You can deploy this model and start earning money today!

RichardErkhov/
osanseviero_-_mistral-instruct-moe-experimental-gguf

Name: osanseviero_-_mistral-instruct-moe-experimental-gguf
Availability: InStock

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

mistral-instruct-moe-experimental - GGUF

Model creator: https://huggingface.co/osanseviero/
Original model: https://huggingface.co/osanseviero/mistral-instruct-moe-experimental/

Name	Quant method	Size
mistral-instruct-moe-experimental.Q2_K.gguf	Q2_K	4.43GB
mistral-instruct-moe-experimental.IQ3_XS.gguf	IQ3_XS	4.95GB
mistral-instruct-moe-experimental.IQ3_S.gguf	IQ3_S	5.22GB
mistral-instruct-moe-experimental.Q3_K_S.gguf	Q3_K_S	5.2GB
mistral-instruct-moe-experimental.IQ3_M.gguf	IQ3_M	4.55GB
mistral-instruct-moe-experimental.Q3_K.gguf	Q3_K	5.78GB
mistral-instruct-moe-experimental.Q3_K_M.gguf	Q3_K_M	3.59GB
mistral-instruct-moe-experimental.Q3_K_L.gguf	Q3_K_L	6.27GB
mistral-instruct-moe-experimental.IQ4_XS.gguf	IQ4_XS	6.5GB
mistral-instruct-moe-experimental.Q4_0.gguf	Q4_0	6.78GB
mistral-instruct-moe-experimental.IQ4_NL.gguf	IQ4_NL	6.85GB
mistral-instruct-moe-experimental.Q4_K_S.gguf	Q4_K_S	6.84GB
mistral-instruct-moe-experimental.Q4_K.gguf	Q4_K	7.25GB
mistral-instruct-moe-experimental.Q4_K_M.gguf	Q4_K_M	7.25GB
mistral-instruct-moe-experimental.Q4_1.gguf	Q4_1	7.52GB
mistral-instruct-moe-experimental.Q5_0.gguf	Q5_0	8.26GB
mistral-instruct-moe-experimental.Q5_K_S.gguf	Q5_K_S	8.26GB
mistral-instruct-moe-experimental.Q5_K.gguf	Q5_K	8.51GB
mistral-instruct-moe-experimental.Q5_K_M.gguf	Q5_K_M	8.51GB
mistral-instruct-moe-experimental.Q5_1.gguf	Q5_1	9.01GB
mistral-instruct-moe-experimental.Q6_K.gguf	Q6_K	9.84GB
mistral-instruct-moe-experimental.Q8_0.gguf	Q8_0	12.75GB

Original model description:

license: apache-2.0 tags:

mergekit
merge
moe base_model:
mistralai/Mistral-7B-Instruct-v0.2
mistralai/Mistral-7B-Instruct-v0.1 model-index:
name: mistral-instruct-moe-experimental 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: 61.01 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=osanseviero/mistral-instruct-moe-experimental 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: 81.55 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=osanseviero/mistral-instruct-moe-experimental 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: 58.22 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=osanseviero/mistral-instruct-moe-experimental 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: 60.4 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=osanseviero/mistral-instruct-moe-experimental 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: 76.09 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=osanseviero/mistral-instruct-moe-experimental 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: 31.08 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=osanseviero/mistral-instruct-moe-experimental name: Open LLM Leaderboard

Mistral Instruct MoE experimental

This is a merge of pre-trained language models created using mergekit using the mixtral branch.

This is an experimental model and has nothing to do with Mixtral. Mixtral is not a merge of models per se, but a transformer with MoE layers learned during training

This uses a random gate, so I expect not great results. We'll see!

Merge Details

Merge Method

This model was merged using the MoE merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml

base_model: mistralai/Mistral-7B-Instruct-v0.2
gate_mode: random
dtype: bfloat16
experts:
  - source_model: mistralai/Mistral-7B-Instruct-v0.2
    positive_prompts: [""]
  - source_model: mistralai/Mistral-7B-Instruct-v0.1
    positive_prompts: [""]

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	61.39
AI2 Reasoning Challenge (25-Shot)	61.01
HellaSwag (10-Shot)	81.55
MMLU (5-Shot)	58.22
TruthfulQA (0-shot)	60.40
Winogrande (5-shot)	76.09
GSM8k (5-shot)	31.08

RichardErkhov/osanseviero_-_mistral-instruct-moe-experimental-gguf