Downloads · 30 days
45
1% of all-time downloads
Replete-AI_-_Llama-3-11.5B-V2-gguf
RichardErkhov/Replete-AI_-_Llama-3-11.5B-V2-gguf
Replete-AI_-_Llama-3-11.5B-V2-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.
All-time downloads
3.1K
Public
Repo size
132 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf153 GB · 100%
At a glance
- Access
- Public
- Created
- Jul 4, 2024
- Updated
- Jul 4, 2024
- SHA
- 401551cd
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Llama-3-11.5B-V2 - GGUF
- Model creator: https://huggingface.co/Replete-AI/
- Original model: https://huggingface.co/Replete-AI/Llama-3-11.5B-V2/
| Name | Quant method | Size |
|---|---|---|
| Llama-3-11.5B-V2.Q2_K.gguf | Q2_K | 4.16GB |
| Llama-3-11.5B-V2.IQ3_XS.gguf | IQ3_XS | 4.61GB |
| Llama-3-11.5B-V2.IQ3_S.gguf | IQ3_S | 4.83GB |
| Llama-3-11.5B-V2.Q3_K_S.gguf | Q3_K_S | 4.81GB |
| Llama-3-11.5B-V2.IQ3_M.gguf | IQ3_M | 4.98GB |
| Llama-3-11.5B-V2.Q3_K.gguf | Q3_K | 5.3GB |
| Llama-3-11.5B-V2.Q3_K_M.gguf | Q3_K_M | 5.3GB |
| Llama-3-11.5B-V2.Q3_K_L.gguf | Q3_K_L | 5.73GB |
| Llama-3-11.5B-V2.IQ4_XS.gguf | IQ4_XS | 5.93GB |
| Llama-3-11.5B-V2.Q4_0.gguf | Q4_0 | 6.17GB |
| Llama-3-11.5B-V2.IQ4_NL.gguf | IQ4_NL | 6.23GB |
| Llama-3-11.5B-V2.Q4_K_S.gguf | Q4_K_S | 6.21GB |
| Llama-3-11.5B-V2.Q4_K.gguf | Q4_K | 6.53GB |
| Llama-3-11.5B-V2.Q4_K_M.gguf | Q4_K_M | 6.53GB |
| Llama-3-11.5B-V2.Q4_1.gguf | Q4_1 | 6.81GB |
| Llama-3-11.5B-V2.Q5_0.gguf | Q5_0 | 7.45GB |
| Llama-3-11.5B-V2.Q5_K_S.gguf | Q5_K_S | 7.45GB |
| Llama-3-11.5B-V2.Q5_K.gguf | Q5_K | 7.64GB |
| Llama-3-11.5B-V2.Q5_K_M.gguf | Q5_K_M | 7.64GB |
| Llama-3-11.5B-V2.Q5_1.gguf | Q5_1 | 8.09GB |
| Llama-3-11.5B-V2.Q6_K.gguf | Q6_K | 8.81GB |
| Llama-3-11.5B-V2.Q8_0.gguf | Q8_0 | 11.41GB |
Original model description:
license: other license_name: llama-3 license_link: https://llama.meta.com/llama3/license/
Llama-3-11.5B-v2
Thank you to Meta for the weights for Meta-Llama-3-8B
This is an upscaling of the Meta-Llama-3-8B Ai using techniques created for chargoddard/mistral-11b-slimorca. This Ai model has been upscaled from 8b parameters to 11.5b parameters without any continuous pretraining or fine-tuning.
Unlike version 1 this model has no issues at fp16 or any quantizations.
The model that was used to create this one is linked below:
- Created
- Jul 4, 2024
- Updated
- Jul 4, 2024