Downloads · 30 days
49
3% of all-time downloads
RichardErkhov/bunnycore_-_Qwen2.5-3B-RP-Mix-gguf
bunnycore_-_Qwen2.5-3B-RP-Mix-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
49
3% of all-time downloads
All-time downloads
1.9K
Public
Repo size
35 GB
Likes
0
Public
Click a slice to open those files.
.gguf41.2 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Qwen2.5-3B-RP-Mix - GGUF
| Name | Quant method | Size |
|---|---|---|
| Qwen2.5-3B-RP-Mix.Q2_K.gguf | Q2_K | 1.28GB |
| Qwen2.5-3B-RP-Mix.Q3_K_S.gguf | Q3_K_S | 1.48GB |
| Qwen2.5-3B-RP-Mix.Q3_K.gguf | Q3_K | 1.61GB |
| Qwen2.5-3B-RP-Mix.Q3_K_M.gguf | Q3_K_M | 1.61GB |
| Qwen2.5-3B-RP-Mix.Q3_K_L.gguf | Q3_K_L | 1.71GB |
| Qwen2.5-3B-RP-Mix.IQ4_XS.gguf | IQ4_XS | 1.79GB |
| Qwen2.5-3B-RP-Mix.Q4_0.gguf | Q4_0 | 1.86GB |
| Qwen2.5-3B-RP-Mix.IQ4_NL.gguf | IQ4_NL | 1.87GB |
| Qwen2.5-3B-RP-Mix.Q4_K_S.gguf | Q4_K_S | 1.87GB |
| Qwen2.5-3B-RP-Mix.Q4_K.gguf | Q4_K | 1.96GB |
| Qwen2.5-3B-RP-Mix.Q4_K_M.gguf | Q4_K_M | 1.96GB |
| Qwen2.5-3B-RP-Mix.Q4_1.gguf | Q4_1 | 2.04GB |
| Qwen2.5-3B-RP-Mix.Q5_0.gguf | Q5_0 | 2.22GB |
| Qwen2.5-3B-RP-Mix.Q5_K_S.gguf | Q5_K_S | 2.22GB |
| Qwen2.5-3B-RP-Mix.Q5_K.gguf | Q5_K | 2.27GB |
| Qwen2.5-3B-RP-Mix.Q5_K_M.gguf | Q5_K_M | 2.27GB |
| Qwen2.5-3B-RP-Mix.Q5_1.gguf | Q5_1 | 2.4GB |
| Qwen2.5-3B-RP-Mix.Q6_K.gguf | Q6_K | 2.6GB |
| Qwen2.5-3B-RP-Mix.Q8_0.gguf | Q8_0 | 3.37GB |
library_name: transformers tags:
This is a merge of pre-trained language models created using mergekit.
This model was merged using the passthrough merge method using Qwen/Qwen2.5-3B-Instruct + bunnycore/Qwen-2.5-3b-Rp-lora_model as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
base_model: Qwen/Qwen2.5-3B-Instruct+bunnycore/Qwen-2.5-3b-Rp-lora_model
dtype: bfloat16
merge_method: passthrough
models:
- model: Qwen/Qwen2.5-3B-Instruct+bunnycore/Qwen-2.5-3b-Rp-lora_model
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 23.15 |
| IFEval (0-Shot) | 57.21 |
| BBH (3-Shot) | 28.31 |
| MATH Lvl 5 (4-Shot) | 7.40 |
| GPQA (0-shot) | 3.13 |
| MuSR (0-shot) | 12.56 |
| MMLU-PRO (5-shot) | 30.31 |