You can deploy this model and start earning money today!

RichardErkhov/
EmbeddedLLM_-_Mistral-7B-Merge-14-v0.2-gguf

Name: EmbeddedLLM_-_Mistral-7B-Merge-14-v0.2-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Mistral-7B-Merge-14-v0.2 - GGUF

Model creator: https://huggingface.co/EmbeddedLLM/
Original model: https://huggingface.co/EmbeddedLLM/Mistral-7B-Merge-14-v0.2/

Name	Quant method	Size
Mistral-7B-Merge-14-v0.2.Q2_K.gguf	Q2_K	2.53GB
Mistral-7B-Merge-14-v0.2.IQ3_XS.gguf	IQ3_XS	2.81GB
Mistral-7B-Merge-14-v0.2.IQ3_S.gguf	IQ3_S	2.96GB
Mistral-7B-Merge-14-v0.2.Q3_K_S.gguf	Q3_K_S	2.95GB
Mistral-7B-Merge-14-v0.2.IQ3_M.gguf	IQ3_M	3.06GB
Mistral-7B-Merge-14-v0.2.Q3_K.gguf	Q3_K	3.28GB
Mistral-7B-Merge-14-v0.2.Q3_K_M.gguf	Q3_K_M	3.28GB
Mistral-7B-Merge-14-v0.2.Q3_K_L.gguf	Q3_K_L	3.56GB
Mistral-7B-Merge-14-v0.2.IQ4_XS.gguf	IQ4_XS	3.67GB
Mistral-7B-Merge-14-v0.2.Q4_0.gguf	Q4_0	3.83GB
Mistral-7B-Merge-14-v0.2.IQ4_NL.gguf	IQ4_NL	3.87GB
Mistral-7B-Merge-14-v0.2.Q4_K_S.gguf	Q4_K_S	3.86GB
Mistral-7B-Merge-14-v0.2.Q4_K.gguf	Q4_K	4.07GB
Mistral-7B-Merge-14-v0.2.Q4_K_M.gguf	Q4_K_M	4.07GB
Mistral-7B-Merge-14-v0.2.Q4_1.gguf	Q4_1	4.24GB
Mistral-7B-Merge-14-v0.2.Q5_0.gguf	Q5_0	4.65GB
Mistral-7B-Merge-14-v0.2.Q5_K_S.gguf	Q5_K_S	4.65GB
Mistral-7B-Merge-14-v0.2.Q5_K.gguf	Q5_K	4.78GB
Mistral-7B-Merge-14-v0.2.Q5_K_M.gguf	Q5_K_M	4.78GB
Mistral-7B-Merge-14-v0.2.Q5_1.gguf	Q5_1	5.07GB
Mistral-7B-Merge-14-v0.2.Q6_K.gguf	Q6_K	5.53GB
Mistral-7B-Merge-14-v0.2.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: cc-by-nc-4.0 language:

en tags:
merge base_model:
janai-hq/trinity-v1
EmbeddedLLM/Mistral-7B-Merge-14-v0

Update 2023-12-19

In light of dataset contamination issue among the merged models raised by the community in recent days, in particular berkeley-nest/Starling-LM-7B-alpha, Q-bert/MetaMath-Cybertron-Starling, and janai-hq/trinity-v1, we decided to remake another model without the models mentioned. Additionally, their CC-by-NC-4.0 license is restrictive and thus are not suitable for an open model.

Open LLM Leaderboard

For reference, this model obtained an average score of 72.88.

Average	72.88
ARC	68.86
HellaSwag	87.01
MMLU	65.05
TruthfulQA	64.19
Winogrande	81.69
GSM8K	70.51

Model Description

This is an experiment to test merging 14 models using DARE TIES 🦙

The merged model is then merged again with janai-hq/trinity-v1 using Gradient SLERP. The result is a base model that performs quite well but requires some further instruction fine-tuning.

The 14 models are as follows:

base model: mistralai/Mistral-7B-v0.1

The yaml config file for this model is here:

yaml

slices:
  - sources:
      - model: janai-hq/trinity-v1
        layer_range: [0, 32]
      - model: EmbeddedLLM/Mistral-7B-Merge-14-v0
        layer_range: [0, 32]
merge_method: slerp
base_model: janai-hq/trinity-v1
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
dtype: bfloat16

RichardErkhov/EmbeddedLLM_-_Mistral-7B-Merge-14-v0.2-gguf

Original model description:

Update 2023-12-19

Open LLM Leaderboard

Model Description

RichardErkhov/
EmbeddedLLM_-_Mistral-7B-Merge-14-v0.2-gguf