LLM Name | RunpodV1 Merged 16bit |
Repository ๐ค | https://huggingface.co/Gragroo/runpodV1-merged_16bit |
Base Model(s) | |
Merged Model | Yes |
Model Size | 3b |
Updated | 2024-11-02 |
Maintainer | Gragroo |
Model Type | llama |
Instruction-Based | Yes |
Quantization Type | 4bit |
Model Architecture | LlamaForCausalLM |
License | apache-2.0 |
Context Length | 131072 |
Model Max Length | 131072 |
Transformers Version | 4.44.2 |
Vocabulary Size | 128256 |
Torch Data Type | bfloat16 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
TaraV2 M16B | 0 | 483 | 6 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Llama 3.2 3B Instruct Bnb 4bit | 128K / 2.2 GB | 218065 | 15 |
Llama Magpie 3.2 3B Instruct | 128K / 6.5 GB | 32 | 7 |
Llama 3.2 3B Instruct 4bit | 128K / 1.8 GB | 35271 | 19 |
Llama Sentient 3.2 3B Instruct | 128K / 6.5 GB | 335 | 9 |
...truct Gptqmodel 4bit Vortex V3 | 128K / 3.2 GB | 1640 | 3 |
...Llama 3.2 3B Instruct Bnb 4bit | 128K / 6.5 GB | 53 | 1 |
Llama 3.2 3B Overthinker | 128K / 6.5 GB | 272 | 18 |
TaraV1 M16B | 128K / 6.5 GB | 624 | 0 |
...nstruct Medical Conversational | 128K / 6.5 GB | 1038 | 6 |
ISLEXITAS WELSPUN 7L 29 11 24 | 128K / 6.5 GB | 25 | 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