LLM Name | Gemma Pragma |
Repository | Open on ๐ค |
Required VRAM | 0.1 GB |
Updated | 2024-07-26 |
Maintainer | kursathalat |
Model Files | |
Model Architecture | AutoModelForCausalLM |
Is Biased | none |
Tokenizer Class | GemmaTokenizer |
Padding Token | <pad> |
PEFT Type | LORA |
LoRA Model | Yes |
PEFT Target Modules | v_proj|down_proj|o_proj|q_proj|k_proj|up_proj|gate_proj |
LoRA Alpha | 8 |
LoRA Dropout | 0 |
R Param | 8 |
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
---|---|---|---|---|
Tiny Llama Miniguanaco | 0.2 | 2K / 2.2 GB | 7 | 1 |
Finetuned Llava Lora | 0.3 | 0K / 0.1 GB | 199 | 0 |
Qwen7B Haiguitang | 0.3 | 0K / 15.3 GB | 56 | 0 |
Modelv3 | 0.3 | 0K / 13.5 GB | 42 | 0 |
Transliteration Llama | 0.2 | 0K / 0.1 GB | 57 | 0 |
Alphace Email | 0.2 | 0K / 0.1 GB | 19 | 0 |
Partis Goodone | 0.2 | 0K / 16.1 GB | 16 | 1 |
Accel | 0.2 | 0K / 0 GB | 8 | 0 |
Chinese Poetry Generation | 0.2 | 0K / 0 GB | 7 | 0 |
Keywords Generator | 0.2 | 0K / 0 GB | 15 | 0 |
๐ 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! ๐