Adapter Base model:01-ai/yi-1.5-6b-cha... Base model:adapter:01-ai/yi-1.... Finetuned Generated from trainer Llama-factory Lora Peft Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/langgptai/Yi-1.5-6B-Chat-sa-v0.1
Yi 1.5 6B Chat Sa V0.1 Benchmarks
ARC: 61.35 vs 96.7 (so35)-36.6%
HellaSwag: 77.93 vs 95.3 (gpt4)-18.2%
MMLU: 64.76 vs 88.3 (so35)-26.7%
TruthfulQA: 49.82 vs 59 (gpt4)-15.6%
WinoGrande: 74.66 vs 87.5 (gpt4)-14.7%
GSM8K: 68.69 vs 96.4 (so35)-28.7%
LLME Score: 0.18576
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 1.5 6B Chat Sa V0.1 Parameters and Internals
| Training Details |
|
| LLM Name | Yi 1.5 6B Chat Sa V0.1 |
| Repository 🤗 | https://huggingface.co/langgptai/Yi-1.5-6B-Chat-sa-v0.1 |
| Base Model(s) | |
| Model Size | 6b |
| Required VRAM | 0 GB |
| Updated | 2024-11-17 |
| Maintainer | langgptai |
| Model Files | |
| Model Architecture | Adapter |
| License | other |
| Model Max Length | 4096 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | v_proj|q_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0 |
| R Param | 8 |
Best Alternatives to Yi 1.5 6B Chat Sa V0.1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| 01 Ai Yi 1.5 6B 1719098372 | 0K / 0.4 GB | 24 | 0 |
| 01 Ai Yi 1.5 6B 1719335236 | 0K / 0.4 GB | 5 | 0 |
| 01 Ai Yi 1.5 6B 1718986516 | 0K / 0.4 GB | 5 | 0 |
| Dreamtobenlpsama Mnlp M2 | 0K / 0 GB | 5 | 0 |
| Yi 6B Yoruno Peft | 0K / 0.6 GB | 3 | 1 |
| Trl Rm Tldr Gptj | 0K / 0 GB | 6 | 1 |
| Yi 6b Chat Medical Qa Full | 0K / 0 GB | 3 | 1 |
| Yi 6B Chat Finance Qa | 0K / 0 GB | 4 | 1 |
| ...i 6b Chat Medical Qa Full Beta | 0K / 0 GB | 2 | 1 |
| Chatglm3 6B Csc Chinese Lora | 0K / 0.1 GB | 73 | 41 |
Rank the Yi 1.5 6B Chat Sa V0.1 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! 🌟
What open-source LLMs or SLMs are you in search of? 48046 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124