chlee10_-_T3Q-MSlerp-7Bx2-gguf

RichardErkhov/chlee10_-_T3Q-MSlerp-7Bx2-gguf

chlee10_-_T3Q-MSlerp-7Bx2-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

8% of all-time downloads

All-time downloads

437

Public

Repo size

146 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf169 GB · 100%

At a glance

Access: Public
Created: Sep 13, 2024
Updated: Sep 13, 2024
SHA: e18467db

Model card

From the Hugging Face model README

Quantization made by Richard Erkhov.

Github

Discord

Request more models

T3Q-MSlerp-7Bx2 - GGUF

Model creator: https://huggingface.co/chlee10/
Original model: https://huggingface.co/chlee10/T3Q-MSlerp-7Bx2/

Name	Quant method	Size
T3Q-MSlerp-7Bx2.Q2_K.gguf	Q2_K	4.43GB
T3Q-MSlerp-7Bx2.IQ3_XS.gguf	IQ3_XS	4.95GB
T3Q-MSlerp-7Bx2.IQ3_S.gguf	IQ3_S	5.22GB
T3Q-MSlerp-7Bx2.Q3_K_S.gguf	Q3_K_S	5.2GB
T3Q-MSlerp-7Bx2.IQ3_M.gguf	IQ3_M	5.35GB
T3Q-MSlerp-7Bx2.Q3_K.gguf	Q3_K	5.78GB
T3Q-MSlerp-7Bx2.Q3_K_M.gguf	Q3_K_M	5.78GB
T3Q-MSlerp-7Bx2.Q3_K_L.gguf	Q3_K_L	6.27GB
T3Q-MSlerp-7Bx2.IQ4_XS.gguf	IQ4_XS	6.5GB
T3Q-MSlerp-7Bx2.Q4_0.gguf	Q4_0	6.78GB
T3Q-MSlerp-7Bx2.IQ4_NL.gguf	IQ4_NL	6.85GB
T3Q-MSlerp-7Bx2.Q4_K_S.gguf	Q4_K_S	6.84GB
T3Q-MSlerp-7Bx2.Q4_K.gguf	Q4_K	7.25GB
T3Q-MSlerp-7Bx2.Q4_K_M.gguf	Q4_K_M	7.25GB
T3Q-MSlerp-7Bx2.Q4_1.gguf	Q4_1	7.52GB
T3Q-MSlerp-7Bx2.Q5_0.gguf	Q5_0	8.26GB
T3Q-MSlerp-7Bx2.Q5_K_S.gguf	Q5_K_S	8.26GB
T3Q-MSlerp-7Bx2.Q5_K.gguf	Q5_K	8.51GB
T3Q-MSlerp-7Bx2.Q5_K_M.gguf	Q5_K_M	8.51GB
T3Q-MSlerp-7Bx2.Q5_1.gguf	Q5_1	9.01GB
T3Q-MSlerp-7Bx2.Q6_K.gguf	Q6_K	9.84GB
T3Q-MSlerp-7Bx2.Q8_0.gguf	Q8_0	12.75GB

Original model description:

library_name: transformers license: apache-2.0

T3Q-MSlerp-7Bx2

T3Q-MSlerp-7Bx2 is a merge of the following models using mergekit:

Model Developers Chihoon Lee(chlee10), T3Q

  
  slices:
      - sources:
        - model: zhengr/MixTAO-7Bx2-MoE-v8.1
          layer_range: [0, 32]
        - model: yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
          layer_range: [0, 32]
  
  merge_method: slerp
  base_model: zhengr/MixTAO-7Bx2-MoE-v8.1
  
  parameters:
   t:
      - filter: self_attn
        value: [0, 0.5, 0.3, 0.7, 1]
      - filter: mlp
        value: [1, 0.5, 0.7, 0.3, 0]
      - value: 0.5 # fallback for rest of tensors
      
  dtype: float16

Created: Sep 13, 2024
Updated: Sep 13, 2024