AmberChat By LLM360: Benchmarks, Features and Detailed Analysis. Insights on AmberChat.

Arxiv:2312.06550 Autotrain compatible Dataset:icybee/share gpt 90k v... Dataset:wizardlm/wizardlm evol... En Endpoints compatible Instruct Llama Region:us Safetensors Sharded Tensorflow

AmberChat Benchmarks

ARC: 42.92 vs 96.7 (so35)^-55.6%

HellaSwag: 74.01 vs 95.3 (gpt4)^-22.3%

MMLU: 38.75 vs 88.3 (so35)^-56.1%

TruthfulQA: 41.18 vs 59 (gpt4)^-30.2%

WinoGrande: 66.61 vs 87.5 (gpt4)^-23.9%

GSM8K: 5.53 vs 96.4 (so35)^-94.3%

LLME Score: 0.21464

^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)

AmberChat Parameters and Internals

LLM Name	AmberChat
Repository 🤗	https://huggingface.co/LLM360/AmberChat
Model Size	6.7b
Required VRAM	13.5 GB
Updated	2024-09-16
Maintainer	LLM360
Model Type	llama
Instruction-Based	Yes
Model Files	4.9 GB: 1-of-3 5.0 GB: 2-of-3 3.6 GB: 3-of-3
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.35.2
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32000
Torch Data Type	bfloat16

Quantized Models of the AmberChat

Model	Likes	Downloads	VRAM
AmberChat GGUF	2	190	2 GB
AmberChat GPTQ	1	6	3 GB
AmberChat AWQ	1	6	3 GB

Best Alternatives to AmberChat

Best Alternatives	Context / RAM	Downloads	Likes
Magicoder S DS 6.7B	16K / 27.1 GB	8909	200
Speechless Coder Ds 6.7B	16K / 13.5 GB	682	5
Code 290K 6.7B Instruct	16K / 13.5 GB	60	6
Datascience Coder 6.7B	16K / 13.5 GB	673	3
Merge Code Gen	16K / 13.6 GB	5	0
... 6.7B Instruct Trt Int4 G64 Hf	16K / 4.2 GB	5	0
...6.7B Instruct Trt Int8 G128 Hf	16K / 7.2 GB	7	0
AIGCodeGeek DS 6.7B	16K / 13.5 GB	19	4
...d Llama 6.7B RAG Code Instruct	16K / 13.5 GB	3	1
Magicoder S DS 6.7B MLX	16K / 13.4 GB	7	1

Note: green Score (e.g. "73.2") means that the model is better than LLM360/AmberChat.

Rank the AmberChat 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? 35941 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 v2024072803

Support LLM Explorer