Llama With Eeve The Third 04 150M By kikikara: Benchmarks, Features and Detailed Analysis. Insights on Llama With Eeve The Third 04 150M.

Autotrain compatible Conversational Dataset:haerae-hub/k2-feedback Dataset:haerae-hub/korean-huma... Dataset:heegyu/aulm-0809 Dataset:heegyu/cot-collection-... Dataset:heegyu/kowikitext Dataset:heegyu/open-korean-ins... Dataset:instructkr/ko elo aren... Dataset:markrai/kocommercial-d... Dataset:maywell/ko wikidata qa Dataset:nlpai-lab/kullm-v2 Endpoints compatible Ko Llama Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/kikikara/llama_with_eeve_the_third_04_150M

Llama With Eeve The Third 04 150M Benchmarks

LLME Score: 0.19379

^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)

Llama With Eeve The Third 04 150M (kikikara/llama_with_eeve_the_third_04_150M)

Llama With Eeve The Third 04 150M Parameters and Internals

Model Type

text-generation

Supported Languages

ko (proficient)

Training Details

Data Sources:

maywell/ko_wikidata_QA, nlpai-lab/kullm-v2, heegyu/kowikitext, MarkrAI/KoCommercial-Dataset, heegyu/CoT-collection-ko, HAERAE-HUB/Korean-Human-Judgements, instructkr/ko_elo_arena_0207, HAERAE-HUB/K2-Feedback, heegyu/open-korean-instructions, heegyu/aulm-0809

Methodology:

Random initialization with a pre-trained model. System prompt included during training: '당신은 비도덕적이거나, 성적이거나, 불법적이거나 또는 사회 통념적으로 허용되지 않는 발언은 하지 않습니다. 사용자와 즐겁게 대화하며, 사용자의 응답에 가능한 정확하고 친절하게 응답함으로써 최대한 도와주려고 노력합니다. {question}'

Model Architecture:

llama architecture with eeve tokenizer

Input Output

Input Format:

Prompts must include the system format specified: '### System:...'

Accepted Modalities:

text

Output Format:

Generates text based on prompts

LLM Name	Llama With Eeve The Third 04 150M
Repository 🤗	https://huggingface.co/kikikara/llama_with_eeve_the_third_04_150M
Model Size	150m
Required VRAM	0.6 GB
Updated	2025-02-22
Maintainer	kikikara
Model Type	llama
Model Files	0.6 GB
Supported Languages	ko
Model Architecture	LlamaForCausalLM
Context Length	32768
Model Max Length	32768
Transformers Version	4.41.1
Tokenizer Class	LlamaTokenizer
Padding Token	<\|im_end\|>
Vocabulary Size	40960
Torch Data Type	float32

Best Alternatives to Llama With Eeve The Third 04 150M

Best Alternatives	Context / RAM	Downloads	Likes
Llama With Eeve New 03 150m	32K / 0.6 GB	143	1
...th Eeve The Third 04 Math 150M	32K / 0.6 GB	67	0
Llama With Eeve New 150m	32K / 0.6 GB	53	0
...ma With Eeve The Third 06 150M	32K / 0.6 GB	53	0
... Eeve The Third 04 Law 01 150M	32K / 0.6 GB	55	0
Llama 150M Fresh	2K / 0.9 GB	1031	1

Note: green Score (e.g. "73.2") means that the model is better than kikikara/llama_with_eeve_the_third_04_150M.

Rank the Llama With Eeve The Third 04 150M 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? 43470 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

Llama With Eeve The Third 04 150M by kikikara

» All LLMs » kikikara » Llama With Eeve The Third 04 150M URL Share it on

Llama With Eeve The Third 04 150M Benchmarks

Llama With Eeve The Third 04 150M Parameters and Internals

Best Alternatives to Llama With Eeve The Third 04 150M

Rank the Llama With Eeve The Third 04 150M Capabilities

What open-source LLMs or SLMs are you in search of? 43470 in total.