Downloads · 30 days
55
2% of all-time downloads
RichardErkhov/bunnycore_-_Qwen-2.5-3b-RP-gguf
bunnycore_-_Qwen-2.5-3b-RP-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
55
2% of all-time downloads
All-time downloads
2.3K
Public
Repo size
39.7 GB
Likes
0
Public
Click a slice to open those files.
.gguf46 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Qwen-2.5-3b-RP - GGUF
| Name | Quant method | Size |
|---|---|---|
| Qwen-2.5-3b-RP.Q2_K.gguf | Q2_K | 1.28GB |
| Qwen-2.5-3b-RP.IQ3_XS.gguf | IQ3_XS | 1.42GB |
| Qwen-2.5-3b-RP.IQ3_S.gguf | IQ3_S | 1.48GB |
| Qwen-2.5-3b-RP.Q3_K_S.gguf | Q3_K_S | 1.48GB |
| Qwen-2.5-3b-RP.IQ3_M.gguf | IQ3_M | 1.51GB |
| Qwen-2.5-3b-RP.Q3_K.gguf | Q3_K | 1.61GB |
| Qwen-2.5-3b-RP.Q3_K_M.gguf | Q3_K_M | 1.61GB |
| Qwen-2.5-3b-RP.Q3_K_L.gguf | Q3_K_L | 1.71GB |
| Qwen-2.5-3b-RP.IQ4_XS.gguf | IQ4_XS | 1.79GB |
| Qwen-2.5-3b-RP.Q4_0.gguf | Q4_0 | 1.86GB |
| Qwen-2.5-3b-RP.IQ4_NL.gguf | IQ4_NL | 1.87GB |
| Qwen-2.5-3b-RP.Q4_K_S.gguf | Q4_K_S | 1.87GB |
| Qwen-2.5-3b-RP.Q4_K.gguf | Q4_K | 1.96GB |
| Qwen-2.5-3b-RP.Q4_K_M.gguf | Q4_K_M | 1.96GB |
| Qwen-2.5-3b-RP.Q4_1.gguf | Q4_1 | 2.04GB |
| Qwen-2.5-3b-RP.Q5_0.gguf | Q5_0 | 2.22GB |
| Qwen-2.5-3b-RP.Q5_K_S.gguf | Q5_K_S | 2.22GB |
| Qwen-2.5-3b-RP.Q5_K.gguf | Q5_K | 2.27GB |
| Qwen-2.5-3b-RP.Q5_K_M.gguf | Q5_K_M | 2.27GB |
| Qwen-2.5-3b-RP.Q5_1.gguf | Q5_1 | 2.4GB |
| Qwen-2.5-3b-RP.Q6_K.gguf | Q6_K | 2.6GB |
| Qwen-2.5-3b-RP.Q8_0.gguf | Q8_0 | 3.37GB |
base_model:
This is a merge of pre-trained language models created using mergekit.
This model was merged using the DARE TIES merge method using Replete-AI/Replete-LLM-V2.5-Qwen-3b as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: Replete-AI/Replete-LLM-V2.5-Qwen-3b+bunnycore/qwen-2.5-3b-lora_model
parameters:
density: 0.5
weight: 0.5
- model: unsloth/Qwen2.5-3B-Instruct+bunnycore/qwen-2.5-3b-lora_model
parameters:
density: 0.5
weight: 0.5
merge_method: dare_ties
base_model: Replete-AI/Replete-LLM-V2.5-Qwen-3b
parameters:
normalize: false
int8_mask: true
dtype: float16