You can deploy this model and start earning money today!

RichardErkhov/
monology_-_openinstruct-mistral-7b-gguf

Name: monology_-_openinstruct-mistral-7b-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

openinstruct-mistral-7b - GGUF

Model creator: https://huggingface.co/monology/
Original model: https://huggingface.co/monology/openinstruct-mistral-7b/

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

Original model description:

language:

en license: apache-2.0 library_name: transformers datasets:
monology/VMware-open-instruct-higgsfield pipeline_tag: text-generation model-index:
name: openinstruct-mistral-7b 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: 59.73 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=monology/openinstruct-mistral-7b 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: 82.77 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=monology/openinstruct-mistral-7b 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: 60.55 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=monology/openinstruct-mistral-7b 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: 48.76 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=monology/openinstruct-mistral-7b 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: 79.56 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=monology/openinstruct-mistral-7b 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: 50.49 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=monology/openinstruct-mistral-7b name: Open LLM Leaderboard

OpenInstruct Mistral-7B

1st among commercially-usable 7B models on the Open LLM Leaderboard!*

This is mistralai/Mistral-7B-v0.1 finetuned on VMware/open-instruct.
Quantized to FP16 and released under the Apache-2.0 license by myself.
Compute generously provided by Higgsfield AI.

Prompt format: Alpaca

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
[your instruction goes here]

### Response:

Recommended preset:

temperature: 0.2
top_k: 50
top_p 0.95
repetition_penalty: 1.1

*as of 21 Nov 2023. "commercially-usable" includes both an open-source base model and a non-synthetic open-source finetune dataset. updated leaderboard results available here.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	63.64
AI2 Reasoning Challenge (25-Shot)	59.73
HellaSwag (10-Shot)	82.77
MMLU (5-Shot)	60.55
TruthfulQA (0-shot)	48.76
Winogrande (5-shot)	79.56
GSM8k (5-shot)	50.49

RichardErkhov/monology_-_openinstruct-mistral-7b-gguf