4-bit Autotrain compatible Bitsandbytes Dataset:nobodyexistsontheinter... Endpoints compatible Llama Lora Region:us
Model Card on HF 🤗: https://huggingface.co/NobodyExistsOnTheInternet/Yi-34b-qlora-e1
Yi 34B Qlora E1 Benchmarks
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 Qlora E1 Parameters and Internals
| Additional Notes |
| ||||||
| Training Details |
|
| LLM Name | Yi 34B Qlora E1 |
| Repository 🤗 | https://huggingface.co/NobodyExistsOnTheInternet/Yi-34b-qlora-e1 |
| Model Size | 34b |
| Required VRAM | 5.8 GB |
| Updated | 2025-02-22 |
| Maintainer | NobodyExistsOnTheInternet |
| Model Files | |
| Model Architecture | AutoModelForCausalLM |
| License | mit |
| Model Max Length | 4096 |
| Is Biased | none |
| Tokenizer Class | YiTokenizer |
| Padding Token | <unk> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | gate_proj|k_proj|q_proj|up_proj|v_proj|o_proj|down_proj |
| LoRA Alpha | 256 |
| LoRA Dropout | 0.05 |
| R Param | 128 |
Best Alternatives to Yi 34B Qlora E1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...awrr1 LORA DPO Experimental R3 | 0K / 0.5 GB | 1655 | 1 |
| Yi 34B 200K AEZAKMI V2 LoRA | 0K / 0.5 GB | 4 | 1 |
| Yi 34B AEZAKMI V1 LoRA | 0K / 0.5 GB | 4 | 1 |
| ... 34B Spicyboros 2 2 Run3 QLoRA | 0K / 0.5 GB | 7 | 1 |
| Yi 34B Spicyboros 3.1 2 LoRA | 0K / 2 GB | 5 | 1 |
| Limarpv3 Yi Llama 34B Lora | 0K / 1 GB | 14 | 10 |
| Yi 34B Spicyboros 3.1 LoRA | 0K / 2 GB | 6 | 4 |
| Yi 34B GiftedConvo | 0K / 5.8 GB | 21 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than NobodyExistsOnTheInternet/Yi-34b-qlora-e1 .
Rank the Yi 34B Qlora E1 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? 43508 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227