TinyLlama 1.1B 32K By Doctor-Shotgun: Benchmarks, Features and Detailed Analysis. Insights on TinyLlama 1.1B 32K.

Autotrain compatible Dataset:togethercomputer/redpa... En Endpoints compatible Llama Llama 2 Pytorch Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/Doctor-Shotgun/TinyLlama-1.1B-32k

TinyLlama 1.1B 32K Benchmarks

LLME Score: 0.18061

^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)

TinyLlama 1.1B 32K (Doctor-Shotgun/TinyLlama-1.1B-32k)

TinyLlama 1.1B 32K Parameters and Internals

Model Type

text generation, long-context modeling

Use Cases

Areas:

research

Primary Use Cases:

long-context speculative decoding

Additional Notes

The quantized model fits alongside a 4.25bpw 70B model at 32k sequence length and provides noticeable speed-up with speculative decoding.

Supported Languages

en (high)

Training Details

Data Sources:

togethercomputer/RedPajama-Data-1T-Sample

Data Volume:

1T tokens

Methodology:

context finetune with increased rope theta (rope frequency base) for long-context modeling

Context Length:

32768

Hardware Used:

single A6000

Model Architecture:

Derived from TinyLlama-1.1B architecture

Input Output

Accepted Modalities:

text

Output Format:

text

LLM Name	TinyLlama 1.1B 32K
Repository 🤗	https://huggingface.co/Doctor-Shotgun/TinyLlama-1.1B-32k
Model Size	1.1b
Required VRAM	2.2 GB
Updated	2024-12-14
Maintainer	Doctor-Shotgun
Model Type	llama
Model Files	2.2 GB 2.2 GB
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.36.2
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32000
Torch Data Type	bfloat16

Quantized Models of the TinyLlama 1.1B 32K

Model	Likes	Downloads	VRAM
...E TinyLlama 1.1B 32K Base 8bit	1	23	1 GB
...E TinyLlama 1.1B 32K Base 4bit	1	13	0 GB
TinyLlama 1.1B 32K GGUF	0	21	0 GB

Best Alternatives to TinyLlama 1.1B 32K

Best Alternatives	Context / RAM	Downloads	Likes
Coven Tiny 1.1b 32k Orpo Alpha	32K / 2.2 GB	17	2
Test Mix 01	32K / 2.2 GB	13	0
Palmer Merge Test 5	32K / 2.2 GB	10	0
TinyLlama 1.1B 32K Instruct	32K / 2.2 GB	628	12
...llama 1.1B 16K Instructions V4	32K / 2.2 GB	7	0
TinyJ.O.S.I.E. 1.1B 32K Base	32K / 2.2 GB	31	1
Palmer 002 32K	32K / 2.2 GB	18	0
TinyJ.O.S.I.E. 1.1B 32K Base	32K / 2.2 GB	5	1
...lama 1.1B 16K Instructions Rag	32K / 2.2 GB	16	0
Tinyllama History Chat V1.1	32K / 2.2 GB	20	0

Note: green Score (e.g. "73.2") means that the model is better than Doctor-Shotgun/TinyLlama-1.1B-32k.

Rank the TinyLlama 1.1B 32K 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? 39237 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 v20241124

Support LLM Explorer