4-bit Autotrain compatible Bitsandbytes Dataset:adamo1139/rawrr v1 Dpo Endpoints compatible Llama Lora Qlora Region:us Safetensors Unsloth
Yi 34B 200K Rawrr1 LORA DPO Experimental R3 Benchmarks
ARC: 64.85-32.7%
HellaSwag: 84.77-11%
MMLU: 76-12.1%
TruthfulQA: 45.35-23.1%
WinoGrande: 83.11-5%
GSM8K: 61.64-33%
nn.n% — How the model compares to the GPT-4.
Yi 34B 200K Rawrr1 LORA DPO Experimental R3 Parameters and Internals
| LLM Name | Yi 34B 200K Rawrr1 LORA DPO Experimental R3 |
| Repository | Open on 🤗 |
| Model Size | 34b |
| Required VRAM | 0.5 GB |
| Updated | 2024-07-27 |
| Maintainer | adamo1139 |
| Model Files | |
| Model Architecture | AutoModelForCausalLM |
| License | apache-2.0 |
| Model Max Length | 200000 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | gate_proj|q_proj|o_proj|down_proj|v_proj|up_proj|k_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0 |
| R Param | 16 |
Best Alternatives to Yi 34B 200K Rawrr1 LORA DPO Experimental R3
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Yi 34B Qlora E1 | 0.2 | 0K / 5.8 GB | 947 | 0 |
| Yi 34B 200K AEZAKMI V2 LoRA | 0.2 | 0K / 0.5 GB | 7 | 1 |
| Yi 34B AEZAKMI V1 LoRA | 0.2 | 0K / 0.5 GB | 8 | 1 |
| ... 34B Spicyboros 2 2 Run3 QLoRA | 0.2 | 0K / 0.5 GB | 11 | 1 |
| Yi 34B Spicyboros 3.1 2 LoRA | 0.2 | 0K / 2 GB | 12 | 1 |
| Limarpv3 Yi Llama 34B Lora | 0.2 | 0K / 1 GB | 24 | 8 |
| Yi 34B Spicyboros 3.1 LoRA | 0.2 | 0K / 2 GB | 8 | 4 |
| Yi 34B GiftedConvo | 0.2 | 0K / 5.8 GB | 11 | 2 |
Rank the Yi 34B 200K Rawrr1 LORA DPO Experimental R3 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? 34447 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501