Yi 34B Chat By 01-ai: Benchmarks, Features and Detailed Analysis. Insights on Yi 34B Chat.

Arxiv:2311.16502 Arxiv:2401.11944 Arxiv:2403.04652 Autotrain compatible Conversational Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/01-ai/Yi-34B-Chat

Yi 34B Chat Benchmarks

LMSys ELO: 1111 vs 1272 (so35)^-12.7%

IFEval: 46.99 vs 88 (so35)^-46.6%

ARC: 65.1 vs 96.7 (so35)^-32.7%

HellaSwag: 84.08 vs 95.3 (gpt4)^-11.8%

MMLU: 74.87 vs 88.3 (so35)^-15.2%

TruthfulQA: 55.41 vs 59 (gpt4)^-6.1%

WinoGrande: 79.79 vs 87.5 (gpt4)^-8.8%

GSM8K: 19.79 vs 96.4 (so35)^-79.5%

MATH Lvl 5: 6.27

LLME Score: 0.38103

^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)

Yi 34B Chat Parameters and Internals

Model Type

Text Generation, Multimodal

Use Cases

Areas:

Personal, Academic, Commercial

Applications:

Code generation, Math solutions, Commonsense reasoning, Reading comprehension

Limitations:

Hallucination potential, Non-determinism in response generation, Cumulative error in extended tasks

Considerations:

Adjust generation configuration parameters such as temperature, top_p, or top_k to improve output consistency.

Supported Languages

English (B), Chinese (B)

Training Details

Data Sources:

3T multilingual corpus

Model Architecture:

Transformer and Llama architectures

Input Output

Accepted Modalities:

text

Output Format:

text

Performance Tips:

Recommendations to adjust temperature, top_p, or top_k settings for better output.

Release Notes

Version:

Yi-34B

Date:

2023-11-02

Notes:

Initial open-source release of Yi-34B and Yi-6B base models.

Version:

Yi-9B

Date:

2024-03-06

Notes:

Yi-9B becomes the top performer among similar-sized open-source models in coding, math, and reasoning.

LLM Name	Yi 34B Chat
Repository 🤗	https://huggingface.co/01-ai/Yi-34B-Chat
Model Size	34b
Required VRAM	69.2 GB
Updated	2025-03-22
Maintainer	01-ai
Model Type	llama
Model Files	4.8 GB: 1-of-15 4.8 GB: 2-of-15 5.0 GB: 3-of-15 4.8 GB: 4-of-15 4.8 GB: 5-of-15 5.0 GB: 6-of-15 4.8 GB: 7-of-15 4.8 GB: 8-of-15 5.0 GB: 9-of-15 4.8 GB: 10-of-15 4.8 GB: 11-of-15 5.0 GB: 12-of-15 4.8 GB: 13-of-15 4.8 GB: 14-of-15 1.2 GB: 15-of-15
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.35.0
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	64000
Torch Data Type	bfloat16

Quantized Models of the Yi 34B Chat

Model	Likes	Downloads	VRAM
Yi 34B Chat GGUF	71	4769	14 GB
Yi 34B Chat GGUF	3	164	12 GB
Yi 34B Chat GPTQ	16	40	18 GB
Yi 34B Chat AWQ	13	13	19 GB

Best Alternatives to Yi 34B Chat

Best Alternatives	Context / RAM	Downloads	Likes
Casual Magnum 34B	195K / 68.8 GB	17	1
Yi 34B 200K	195K / 68.9 GB	7497	318
Bagel 34B V0.2	195K / 68.7 GB	6279	41
34B Beta	195K / 69.2 GB	1696	63
Bagel Hermes 34B Slerp	195K / 68.9 GB	1938	1
Smaug 34B V0.1	195K / 69.2 GB	1684	60
Yi 34B 200K AEZAKMI V2	195K / 69.2 GB	2088	12
Mergekit Slerp Anaazls	195K / 69.2 GB	6	0
Faro Yi 34B	195K / 69.2 GB	1741	6
Dolphin 2.2 Yi 34B 200K	195K / 69.2 GB	2050	36

Rank the Yi 34B Chat 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? 45389 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