KnutJaegersberg_-_Deacon-34B-gguf

RichardErkhov/KnutJaegersberg_-_Deacon-34B-gguf

KnutJaegersberg_-_Deacon-34B-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

5% of all-time downloads

All-time downloads

374

Public

Repo size

389 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf451 GB · 100%

At a glance

Access: Public
Created: Sep 25, 2024
Updated: Sep 26, 2024
SHA: fc4ffdf5

Model card

From the Hugging Face model README

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Deacon-34B - GGUF

Model creator: https://huggingface.co/KnutJaegersberg/
Original model: https://huggingface.co/KnutJaegersberg/Deacon-34B/

Name	Quant method	Size
Deacon-34B.Q2_K.gguf	Q2_K	11.94GB
Deacon-34B.IQ3_XS.gguf	IQ3_XS	13.26GB
Deacon-34B.IQ3_S.gguf	IQ3_S	13.99GB
Deacon-34B.Q3_K_S.gguf	Q3_K_S	13.93GB
Deacon-34B.IQ3_M.gguf	IQ3_M	14.5GB
Deacon-34B.Q3_K.gguf	Q3_K	15.51GB
Deacon-34B.Q3_K_M.gguf	Q3_K_M	15.51GB
Deacon-34B.Q3_K_L.gguf	Q3_K_L	16.89GB
Deacon-34B.IQ4_XS.gguf	IQ4_XS	17.36GB
Deacon-34B.Q4_0.gguf	Q4_0	18.13GB
Deacon-34B.IQ4_NL.gguf	IQ4_NL	18.3GB
Deacon-34B.Q4_K_S.gguf	Q4_K_S	18.25GB
Deacon-34B.Q4_K.gguf	Q4_K	19.24GB
Deacon-34B.Q4_K_M.gguf	Q4_K_M	19.24GB
Deacon-34B.Q4_1.gguf	Q4_1	20.1GB
Deacon-34B.Q5_0.gguf	Q5_0	22.08GB
Deacon-34B.Q5_K_S.gguf	Q5_K_S	22.08GB
Deacon-34B.Q5_K.gguf	Q5_K	22.65GB
Deacon-34B.Q5_K_M.gguf	Q5_K_M	22.65GB
Deacon-34B.Q5_1.gguf	Q5_1	24.05GB
Deacon-34B.Q6_K.gguf	Q6_K	26.28GB
Deacon-34B.Q8_0.gguf	Q8_0	34.03GB

Original model description:

pipeline_tag: text-generation datasets:

totally-not-an-llm/EverythingLM-data-V3 license: apache-2.0

This model has been llamafied and uses a llama tokenizer. I took it from https://huggingface.co/chargoddard/Yi-34B-Llama It's fine tuned on EverythingLM dataset for 5 epochs with NEFTune. If you want to understand the pun of the model name, you gotta look at the 3b version of it.

License The Yi series models are fully open for academic research and free commercial usage with permission via applications. All usage must adhere to the Model License Agreement 2.0. To apply for the official commercial license, please contact us ([email protected]).

Prompt Example:

### System:

You are an AI assistant. User will give you a task. Your goal is to complete the task as faithfully as you can. While performing the task think step-by-step and justify your steps.

### Instruction: 

How do you fine tune a large language model? 

### Response:

Created: Sep 25, 2024
Updated: Sep 26, 2024