language:
- en
- fr
- es
- pt
license: other
library_name: transformers
tags:
- mergekit
- merge
- falcon3
base_model:
- neopolita/jessi-v0.4-falcon3-7b-instruct
- tiiuae/Falcon3-7B-Instruct
license_name: falcon-llm-license
license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
model-index:
- name: Falcon3-Jessi-v0.4-7B-Slerp
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: IFEval (0-Shot)
type: HuggingFaceH4/ifeval
args:
num_few_shot: 0
metrics:
- type: inst_level_strict_acc and prompt_level_strict_acc
value: 76.76
name: strict accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Falcon3-Jessi-v0.4-7B-Slerp
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BBH (3-Shot)
type: BBH
args:
num_few_shot: 3
metrics:
- type: acc_norm
value: 37.29
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Falcon3-Jessi-v0.4-7B-Slerp
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MATH Lvl 5 (4-Shot)
type: hendrycks/competition_math
args:
num_few_shot: 4
metrics:
- type: exact_match
value: 34.59
name: exact match
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Falcon3-Jessi-v0.4-7B-Slerp
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GPQA (0-shot)
type: Idavidrein/gpqa
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 8.28
name: acc_norm
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Falcon3-Jessi-v0.4-7B-Slerp
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MuSR (0-shot)
type: TAUR-Lab/MuSR
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 20.49
name: acc_norm
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Falcon3-Jessi-v0.4-7B-Slerp
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU-PRO (5-shot)
type: TIGER-Lab/MMLU-Pro
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 34
name: accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Falcon3-Jessi-v0.4-7B-Slerp
name: Open LLM Leaderboard
Merged Model
This is a merge of pre-trained language models created using mergekit.
This model is currently ranked #1 on the Open LLM Leaderboard among models up to 10B parameters and #2 among models up to 14B parameters!
Merge Details
Merge Method
This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
Falcon3-7B-Instruct
Falcon3 family of Open Foundation Models is a set of pretrained and instruct LLMs ranging from 1B to 10B.
This repository contains the Falcon3-7B-Instruct. It achieves state of art results (at the time of release) on reasoning, language understanding, instruction following, code and mathematics tasks. Falcon3-7B-Instruct supports 4 languages (English, French, Spanish, Portuguese) and a context length up to 32K.
Configuration
The following YAML configuration was used to produce this model:
base_model: neopolita/jessi-v0.4-falcon3-7b-instruct
dtype: bfloat16
merge_method: slerp
parameters:
t:
- filter: self_attn
value: [0.0, 0.5, 0.3, 0.7, 1.0]
- filter: mlp
value: [1.0, 0.5, 0.7, 0.3, 0.0]
- value: 0.5
slices:
- sources:
- layer_range: [0, 28]
model: tiiuae/Falcon3-7B-Instruct
- layer_range: [0, 28]
model: neopolita/jessi-v0.4-falcon3-7b-instruct
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 35.23 |
| IFEval (0-Shot) | 76.76 |
| BBH (3-Shot) | 37.29 |
| MATH Lvl 5 (4-Shot) | 34.59 |
| GPQA (0-shot) | 8.28 |
| MuSR (0-shot) | 20.49 |
| MMLU-PRO (5-shot) | 34.00 |
