What are the hardware requirements for Snorkel Mistral PairRM DPO 8.0bpw H8 EXL2?

Snorkel Mistral PairRM DPO 8.0bpw H8 EXL2 requires approximately 7.4 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 Snorkel Mistral PairRM DPO 8.0bpw H8 EXL2 and how large is it?

Snorkel Mistral PairRM DPO 8.0bpw H8 EXL2 is developed by LoneStriker. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Snorkel Mistral PairRM DPO 8.0bpw H8 EXL2?

Snorkel Mistral PairRM DPO 8.0bpw H8 EXL2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Snorkel Mistral PairRM DPO 8.0bpw H8 EXL2 by LoneStriker — VRAM 7.4GB, 32K context

Name: Snorkel Mistral PairRM DPO 8.0bpw H8 EXL2
Author: LoneStriker

Snorkel Mistral PairRM DPO 8.0bpw H8 EXL2 is an open-source language model by LoneStriker. Features: LLM, VRAM: 7.4GB, Context: 32K, License: apache-2.0, Quantized, LLM Explorer Score: 0.11.

Arxiv:2305.18290 Arxiv:2306.02561 Arxiv:2401.10020 Conversational Dataset:snorkelai/snorkel-mist... Endpoints compatible Exl2 Mistral Pytorch Quantized Region:us

Model Card on HF 🤗: https://huggingface.co/LoneStriker/Snorkel-Mistral-PairRM-DPO-8.0bpw-h8-exl2

Snorkel Mistral PairRM DPO 8.0bpw H8 EXL2 Parameters and Internals

Model Type

text-generation

Use Cases

Limitations:

No moderation mechanisms included.

Additional Notes

Endpoint for initial trials, not ongoing production use.

Training Details

Data Sources:

snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset, UltraFeedback

Methodology:

1. Generate five response variations for each prompt from a subset of 20,000 using the LLM - to start, we used Mistral-7B-Instruct-v0.2. 2. Apply PairRM for response reranking. 3. Update the LLM by applying Direct Preference Optimization (DPO) on the top (chosen) and bottom (rejected) responses. 4. Use this LLM as the base model for the next iteration, repeating three times in total.

Input Output

Input Format:

[INST] {prompt} [/INST]

LLM Name	Snorkel Mistral PairRM DPO 8.0bpw H8 EXL2
Repository 🤗	https://huggingface.co/LoneStriker/Snorkel-Mistral-PairRM-DPO-8.0bpw-h8-exl2
Required VRAM	7.4 GB
Updated	2026-08-04
Maintainer	LoneStriker
Model Type	mistral
Model Files	7.4 GB 0.0 GB
Quantization Type	exl2
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.34.0
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Snorkel Mistral PairRM DPO 8.0bpw H8 EXL2 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

Best Alternatives to Snorkel Mistral PairRM DPO 8.0bpw H8 EXL2

Best Alternatives	Context / RAM	Downloads	Likes
NemoMix Unleashed EXL2 4bpw	1000K / 7.3 GB	5	9
...al Small 2505 Unsloth Bnb 4bit	128K / 15 GB	82	5
...0.88 07.02 RP DPO Merged 16bit	32K / 14.4 GB	6	0
...eZephir Sft Instruct Ead 16bit	32K / 14.4 GB	56	0
...cr To Json V1 HQQ 1bit Smashed	32K / 1.6 GB	5	0
...cr To Json V1 HQQ 4bit Smashed	32K / 4.2 GB	5	0
ScikitLLM Model EXL2	32K / 3 GB	5	1
Chargen V2 8bpw EXL2	32K / 7.4 GB	1	1
HamSter 0.2 8.0bpw H8 EXL2	32K / 7.4 GB	3	1
...N L1 Chat RL V1.3.0bpw H6 EXL2	32K / 3 GB	8	0

Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Snorkel-Mistral-PairRM-DPO-8.0bpw-h8-exl2.