuralPizza-7B-V0.2.Q4_K.gguf | Q4_K | 4.07GB |
| NeuralPizza-7B-V0.2.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| NeuralPizza-7B-V0.2.Q4_1.gguf | Q4_1 | 4.24GB |
| NeuralPizza-7B-V0.2.Q5_0.gguf | Q5_0 | 4.65GB |
| NeuralPizza-7B-V0.2.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| NeuralPizza-7B-V0.2.Q5_K.gguf | Q5_K | 4.78GB |
| NeuralPizza-7B-V0.2.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| NeuralPizza-7B-V0.2.Q5_1.gguf | Q5_1 | 5.07GB |
| NeuralPizza-7B-V0.2.Q6_K.gguf | Q6_K | 5.53GB |
| NeuralPizza-7B-V0.2.Q8_0.gguf | Q8_0 | 7.17GB |
Original model description:
library_name: Transformers tags:
- transformers
- fine-tuned
- language-modeling
- direct-preference-optimization datasets:
- Intel/orca_dpo_pairs license: apache-2.0
Model Description
NeuralPizza-7B-V0.2 is a fine-tuned version of the RatanRohith/NeuralMathChat-7B-V0.2 model, specialized through Direct Preference Optimization (DPO). It was fine-tuned using the Intel/orca_dpo_pairs dataset, focusing on enhancing model performance based on preference comparisons.
Intended Use
This model is primarily intended for research and experimental applications in language modeling, especially for exploring the Direct Preference Optimization method. It provides insights into the nuances of DPO in the context of language model tuning.
Training Data
The model was fine-tuned using the Intel/orca_dpo_pairs dataset. This dataset is designed for applying and testing Direct Preference Optimization techniques in language models.
- Created
- Sep 3, 2024
- Updated
- Sep 3, 2024