What are the hardware requirements for Truthful DPO TomGrc FusionNet 7Bx2 MoE 13B?

Truthful DPO TomGrc FusionNet 7Bx2 MoE 13B requires approximately 25.8 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Truthful DPO TomGrc FusionNet 7Bx2 MoE 13B and how large is it?

Truthful DPO TomGrc FusionNet 7Bx2 MoE 13B is developed by yunconglong, a model with 12.9b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Truthful DPO TomGrc FusionNet 7Bx2 MoE 13B perform on standard benchmarks?

Truthful DPO TomGrc FusionNet 7Bx2 MoE 13B has the following published scores: MMLU 64.67. Compare against reference models on this page or on the LLM Explorer leaderboards.

Truthful DPO TomGrc FusionNet 7Bx2 MoE 13B by yunconglong — VRAM 25.8GB, 32K context

Name: Truthful DPO TomGrc FusionNet 7Bx2 MoE 13B
Rating: 3 (4 reviews)
Author: yunconglong

Truthful DPO TomGrc FusionNet 7Bx2 MoE 13B is an open-source language model by yunconglong. Features: 12.9b LLM, VRAM: 25.8GB, Context: 32K, License: mit, MoE, LLM Explorer Score: 0.14, Arc: 74.9, HellaSwag: 89.3, MMLU: 64.7, GSM8K: 69.5.

Dpo Endpoints compatible Mixtral Moe Region:us Rl-tuned Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B

Truthful DPO TomGrc FusionNet 7Bx2 MoE 13B Parameters and Internals

Model Type

moe, DPO, RL-TUNED

Additional Notes

Supports the DPO Trainer for training language models, as described in the paper Direct Preference Optimization: Your Language Model is Secretly a Reward Model by Rafailov et al., 2023.

Training Details

Data Sources:

jondurbin/truthy-dpo-v0.1

Methodology:

DPO (Direct Preference Optimization) Trainer for training language models from preference data.

LLM Name	Truthful DPO TomGrc FusionNet 7Bx2 MoE 13B
Repository 🤗	https://huggingface.co/yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
Model Size	12.9b
Required VRAM	25.8 GB
Updated	2026-08-08
Maintainer	yunconglong
Model Type	mixtral
Model Files	5.0 GB: 1-of-6 4.9 GB: 2-of-6 5.0 GB: 3-of-6 5.0 GB: 4-of-6 4.9 GB: 5-of-6 1.0 GB: 6-of-6
Model Architecture	MixtralForCausalLM
License	mit
Context Length	32768
Model Max Length	32768
Transformers Version	4.36.2
Tokenizer Class	LlamaTokenizer
Padding Token	<s>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Truthful DPO TomGrc FusionNet 7Bx2 MoE 13B capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Quantized Models of the Truthful DPO TomGrc FusionNet 7Bx2 MoE 13B

Model	Likes	Downloads	VRAM
...rc FusionNet 7Bx2 MoE 13B GPTQ	1	0	7 GB
...Grc FusionNet 7Bx2 MoE 13B AWQ	3	7	7 GB

Best Alternatives to Truthful DPO TomGrc FusionNet 7Bx2 MoE 13B

Best Alternatives	Context / RAM	Downloads	Likes
MixTAO 7Bx2 MoE V8.1	32K / 25.8 GB	15381	56
Inf Silent Kunoichi V0.1 2x7B	32K / 25.6 GB	8	0
Inf Silent Kunoichi V0.2 2x7B	32K / 25.6 GB	9	1
LogoS 7Bx2 MoE 13B V0.2	32K / 25.9 GB	7978	10
MixTAO 7Bx2 MoE V8.1	32K / 25.8 GB	8760	52
MultiMash8 13B Slerp	32K / 25.7 GB	5	0
MultiMash11 13B Slerp	32K / 25.7 GB	9	0
MultiMash9 13B Slerp	32K / 25.7 GB	5	0
MultiMash10 13B Slerp	32K / 25.7 GB	8	0
Multimash3 12B Slerp	32K / 25.7 GB	8	0

Note: green Score (e.g. "73.2") means that the model is better than yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B.