Alphacode-AI_-_Alphacode-MALI-11B-gguf

RichardErkhov/Alphacode-AI_-_Alphacode-MALI-11B-gguf

Alphacode-AI_-_Alphacode-MALI-11B-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

7% of all-time downloads

All-time downloads

1.3K

Public

Repo size

124 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf144 GB · 100%

At a glance

Access: Public
Created: Jul 2, 2024
Updated: Jul 3, 2024
SHA: bd2425eb

Model card

From the Hugging Face model README

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Alphacode-MALI-11B - GGUF

Model creator: https://huggingface.co/Alphacode-AI/
Original model: https://huggingface.co/Alphacode-AI/Alphacode-MALI-11B/

Name	Quant method	Size
Alphacode-MALI-11B.Q2_K.gguf	Q2_K	3.8GB
Alphacode-MALI-11B.IQ3_XS.gguf	IQ3_XS	4.23GB
Alphacode-MALI-11B.IQ3_S.gguf	IQ3_S	4.46GB
Alphacode-MALI-11B.Q3_K_S.gguf	Q3_K_S	4.43GB
Alphacode-MALI-11B.IQ3_M.gguf	IQ3_M	4.6GB
Alphacode-MALI-11B.Q3_K.gguf	Q3_K	4.94GB
Alphacode-MALI-11B.Q3_K_M.gguf	Q3_K_M	4.94GB
Alphacode-MALI-11B.Q3_K_L.gguf	Q3_K_L	5.37GB
Alphacode-MALI-11B.IQ4_XS.gguf	IQ4_XS	5.54GB
Alphacode-MALI-11B.Q4_0.gguf	Q4_0	5.77GB
Alphacode-MALI-11B.IQ4_NL.gguf	IQ4_NL	5.83GB
Alphacode-MALI-11B.Q4_K_S.gguf	Q4_K_S	5.81GB
Alphacode-MALI-11B.Q4_K.gguf	Q4_K	6.15GB
Alphacode-MALI-11B.Q4_K_M.gguf	Q4_K_M	6.15GB
Alphacode-MALI-11B.Q4_1.gguf	Q4_1	6.4GB
Alphacode-MALI-11B.Q5_0.gguf	Q5_0	7.03GB
Alphacode-MALI-11B.Q5_K_S.gguf	Q5_K_S	7.03GB
Alphacode-MALI-11B.Q5_K.gguf	Q5_K	7.22GB
Alphacode-MALI-11B.Q5_K_M.gguf	Q5_K_M	7.22GB
Alphacode-MALI-11B.Q5_1.gguf	Q5_1	7.66GB
Alphacode-MALI-11B.Q6_K.gguf	Q6_K	8.37GB
Alphacode-MALI-11B.Q8_0.gguf	Q8_0	10.84GB

Original model description:

license: cc-by-4.0 language:

ko pipeline_tag: text-generation tags:
merge

mali

MALI-11B (Model with Auto Learning Ideation) is a merge version of Alphacode's Models that has been fine-tuned with Our In House CustomData.

Train Spec : We utilized an A100x8 for training our model with DeepSpeed / HuggingFace TRL Trainer / HuggingFace Accelerate

Contact : Alphacode Co. [https://alphacode.ai/]

Created: Jul 2, 2024
Updated: Jul 3, 2024