RichardErkhov
/

Q-bert_-_Terminis-7B-gguf

Model card Files Files and versions

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Request more models

Terminis-7B - GGUF

Model creator: https://huggingface.co/Q-bert/
Original model: https://huggingface.co/Q-bert/Terminis-7B/

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

Original model description:

license: apache-2.0 language: - en pipeline_tag: text-generation tags: - merge

Terminis-7B

Merge v1olet/v1olet_marcoroni-go-bruins-merge-7B and mistralai/Mistral-7B-Instruct-v0.2 using slerp merge.

You can use ChatML and Alpaca format.

Open LLM Leaderboard Evaluation Results

Detailed results can be found Coming soon

Metric	Value
Avg.	Coming soon
ARC (25-shot)	Coming soon
HellaSwag (10-shot)	Coming soon
MMLU (5-shot)	Coming soon
TruthfulQA (0-shot)	Coming soon
Winogrande (5-shot)	Coming soon
GSM8K (5-shot)	Coming soon

Downloads last month: 25

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

Log In to add your hardware

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support