Downloads · 30 days
84
3% of all-time downloads
RichardErkhov/rityak_-_Qwen2.5-LumenReplete-14B-gguf
rityak_-_Qwen2.5-LumenReplete-14B-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
84
3% of all-time downloads
All-time downloads
3K
Public
Repo size
136 GB
Likes
0
Public
Click a slice to open those files.
.gguf163 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Qwen2.5-LumenReplete-14B - GGUF
| Name | Quant method | Size |
|---|---|---|
| Qwen2.5-LumenReplete-14B.Q2_K.gguf | Q2_K | 5.37GB |
| Qwen2.5-LumenReplete-14B.Q3_K_S.gguf | Q3_K_S | 6.2GB |
| Qwen2.5-LumenReplete-14B.Q3_K.gguf | Q3_K | 6.83GB |
| Qwen2.5-LumenReplete-14B.Q3_K_M.gguf | Q3_K_M | 6.83GB |
| Qwen2.5-LumenReplete-14B.Q3_K_L.gguf | Q3_K_L | 7.38GB |
| Qwen2.5-LumenReplete-14B.IQ4_XS.gguf | IQ4_XS | 7.62GB |
| Qwen2.5-LumenReplete-14B.Q4_0.gguf | Q4_0 | 4.69GB |
| Qwen2.5-LumenReplete-14B.IQ4_NL.gguf | IQ4_NL | 3.2GB |
| Qwen2.5-LumenReplete-14B.Q4_K_S.gguf | Q4_K_S | 3.29GB |
| Qwen2.5-LumenReplete-14B.Q4_K.gguf | Q4_K | 8.37GB |
| Qwen2.5-LumenReplete-14B.Q4_K_M.gguf | Q4_K_M | 8.37GB |
| Qwen2.5-LumenReplete-14B.Q4_1.gguf | Q4_1 | 8.74GB |
| Qwen2.5-LumenReplete-14B.Q5_0.gguf | Q5_0 | 9.56GB |
| Qwen2.5-LumenReplete-14B.Q5_K_S.gguf | Q5_K_S | 9.56GB |
| Qwen2.5-LumenReplete-14B.Q5_K.gguf | Q5_K | 9.78GB |
| Qwen2.5-LumenReplete-14B.Q5_K_M.gguf | Q5_K_M | 9.78GB |
| Qwen2.5-LumenReplete-14B.Q5_1.gguf | Q5_1 | 10.37GB |
| Qwen2.5-LumenReplete-14B.Q6_K.gguf | Q6_K | 11.29GB |
| Qwen2.5-LumenReplete-14B.Q8_0.gguf | Q8_0 | 14.62GB |
base_model:
This is a merge of pre-trained language models created using mergekit.
This model was merged using the linear DARE merge method using Replete-AI/Replete-LLM-V2.5-Qwen-14b as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: v000000/Qwen2.5-Lumen-14B
parameters:
weight: 1.2
base_model: Replete-AI/Replete-LLM-V2.5-Qwen-14b
parameters:
normalize: false
int8_mask: true
merge_method: dare_linear
dtype: float32
out_dtype: bfloat16
tokenizer_source: base