Model Type |
| |||||||||||||||
Use Cases |
| |||||||||||||||
Additional Notes |
| |||||||||||||||
Supported Languages |
| |||||||||||||||
Training Details |
| |||||||||||||||
Input Output |
| |||||||||||||||
Release Notes |
|
LLM Name | Kancil V0 Llama3 |
Repository ๐ค | https://huggingface.co/afrizalha/Kancil-V0-llama3 |
Model Size | 4.7b |
Required VRAM | 5.8 GB |
Updated | 2025-06-09 |
Maintainer | afrizalha |
Model Files | |
Supported Languages | id |
Model Architecture | AutoModelForCausalLM |
License | llama3 |
Model Max Length | 8192 |
Is Biased | none |
Tokenizer Class | PreTrainedTokenizerFast |
Padding Token | <|end_of_text|> |
PEFT Type | LORA |
LoRA Model | Yes |
PEFT Target Modules | down_proj|q_proj|k_proj|o_proj|up_proj|gate_proj|v_proj |
LoRA Alpha | 64 |
LoRA Dropout | 0 |
R Param | 64 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
ARFLLaMa | 0K / 5.8 GB | 18 | 0 |
Soro 34K 1 | 0K / 5.8 GB | 16 | 0 |
...Llm Finetuned V3 High Accuracy | 0K / 5.8 GB | 15 | 1 |
KoLlamaCredit | 0K / 8.3 GB | 13 | 0 |
Llama3 Petro Instruct V1 | 0K / 5.8 GB | 14 | 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