Saiga2 7B Lora By IlyaGusev: Benchmarks, Features and Detailed Analysis. Insights on Saiga2 7B Lora.

Adapter Conversational Dataset:ilyagusev/oasst1 ru ma... Dataset:ilyagusev/ru sharegpt ... Dataset:ilyagusev/ru turbo alp... Dataset:ilyagusev/ru turbo alp... Dataset:ilyagusev/ru turbo sai... Dataset:lksy/ru instruct gpt4 Finetuned Instruct Lora Region:us Ru

Model Card on HF 🤗: https://huggingface.co/IlyaGusev/saiga2_7b_lora

Saiga2 7b Lora Benchmarks

LLME Score: 0.11853

^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)

Saiga2 7B Lora (IlyaGusev/saiga2_7b_lora)

Saiga2 7B Lora Parameters and Internals

Model Type

Conversational

Supported Languages

ru (Proficient)

Training Details

Data Sources:

IlyaGusev/ru_turbo_alpaca, IlyaGusev/ru_turbo_saiga, IlyaGusev/ru_sharegpt_cleaned, IlyaGusev/oasst1_ru_main_branch, IlyaGusev/ru_turbo_alpaca_evol_instruct, lksy/ru_instruct_gpt4

Context Length:

4096

Model Architecture:

Adapter-only version based on LLaMA-2 7B HF

Input Output

Accepted Modalities:

text

Performance Tips:

To run effectively, ensure you are not using the V100 GPU.

Release Notes

Version:

Notes:

Dataset code revision 7712a061d993f61c49b1e2d992e893c48acb3a87; 7 datasets merged; Performance: saiga7b_v5 vs saiga2_7b: 78-8-90

Version:

Notes:

Context extended to 4096; Performance: saiga2_7b_v2 vs saiga2_7b: 85-23-68

LLM Name	Saiga2 7b Lora
Repository 🤗	https://huggingface.co/IlyaGusev/saiga2_7b_lora
Model Size	7b
Required VRAM	0.1 GB
Updated	2025-02-22
Maintainer	IlyaGusev
Instruction-Based	Yes
Model Files	0.1 GB
Supported Languages	ru
Model Architecture	Adapter
License	cc-by-4.0
Model Max Length	4096
Is Biased	none
Tokenizer Class	LlamaTokenizer
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	q_proj\|v_proj\|k_proj\|o_proj
LoRA Alpha	16
LoRA Dropout	0.05
R Param	16

Quantized Models of the Saiga2 7B Lora

Model	Likes	Downloads	VRAM
Llama 2 7B Fp16	44	8394	13 GB

Best Alternatives to Saiga2 7B Lora

Best Alternatives	Context / RAM	Downloads	Likes
Qwen Megumin	0K / 0.1 GB	13	0
Deepthink Reasoning Adapter	0K / 0.2 GB	27	8
Mistral 7B Instruct Sa V0.1	0K / 0 GB	6	0
...Sql Flash Attention 2 Dataeval	0K / 1.9 GB	32	3
...82 6142 45d8 9455 Bc68ca4866eb	0K / 1.2 GB	6	0
Text To Rule Mistral 2	0K / 0.3 GB	6	0
...al 7B Instruct V0.3 1719301256	0K / 0.9 GB	9	0
...al 7B Instruct V0.3 1719297750	0K / 0.4 GB	6	0
Text To Rule Mistral	0K / 0.4 GB	6	0
...al 7B Instruct V0.3 1719341325	0K / 1.7 GB	6	0

Note: green Score (e.g. "73.2") means that the model is better than IlyaGusev/saiga2_7b_lora.

Rank the Saiga2 7B Lora 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? 43508 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.

Release v20241227

Support LLM Explorer