Quantization made by Richard Erkhov.

Github

Discord

Request more models

OpenMia-Indo-Mistral-7b-v3 - GGUF

• Model creator: https://huggingface.co/indischepartij/
• Original model: https://huggingface.co/indischepartij/OpenMia-Indo-Mistral-7b-v3/

Name	Quant method	Size
OpenMia-Indo-Mistral-7b-v3.Q2K.gguf	Q2K	2.53GB
OpenMia-Indo-Mistral-7b-v3.IQ3XS.gguf	IQ3XS	2.81GB
OpenMia-Indo-Mistral-7b-v3.IQ3S.gguf	IQ3S	2.96GB
OpenMia-Indo-Mistral-7b-v3.Q3KS.gguf	Q3K_S	2.95GB
OpenMia-Indo-Mistral-7b-v3.IQ3M.gguf	IQ3M	3.06GB
OpenMia-Indo-Mistral-7b-v3.Q3K.gguf	Q3K	3.28GB
OpenMia-Indo-Mistral-7b-v3.Q3KM.gguf	Q3K_M	3.28GB
OpenMia-Indo-Mistral-7b-v3.Q3KL.gguf	Q3K_L	3.56GB
OpenMia-Indo-Mistral-7b-v3.IQ4XS.gguf	IQ4XS	3.67GB
OpenMia-Indo-Mistral-7b-v3.Q40.gguf	Q40	3.83GB
OpenMia-Indo-Mistral-7b-v3.IQ4NL.gguf	IQ4NL	3.87GB
OpenMia-Indo-Mistral-7b-v3.Q4KS.gguf	Q4K_S	3.86GB
OpenMia-Indo-Mistral-7b-v3.Q4K.gguf	Q4K	4.07GB
OpenMia-Indo-Mistral-7b-v3.Q4KM.gguf	Q4K_M	4.07GB
OpenMia-Indo-Mistral-7b-v3.Q41.gguf	Q41	4.24GB
OpenMia-Indo-Mistral-7b-v3.Q50.gguf	Q50	4.65GB
OpenMia-Indo-Mistral-7b-v3.Q5KS.gguf	Q5K_S	4.65GB
OpenMia-Indo-Mistral-7b-v3.Q5K.gguf	Q5K	4.78GB
OpenMia-Indo-Mistral-7b-v3.Q5KM.gguf	Q5K_M	4.78GB
OpenMia-Indo-Mistral-7b-v3.Q51.gguf	Q51	5.07GB
OpenMia-Indo-Mistral-7b-v3.Q6K.gguf	Q6K	5.53GB
OpenMia-Indo-Mistral-7b-v3.Q80.gguf	Q80	7.17GB

Original model description:

---

language:

• en
• id

license: cc-by-nc-4.0
tags:

• text-generation-inference
• transformers
• mistral
• trl

datasets:

• cahya/alpaca-id-cleaned

base_model: mistral-7b
model-index:

• name: OpenMia-Indo-Mistral-7b-v3

results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
numfewshot: 25
metrics:
- type: acc_norm
value: 66.13
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=gmonsoon/OpenMia-Indo-Mistral-7b-v3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
numfewshot: 10
metrics:
- type: acc_norm
value: 85.47
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=gmonsoon/OpenMia-Indo-Mistral-7b-v3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
numfewshot: 5
metrics:
- type: acc
value: 64.03
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=gmonsoon/OpenMia-Indo-Mistral-7b-v3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
numfewshot: 0
metrics:
- type: mc2
value: 60.05
source:
url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=gmonsoon/OpenMia-Indo-Mistral-7b-v3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
numfewshot: 5
metrics:
- type: acc
value: 82.95
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=gmonsoon/OpenMia-Indo-Mistral-7b-v3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
numfewshot: 5
metrics:
- type: acc
value: 67.63
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=gmonsoon/OpenMia-Indo-Mistral-7b-v3
name: Open LLM Leaderboard

---

!image/png

updated to V3-refined, see: https://huggingface.co/indischepartij/OpenMia-Indo-Mistral-7b-v3-refined

Open LLM Leaderboard

!image/png

MIA : (M)istral finetuned with (I)ndonesia language from (A)lpaca dataset

(formerly named Mistral-7b-Alpaca-Indonesia)

OpenMia-Indo-Mistral-7b-v2 is finetuned model based of Mistral-7b with capability to do conversation in Bahasa Indonesia.

Due to limited resources, this model is still in alpha stage.

Want to contribute to this project? join our organization: https://huggingface.co/indischepartij or contact me at https://twitter.com/gmonsooniii

Modelfile/Prompt format

SYSTEM You are a caring and empathetic sentient AI companion named Mia.

PARAMETER stop <|im_start|> 
PARAMETER stop <|im_end|>

TEMPLATE <|imstart|>system {{ .System }}<|imend|> <|imstart|>user {{ .Prompt }}<|imend|> <|im_start|>assistant

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	71.04
AI2 Reasoning Challenge (25-Shot)	66.13
HellaSwag (10-Shot)	85.47
MMLU (5-Shot)	64.03
TruthfulQA (0-shot)	60.05
Winogrande (5-shot)	82.95
GSM8k (5-shot)	67.63