You can deploy this model and start earning money today!

RichardErkhov/
indischepartij_-_OpenMia-Indo-Mistral-7b-v3-refined-gguf

Name: indischepartij_-_OpenMia-Indo-Mistral-7b-v3-refined-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

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

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

Name	Quant method	Size
OpenMia-Indo-Mistral-7b-v3-refined.Q2_K.gguf	Q2_K	2.53GB
OpenMia-Indo-Mistral-7b-v3-refined.IQ3_XS.gguf	IQ3_XS	2.81GB
OpenMia-Indo-Mistral-7b-v3-refined.IQ3_S.gguf	IQ3_S	2.96GB
OpenMia-Indo-Mistral-7b-v3-refined.Q3_K_S.gguf	Q3_K_S	2.95GB
OpenMia-Indo-Mistral-7b-v3-refined.IQ3_M.gguf	IQ3_M	3.06GB
OpenMia-Indo-Mistral-7b-v3-refined.Q3_K.gguf	Q3_K	3.28GB
OpenMia-Indo-Mistral-7b-v3-refined.Q3_K_M.gguf	Q3_K_M	3.28GB
OpenMia-Indo-Mistral-7b-v3-refined.Q3_K_L.gguf	Q3_K_L	3.56GB
OpenMia-Indo-Mistral-7b-v3-refined.IQ4_XS.gguf	IQ4_XS	3.67GB
OpenMia-Indo-Mistral-7b-v3-refined.Q4_0.gguf	Q4_0	3.83GB
OpenMia-Indo-Mistral-7b-v3-refined.IQ4_NL.gguf	IQ4_NL	3.87GB
OpenMia-Indo-Mistral-7b-v3-refined.Q4_K_S.gguf	Q4_K_S	3.86GB
OpenMia-Indo-Mistral-7b-v3-refined.Q4_K.gguf	Q4_K	4.07GB
OpenMia-Indo-Mistral-7b-v3-refined.Q4_K_M.gguf	Q4_K_M	4.07GB
OpenMia-Indo-Mistral-7b-v3-refined.Q4_1.gguf	Q4_1	4.24GB
OpenMia-Indo-Mistral-7b-v3-refined.Q5_0.gguf	Q5_0	4.65GB
OpenMia-Indo-Mistral-7b-v3-refined.Q5_K_S.gguf	Q5_K_S	4.65GB
OpenMia-Indo-Mistral-7b-v3-refined.Q5_K.gguf	Q5_K	4.78GB
OpenMia-Indo-Mistral-7b-v3-refined.Q5_K_M.gguf	Q5_K_M	4.78GB
OpenMia-Indo-Mistral-7b-v3-refined.Q5_1.gguf	Q5_1	5.07GB
OpenMia-Indo-Mistral-7b-v3-refined.Q6_K.gguf	Q6_K	5.53GB
OpenMia-Indo-Mistral-7b-v3-refined.Q8_0.gguf	Q8_0	7.17GB

Original model description:

language:

en
id license: cc-by-nc-4.0 tags:
text-generation-inference
transformers
mistral
trl datasets:
MBZUAI/Bactrian-X base_model: mistral-7b model-index:
name: OpenMia-Indo-Mistral-7b-v3-refined results:
- task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics:
  - type: acc_norm value: 64.42 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/OpenMia-Indo-Mistral-7b-v3-refined name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics:
  - type: acc_norm value: 84.22 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/OpenMia-Indo-Mistral-7b-v3-refined name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics:
  - type: acc value: 62.64 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/OpenMia-Indo-Mistral-7b-v3-refined 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: num_few_shot: 0 metrics:
  - type: mc2 value: 53.95 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/OpenMia-Indo-Mistral-7b-v3-refined name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics:
  - type: acc value: 81.53 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/OpenMia-Indo-Mistral-7b-v3-refined name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics:
  - type: acc value: 61.26 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/OpenMia-Indo-Mistral-7b-v3-refined name: Open LLM Leaderboard

updated to V3 with some refinement

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

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

OpenMia-Indo-Mistral-7b 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

markdown

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

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

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

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	68.00
AI2 Reasoning Challenge (25-Shot)	64.42
HellaSwag (10-Shot)	84.22
MMLU (5-Shot)	62.64
TruthfulQA (0-shot)	53.95
Winogrande (5-shot)	81.53
GSM8k (5-shot)	61.26

RichardErkhov/indischepartij_-_OpenMia-Indo-Mistral-7b-v3-refined-gguf