Name: YamshadowExperiment28 7B
Author: automerger

YamshadowExperiment28 7B is an open-source language model by automerger. Features: 7b LLM, VRAM: 14.4GB, Context: 32K, License: apache-2.0, Merged, HF Score: 76.9, LLM Explorer Score: 0.22, Arc: 73.3, HellaSwag: 89.3, MMLU: 64.4, TruthfulQA: 78.5, WinoGrande: 85.2, GSM8K: 70.5.

Merged Model Base model:yam-peleg/experimen... Endpoints compatible Mistral Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/automerger/YamshadowExperiment28-7B

YamshadowExperiment28 7B Benchmarks

IFEval: 40.7 vs 88 (so35)^-53.8%

ARC: 73.29 vs 96.7 (so35)^-24.2%

HellaSwag: 89.25 vs 95.3 (gpt4)^-6.3%

MMLU: 64.38 vs 88.3 (so35)^-27.1%

TruthfulQA: 78.53 vs 59 (gpt4)^33.1%

WinoGrande: 85.24 vs 87.5 (gpt4)^-2.6%

GSM8K: 70.51 vs 96.4 (so35)^-26.9%

MATH Lvl 5: 6.12

LLME Score: 0.22107

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

YamshadowExperiment28 7B (automerger/YamshadowExperiment28-7B)

🌟 Advertise your project 🚀

YamshadowExperiment28 7B Parameters and Internals

Model Type

text generation

Use Cases

Applications:

research, commercial applications

Primary Use Cases:

chat-based applications

Limitations:

Overfitting to specific benchmarks.

Additional Notes

The model's excellent results on benchmark tests may be indicative of overfitting.

Training Details

Methodology:

Merge technique: SLERP between layers of two models

Context Length:

8000

Input Output

Input Format:

Alpaca chat template

Accepted Modalities:

text

Output Format:

text

Performance Tips:

The model can sometimes break and output a lot of "INST."

LLM Name	YamshadowExperiment28 7B
Repository 🤗	https://huggingface.co/automerger/YamshadowExperiment28-7B
Base Model(s)	YamShadow 7B Experiment28 7B automerger/YamShadow-7B yam-peleg/Experiment28-7B
Merged Model	Yes
Model Size	7b
Required VRAM	14.4 GB
Updated	2026-04-25
Maintainer	automerger
Model Type	mistral
Model Files	9.9 GB: 1-of-2 4.5 GB: 2-of-2
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.38.2
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32000
Torch Data Type	bfloat16

Quantized Models of the YamshadowExperiment28 7B

Model	Likes	Downloads	VRAM
YamshadowExperiment28 7B GGUF	0	41	2 GB

Best Alternatives to YamshadowExperiment28 7B

Best Alternatives	Context / RAM	Downloads	Likes
...Nemo Instruct 2407 Abliterated	1000K / 24.5 GB	254	20
MegaBeam Mistral 7B 512K	512K / 14.4 GB	11443	54
SpydazWeb AI HumanAI RP	512K / 14.4 GB	14	1
SpydazWeb AI HumanAI 002	512K / 14.4 GB	18	1
...daz Web AI ChatML 512K Project	512K / 14.5 GB	12	0
MegaBeam Mistral 7B 300K	282K / 14.4 GB	3779	16
MegaBeam Mistral 7B 300K	282K / 14.4 GB	7968	16
Hebrew Mistral 7B 200K	256K / 30 GB	1316	15
Astral 256K 7B V2	250K / 14.4 GB	6	0
Astral 256K 7B	250K / 14.4 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than automerger/YamshadowExperiment28-7B.

Rank the YamshadowExperiment28 7B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

What open-source LLMs or SLMs are you in search of? 53185 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

YamshadowExperiment28 7B by automerger

» All LLMs » automerger » YamshadowExperiment28 7B URL Share it on