Cognitivecomputations Samantha 1.11 13B Bnb 4bit Smashed By PrunaAI: Benchmarks, Features and Detailed Analysis. Insights on Cognitivecomputations Samantha 1.11 13B Bnb 4bit Smashed.

4-bit 4bit Autotrain compatible Base model:prunaai/cognitiveco... Base model:quantized:prunaai/c... Bitsandbytes Endpoints compatible Llama Pruna-ai Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/PrunaAI/cognitivecomputations-Samantha-1.11-13b-bnb-4bit-smashed

Cognitivecomputations Samantha 1.11 13B Bnb 4bit Smashed Benchmarks

LLME Score: 0.20152

^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)

Cognitivecomputations Samantha 1.11 13B Bnb 4bit Smashed (PrunaAI/cognitivecomputations-Samantha-1.11-13b-bnb-4bit-smashed)

Cognitivecomputations Samantha 1.11 13B Bnb 4bit Smashed Parameters and Internals

Model Type

causal language model

Use Cases

Considerations:

Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...).

Additional Notes

The naming convention for Pruna Huggingface models involves appending "turbo", "tiny", or "green" if certain efficiency metrics are met compared to the base model.

Training Details

Data Sources:

WikiText

Methodology:

Hardware Used:

HARDWARE_NAME

Input Output

Input Format:

pt tensors

Accepted Modalities:

text

Output Format:

decoded text

Performance Tips:

Test the efficiency gains directly in your use-cases.

LLM Name	Cognitivecomputations Samantha 1.11 13B Bnb 4bit Smashed
Repository 🤗	https://huggingface.co/PrunaAI/cognitivecomputations-Samantha-1.11-13b-bnb-4bit-smashed
Base Model(s)	PrunaAI/cognitivecomputations-Samantha-1.11-13b-bnb-4bit-smashed PrunaAI/cognitivecomputations-Samantha-1.11-13b-bnb-4bit-smashed
Model Size	13b
Required VRAM	7.8 GB
Updated	2025-02-05
Maintainer	PrunaAI
Model Type	llama
Model Files	5.0 GB: 1-of-2 2.8 GB: 2-of-2
Quantization Type	4bit
Model Architecture	LlamaForCausalLM
Context Length	4096
Model Max Length	4096
Transformers Version	4.40.0
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32000
Torch Data Type	float16

Quantized Models of the Cognitivecomputations Samantha 1.11 13B Bnb 4bit Smashed

Model	Likes	Downloads	VRAM
...ntha 1.11 13B Bnb 4bit Smashed	0	79	7 GB

Best Alternatives to Cognitivecomputations Samantha 1.11 13B Bnb 4bit Smashed

Best Alternatives	Context / RAM	Downloads	Likes
Llama13b 32K Illumeet Finetune	32K / 26 GB	5	0
...Maid V3 13B 32K 6.0bpw H6 EXL2	32K / 10 GB	4	1
...Maid V3 13B 32K 8.0bpw H8 EXL2	32K / 13.2 GB	4	1
WhiteRabbitNeo 13B V1	16K / 26 GB	2329	411
CodeLlama 13B Python Fp16	16K / 26 GB	2357	25
CodeLlama 13B Instruct Fp16	16K / 26 GB	2435	28
Codellama 13B Bnb 4bit	16K / 7.2 GB	103	1
CodeLlama 13B Fp16	16K / 26 GB	18	66
...Llama 13B Instruct Hf 4bit MLX	16K / 7.8 GB	66	2
Airophin 13B Pntk 16K Fp16	16K / 26 GB	1241	4

Note: green Score (e.g. "73.2") means that the model is better than PrunaAI/cognitivecomputations-Samantha-1.11-13b-bnb-4bit-smashed.

Rank the Cognitivecomputations Samantha 1.11 13B Bnb 4bit Smashed 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? 42577 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