LLM Name | EvolCodeLlama 7B |
Repository ๐ค | https://huggingface.co/actionpace/EvolCodeLlama-7b |
Base Model(s) | |
Model Size | 7b |
Required VRAM | 13.5 GB |
Updated | 2024-11-21 |
Maintainer | actionpace |
Model Files | |
GGUF Quantization | Yes |
Quantization Type | q8|gguf |
Model Architecture | AutoModelForCausalLM |
Is Biased | none |
Tokenizer Class | CodeLlamaTokenizer |
PEFT Type | LORA |
LoRA Model | Yes |
PEFT Target Modules | up_proj|v_proj|o_proj|down_proj|gate_proj|q_proj|k_proj |
LoRA Alpha | 16 |
LoRA Dropout | 0.05 |
R Param | 32 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
ReWiz 7B | 0K / 14.5 GB | 517 | 0 |
Boptruth NeuralMonarch 7B | 0K / 14.4 GB | 494 | 2 |
...rendyol 7B Base V1 MtLoRA Entr | 0K / 14.6 GB | 98 | 0 |
Mistral Llm V4 | 0K / 14.4 GB | 15 | 0 |
Mistral 7B V0.1 Hitl | 0K / 14.4 GB | 5 | 0 |
Gemma 7B English To Hinglish | 0K / 17.1 GB | 34 | 0 |
...rix Philosophy Mistral 7B LoRA | 0K / 14.4 GB | 928 | 5 |
Gumzo Llama 00 | 0K / 0.3 GB | 37 | 0 |
Legal Summarizer | 0K / 14.4 GB | 37 | 0 |
Medilora Mistral 7B | 0K / 14.4 GB | 180 | 4 |
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