Downloads · 30 days
25
10% of all-time downloads
Meta-Llama-3-11.5B
mpasila/Meta-Llama-3-11.5B
Meta-Llama-3-11.5B is a text generation model from mpasila. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as llama3.
This is a merge of pre-trained language models created using mergekit.
All-time downloads
246
Public
Parameters
11.5B
23 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors23 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- llama3
- Model type
- llama
- Access
- Public
- Created
- Apr 19, 2024
- Updated
- May 7, 2024
- SHA
- b702a23b
Try a prompt
Base models
Model card
From the Hugging Face model README
Meta-Llama-3-11.5B
This is a merge of pre-trained language models created using mergekit.
I had this idea at night that it would make sense to make a frankenmerge of Llama 3.. since we didn't get a 13B or 34B versions this time..
Here's the same thing but for the instruct model: mpasila/Meta-Llama-3-11.5B-Instruct
Merge Details
Merge Method
This model was merged using the passthrough merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: Undi95/Meta-Llama-3-8B-hf
layer_range: [0, 24]
- sources:
- model: Undi95/Meta-Llama-3-8B-hf
layer_range: [8, 32]
merge_method: passthrough
dtype: bfloat16
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- llama3
- Languages
- en
- Created
- Apr 19, 2024
- Updated
- May 7, 2024