Quantization made by Richard Erkhov.

L3-8B-Helium3-baseLlama - GGUF

Model creator: https://huggingface.co/inflatebot/
Original model: https://huggingface.co/inflatebot/L3-8B-Helium3-baseLlama/

Name	Quant method	Size
L3-8B-Helium3-baseLlama.Q2_K.gguf	Q2_K	2.96GB
L3-8B-Helium3-baseLlama.IQ3_XS.gguf	IQ3_XS	3.28GB
L3-8B-Helium3-baseLlama.IQ3_S.gguf	IQ3_S	3.43GB
L3-8B-Helium3-baseLlama.Q3_K_S.gguf	Q3_K_S	3.41GB
L3-8B-Helium3-baseLlama.IQ3_M.gguf	IQ3_M	3.52GB
L3-8B-Helium3-baseLlama.Q3_K.gguf	Q3_K	3.74GB
L3-8B-Helium3-baseLlama.Q3_K_M.gguf	Q3_K_M	3.74GB
L3-8B-Helium3-baseLlama.Q3_K_L.gguf	Q3_K_L	4.03GB
L3-8B-Helium3-baseLlama.IQ4_XS.gguf	IQ4_XS	4.18GB
L3-8B-Helium3-baseLlama.Q4_0.gguf	Q4_0	4.34GB
L3-8B-Helium3-baseLlama.IQ4_NL.gguf	IQ4_NL	4.38GB
L3-8B-Helium3-baseLlama.Q4_K_S.gguf	Q4_K_S	4.37GB
L3-8B-Helium3-baseLlama.Q4_K.gguf	Q4_K	4.58GB
L3-8B-Helium3-baseLlama.Q4_K_M.gguf	Q4_K_M	4.58GB
L3-8B-Helium3-baseLlama.Q4_1.gguf	Q4_1	4.78GB
L3-8B-Helium3-baseLlama.Q5_0.gguf	Q5_0	5.21GB
L3-8B-Helium3-baseLlama.Q5_K_S.gguf	Q5_K_S	5.21GB
L3-8B-Helium3-baseLlama.Q5_K.gguf	Q5_K	5.34GB
L3-8B-Helium3-baseLlama.Q5_K_M.gguf	Q5_K_M	5.34GB
L3-8B-Helium3-baseLlama.Q5_1.gguf	Q5_1	5.65GB
L3-8B-Helium3-baseLlama.Q6_K.gguf	Q6_K	6.14GB
L3-8B-Helium3-baseLlama.Q8_0.gguf	Q8_0	7.95GB

Original model description:

base_model:

NousResearch/Meta-Llama-3-8B
inflatebot/helide-beta-r1
inflatebot/helide-beta-r0
inflatebot/helide-beta-r4 library_name: transformers tags:
mergekit
merge

helium-3-r2

This is a merge of pre-trained language models created using mergekit.

Merge Details

Helium3, but the base model is Llama-3. Ended up being too dry, but if He3's too horny for you, try this one.

GGUFs by mradermacher

Merge Method

This model was merged using the Model Stock merge method using NousResearch/Meta-Llama-3-8B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: inflatebot/helide-beta-r4
  - model: inflatebot/helide-beta-r1
  - model: inflatebot/helide-beta-r0

merge_method: model_stock
base_model: NousResearch/Meta-Llama-3-8B
dtype: bfloat16