Adapter Base model:mistralai/mistral-7... Dataset:helsinki-nlp/opus para... Dataset:turuta/multi30k-uk En Finetuned Ggml License:apache-2.0 Lora Model-index Peft Quantized Region:us Safetensors Translation Uk
Dragoman Benchmarks
Rank the Dragoman 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 Dragoman
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| ...1 Fine Tuned Using Ludwig 4bit | 60.1 | 0K / 0 GB | 1 | 1 |
| Mistral Chess | 60.1 | 0K / 2.7 GB | 94 | 0 |
| Mistral Finetuned DialogSumm | 47.9 | 0K / 0 GB | 7 | 1 |
| ...1 Fine Tuned Using Ludwig 4bit | 40.4 | 0K / 0 GB | 1 | 1 |
| Llama 2 Medical Consultation | — | 0K / 0 GB | 47 | 3 |
| Falcon 7B Spanish 8bit | — | 0K / 0 GB | 6 | 3 |
| Llama 2 7B Hf Codealpaca 4bit | — | 0K / 0 GB | 1 | 1 |
| Falcon 7B Instruct 4bit Lora | — | 0K / 0 GB | 0 | 1 |
| Gemma 7B Us Minecraft | — | 0K / 0 GB | 30 | 0 |
| Gemma7b SFT | — | 0K / 0 GB | 10 | 0 |
Dragoman Parameters and Internals
| LLM Name | Dragoman |
| Repository | Open on 🤗 |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 2.7 GB |
| Updated | 2024-07-05 |
| Maintainer | lang-uk |
| Model Files | |
| Supported Languages | uk en |
| GGML Quantization | Yes |
| Quantization Type | ggml |
| Model Architecture | Adapter |
| License | apache-2.0 |
| Is Biased | none |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | up_proj|q_proj|v_proj|gate_proj|o_proj|lm_head|down_proj|k_proj |
| LoRA Alpha | 128 |
| LoRA Dropout | 0.05 |
| R Param | 256 |
What open-source LLMs or SLMs are you in search of? 34431 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801