Downloads · 30 days
93
7% of all-time downloads
RichardErkhov/bhuvana-ak7_-_OrpoLlama-3.2-1B-gguf
bhuvana-ak7_-_OrpoLlama-3.2-1B-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.
Downloads · 30 days
93
7% of all-time downloads
All-time downloads
1.4K
Public
Repo size
1.9 GB
Likes
0
Public
Click a slice to open those files.
.gguf4.5 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
OrpoLlama-3.2-1B - GGUF
| Name | Quant method | Size |
|---|---|---|
| OrpoLlama-3.2-1B.Q2_K.gguf | Q2_K | 0.21GB |
| OrpoLlama-3.2-1B.Q3_K_S.gguf | Q3_K_S | 0.21GB |
| OrpoLlama-3.2-1B.Q3_K.gguf | Q3_K | 0.22GB |
| OrpoLlama-3.2-1B.Q3_K_M.gguf | Q3_K_M | 0.22GB |
| OrpoLlama-3.2-1B.Q3_K_L.gguf | Q3_K_L | 0.22GB |
| OrpoLlama-3.2-1B.IQ4_XS.gguf | IQ4_XS | 0.22GB |
| OrpoLlama-3.2-1B.Q4_0.gguf | Q4_0 | 0.22GB |
| OrpoLlama-3.2-1B.IQ4_NL.gguf | IQ4_NL | 0.22GB |
| OrpoLlama-3.2-1B.Q4_K_S.gguf | Q4_K_S | 0.22GB |
| OrpoLlama-3.2-1B.Q4_K.gguf | Q4_K | 0.22GB |
| OrpoLlama-3.2-1B.Q4_K_M.gguf | Q4_K_M | 0.22GB |
| OrpoLlama-3.2-1B.Q4_1.gguf | Q4_1 | 0.22GB |
| OrpoLlama-3.2-1B.Q5_0.gguf | Q5_0 | 0.22GB |
| OrpoLlama-3.2-1B.Q5_K_S.gguf | Q5_K_S | 0.22GB |
| OrpoLlama-3.2-1B.Q5_K.gguf | Q5_K | 0.22GB |
| OrpoLlama-3.2-1B.Q5_K_M.gguf | Q5_K_M | 0.22GB |
| OrpoLlama-3.2-1B.Q5_1.gguf | Q5_1 | 0.22GB |
| OrpoLlama-3.2-1B.Q6_K.gguf | Q6_K | 0.22GB |
| OrpoLlama-3.2-1B.Q8_0.gguf | Q8_0 | 0.28GB |
This model is a fine-tuned version of meta-llama/Llama-3.2-1B, using ORPO (Optimized Regularization for Prompt Optimization) Trainer. This model is fine-tuned using the mlabonne/orpo-dpo-mix-40k dataset. Only 1000 data samples were used to train quickly using ORPO.
The base model meta-llama/Llama-3.2-1B has been fine-tuned using ORPO on a few samples of mlabonne/orpo-dpo-mix-40k dataset. The Llama 3.2 instruction-tuned text-only model is optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks. This fine-tuned version is aimed at improving the understanding of the context in prompts and thereby increasing the interpretability of the model.
The model was evaluated on the following benchmarks, with the following performance metrics:
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| hellaswag | 1 | none | 0 | acc | ↑ | 0.2504 | ± | 0.0043 |
| none | 0 | acc_norm | ↑ | 0.2504 | ± | 0.0043 |