What are the hardware requirements for Yi 34B 200K Aezakmi V2 Rawrr V1 Run1 Experimental LoRA?

Yi 34B 200K Aezakmi V2 Rawrr V1 Run1 Experimental LoRA requires approximately 0.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Where can I download or evaluate Yi 34B 200K Aezakmi V2 Rawrr V1 Run1 Experimental LoRA?

Yi 34B 200K Aezakmi V2 Rawrr V1 Run1 Experimental LoRA is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Yi 34B 200K Aezakmi V2 Rawrr V1 Run1 Experimental LoRA by adamo1139 — VRAM 0.5GB

Name: Yi 34B 200K Aezakmi V2 Rawrr V1 Run1 Experimental LoRA
Author: adamo1139

Yi 34B 200K Aezakmi V2 Rawrr V1 Run1 Experimental LoRA is an open-source language model by adamo1139. Features: 34b LLM, VRAM: 0.5GB, LLM Explorer Score: 0.1.

4-bit Adapter Bitsandbytes Finetuned Generated from trainer Llama Lora Peft Region:us

Model Card on HF 🤗: https://huggingface.co/adamo1139/yi-34b-200k-aezakmi-v2-rawrr-v1-run1-experimental-LoRA

Yi 34B 200K Aezakmi V2 Rawrr V1 Run1 Experimental LoRA Parameters and Internals

Model Type

LlamaForCausalLM

Additional Notes

If you want to re-create the model from this, first get yourself Yi-34B-200K llama-fied, then merge in LoRA from adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r2. It's all pretty experimental.

Training Details

Data Sources:

aezakmi_v2_draft2.jsonl

Methodology:

This LoRA has been trained using DPO (I think I will re-run DPO training on rawrr with maybe a bit longer context and with higher lr or epoch count).

Context Length:

1400

LLM Name	Yi 34B 200K Aezakmi V2 Rawrr V1 Run1 Experimental LoRA
Repository 🤗	https://huggingface.co/adamo1139/yi-34b-200k-aezakmi-v2-rawrr-v1-run1-experimental-LoRA
Model Size	34b
Required VRAM	0.5 GB
Updated	2026-08-03
Maintainer	adamo1139
Model Files	0.5 GB
Model Architecture	Adapter
Model Max Length	200000
Is Biased	none
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	up_proj\|v_proj\|down_proj\|gate_proj\|k_proj\|o_proj\|q_proj
LoRA Alpha	32
LoRA Dropout	0.05
R Param	16

Rank the Yi 34B 200K Aezakmi V2 Rawrr V1 Run1 Experimental LoRA 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 Yi 34B 200K Aezakmi V2 Rawrr V1 Run1 Experimental LoRA

Best Alternatives	Context / RAM	Downloads	Likes
30B 2e	0K / 0 GB	5	0
...34B 200K AEZAKMI RAW 2301 LoRA	0K / 0.5 GB	0	1
Airoboros 34B 3.3 Peft	0K / 0.5 GB	0	1
Bagel 34B V0.5 Peft	0K / 0.5 GB	0	1
34B Beta Onc V1	0K / 0 GB	4	1
Deacon 34B Qlora Adapter	0K / 0.1 GB	0	2
...pmoney 34B 200K Chat Evaluator	0K / 2 GB	0	35
...awrr1 LORA DPO Experimental R2	0K / 0.1 GB	3	1
Yi 34B 200K MiniOrca Adapter	0K / 0.1 GB	0	1
Yi 34B Alpaca Cot Lora	0K / 0.1 GB	0	15

Note: green Score (e.g. "73.2") means that the model is better than adamo1139/yi-34b-200k-aezakmi-v2-rawrr-v1-run1-experimental-LoRA.