Downloads · 30 days
88
6% of all-time downloads
RichardErkhov/ehristoforu_-_mllama-3.1-8b-it-gguf
ehristoforu_-_mllama-3.1-8b-it-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
88
6% of all-time downloads
All-time downloads
1.4K
Public
Repo size
92.9 GB
Likes
0
Public
Click a slice to open those files.
.gguf108 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
mllama-3.1-8b-it - GGUF
| Name | Quant method | Size |
|---|---|---|
| mllama-3.1-8b-it.Q2_K.gguf | Q2_K | 2.96GB |
| mllama-3.1-8b-it.IQ3_XS.gguf | IQ3_XS | 3.28GB |
| mllama-3.1-8b-it.IQ3_S.gguf | IQ3_S | 3.43GB |
| mllama-3.1-8b-it.Q3_K_S.gguf | Q3_K_S | 3.41GB |
| mllama-3.1-8b-it.IQ3_M.gguf | IQ3_M | 3.52GB |
| mllama-3.1-8b-it.Q3_K.gguf | Q3_K | 3.74GB |
| mllama-3.1-8b-it.Q3_K_M.gguf | Q3_K_M | 3.74GB |
| mllama-3.1-8b-it.Q3_K_L.gguf | Q3_K_L | 4.03GB |
| mllama-3.1-8b-it.IQ4_XS.gguf | IQ4_XS | 4.18GB |
| mllama-3.1-8b-it.Q4_0.gguf | Q4_0 | 4.34GB |
| mllama-3.1-8b-it.IQ4_NL.gguf | IQ4_NL | 4.38GB |
| mllama-3.1-8b-it.Q4_K_S.gguf | Q4_K_S | 4.37GB |
| mllama-3.1-8b-it.Q4_K.gguf | Q4_K | 4.58GB |
| mllama-3.1-8b-it.Q4_K_M.gguf | Q4_K_M | 4.58GB |
| mllama-3.1-8b-it.Q4_1.gguf | Q4_1 | 4.78GB |
| mllama-3.1-8b-it.Q5_0.gguf | Q5_0 | 5.21GB |
| mllama-3.1-8b-it.Q5_K_S.gguf | Q5_K_S | 5.21GB |
| mllama-3.1-8b-it.Q5_K.gguf | Q5_K | 5.34GB |
| mllama-3.1-8b-it.Q5_K_M.gguf | Q5_K_M | 5.34GB |
| mllama-3.1-8b-it.Q5_1.gguf | Q5_1 | 5.65GB |
| mllama-3.1-8b-it.Q6_K.gguf | Q6_K | 6.14GB |
| mllama-3.1-8b-it.Q8_0.gguf | Q8_0 | 7.95GB |
base_model:
This is a merge of pre-trained language models created using mergekit.
This model was merged using the TIES merge method using unsloth/Meta-Llama-3.1-8B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: unsloth/Meta-Llama-3.1-8B
#no parameters necessary for base model
- model: NousResearch/Hermes-3-Llama-3.1-8B
parameters:
density: 0.5
weight: 0.5
- model: Skywork/Skywork-o1-Open-Llama-3.1-8B
parameters:
density: 0.5
weight: 0.5
- model: arcee-ai/Llama-3.1-SuperNova-Lite
parameters:
density: 0.5
weight: 0.5
- model: cognitivecomputations/dolphin-2.9.4-llama3.1-8b
parameters:
density: 0.5
weight: 0.5
- model: SimpleBerry/LLaMA-O1-Base-1127
parameters:
density: 0.5
weight: 0.5
merge_method: ties
base_model: unsloth/Meta-Llama-3.1-8B
parameters:
normalize: false
int8_mask: true
dtype: bfloat16