4-bit Adapter Base model:mistralai/mixtral-8... Bitsandbytes Dataset:lemonilia/limarp En Finetuned Generated from trainer License:apache-2.0 Lora Mixtral Moe Peft Region:us Safetensors
Rank the Limarp Zloss Mixtral 8x7b Qlora 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! 🌟
Best Alternatives to Limarp Zloss Mixtral 8x7b Qlora
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Trrapi 16 | 70.85 | 0K / 0 GB | 1 | 1 |
| Mixtral 8x7B Instruct V0.1 | 68.87 | 0K / 0.1 GB | 11 | 9 |
| Mixtral 8x7b MonsterInstruct | 66.34 | 0K / 1 GB | 2 | 1 |
| Alpaca13B Lora | — | 0K / 0 GB | 0 | 33 |
| Dolly Lora | — | 0K / 0 GB | 0 | 25 |
| Aurora | — | 0K / 0 GB | 0 | 20 |
| Gpt4all J Lora | — | 0K / 0 GB | 0 | 18 |
| Alpaca | — | 0K / 0 GB | 0 | 14 |
| WizardLM LlaMA LoRA 13 | — | 0K / 0 GB | 0 | 13 |
| Alpaca7B Lora | — | 0K / 0 GB | 0 | 8 |
Note: green Score (e.g. "73.2") means that the model is better than Doctor-Shotgun/limarp-zloss-mixtral-8x7b-qlora .
Limarp Zloss Mixtral 8x7b Qlora Parameters and Internals
| LLM Name | Limarp Zloss Mixtral 8x7b Qlora |
| Repository | Open on 🤗 |
| Base Model(s) | |
| Required VRAM | 1.9 GB |
| Updated | 2024-06-24 |
| Maintainer | Doctor-Shotgun |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Adapter |
| License | apache-2.0 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | w2|k_proj|q_proj|o_proj|w1|v_proj|w3|gate |
| LoRA Alpha | 16 |
| LoRA Dropout | 0.05 |
| R Param | 32 |
What open-source LLMs or SLMs are you in search of? 34902 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801