Quantization made by Richard Erkhov.
L3.1-IFEvalStock-8B - GGUF
- Model creator: https://huggingface.co/rityak/
- Original model: https://huggingface.co/rityak/L3.1-IFEvalStock-8B/
| Name | Quant method | Size |
|---|---|---|
| L3.1-IFEvalStock-8B.Q2_K.gguf | Q2_K | 2.96GB |
| L3.1-IFEvalStock-8B.IQ3_XS.gguf | IQ3_XS | 3.28GB |
| L3.1-IFEvalStock-8B.IQ3_S.gguf | IQ3_S | 3.43GB |
| L3.1-IFEvalStock-8B.Q3_K_S.gguf | Q3_K_S | 3.41GB |
| L3.1-IFEvalStock-8B.IQ3_M.gguf | IQ3_M | 3.52GB |
| L3.1-IFEvalStock-8B.Q3_K.gguf | Q3_K | 3.74GB |
| L3.1-IFEvalStock-8B.Q3_K_M.gguf | Q3_K_M | 3.74GB |
| L3.1-IFEvalStock-8B.Q3_K_L.gguf | Q3_K_L | 4.03GB |
| L3.1-IFEvalStock-8B.IQ4_XS.gguf | IQ4_XS | 4.18GB |
| L3.1-IFEvalStock-8B.Q4_0.gguf | Q4_0 | 4.34GB |
| L3.1-IFEvalStock-8B.IQ4_NL.gguf | IQ4_NL | 4.38GB |
| L3.1-IFEvalStock-8B.Q4_K_S.gguf | Q4_K_S | 4.37GB |
| L3.1-IFEvalStock-8B.Q4_K.gguf | Q4_K | 4.58GB |
| L3.1-IFEvalStock-8B.Q4_K_M.gguf | Q4_K_M | 4.58GB |
| L3.1-IFEvalStock-8B.Q4_1.gguf | Q4_1 | 4.78GB |
| L3.1-IFEvalStock-8B.Q5_0.gguf | Q5_0 | 5.21GB |
| L3.1-IFEvalStock-8B.Q5_K_S.gguf | Q5_K_S | 5.21GB |
| L3.1-IFEvalStock-8B.Q5_K.gguf | Q5_K | 5.34GB |
| L3.1-IFEvalStock-8B.Q5_K_M.gguf | Q5_K_M | 5.34GB |
| L3.1-IFEvalStock-8B.Q5_1.gguf | Q5_1 | 5.65GB |
| L3.1-IFEvalStock-8B.Q6_K.gguf | Q6_K | 6.14GB |
| L3.1-IFEvalStock-8B.Q8_0.gguf | Q8_0 | 7.95GB |
Original model description:
base_model:
- arcee-ai/Llama-Spark
- haoranxu/Llama-3-Instruct-8B-SimPO
- vicgalle/Configurable-Llama-3.1-8B-Instruct
- Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
- VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct library_name: transformers tags:
- mergekit
- merge
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the Model Stock merge method using Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 as a base.
Models Merged
The following models were included in the merge:
- arcee-ai/Llama-Spark
- haoranxu/Llama-3-Instruct-8B-SimPO
- vicgalle/Configurable-Llama-3.1-8B-Instruct
- VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct
Configuration
The following YAML configuration was used to produce this model:
models:
- model: VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct
- model: vicgalle/Configurable-Llama-3.1-8B-Instruct
- model: arcee-ai/Llama-Spark
- model: haoranxu/Llama-3-Instruct-8B-SimPO
merge_method: model_stock
base_model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
normalize: true
int8_mask: true
dtype: float16