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
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
---|---|---|---|---|
Mistral 7B V0.1 GGUF | 60.1 | 0K / 2.7 GB | 176 | 0 |
Mistral 7B V0.1 GGUF | 60.1 | 0K / 3.1 GB | 8214 | 237 |
Mistral 7B V0.1 GGUF | 60.1 | 0K / 4.4 GB | 47 | 0 |
...edia Ru Pruned 0.1 Merged GGUF | 60.1 | 0K / 7.7 GB | 43 | 0 |
Mistral 7B Instruct V0.1 GGUF | 54.6 | 0K / 2.7 GB | 198 | 1 |
Mistral 7B Instruct V0.1 GGUF | 54.6 | 0K / 3.1 GB | 57481 | 495 |
Notus 7B V1 GGUF | 52.8 | 0K / 2.7 GB | 193 | 0 |
Notus 7B V1 GGUF | 52.8 | 0K / 3.1 GB | 625 | 23 |
Vicuna 7B V1.5 GGUF | 48.5 | 0K / 2.8 GB | 1880 | 15 |
Vicuna 7B V1.5 GGML | 48.5 | 0K / 2.9 GB | 3 | 14 |
LLM Name | Gemma Swahili Mollel 1 Epoch |
Repository | Open on ๐ค |
Base Model(s) | |
Model Size | 7b |
Required VRAM | 0.2 GB |
Updated | 2024-07-05 |
Maintainer | Mollel |
Model Files | |
Supported Languages | en sw |
Quantization Type | 4bit |
Model Architecture | AutoModel |
License | apache-2.0 |
Model Max Length | 8192 |
Is Biased | none |
Tokenizer Class | GemmaTokenizer |
Padding Token | <pad> |
PEFT Type | LORA |
LoRA Model | Yes |
PEFT Target Modules | down_proj|o_proj|up_proj|k_proj|q_proj|gate_proj|v_proj |
LoRA Alpha | 16 |
LoRA Dropout | 0 |
R Param | 16 |