LLM Name | MegaDolphin 120B |
Repository ๐ค | https://huggingface.co/cognitivecomputations/MegaDolphin-120b |
Base Model(s) | |
Merged Model | Yes |
Model Size | 70b |
Required VRAM | 240.7 GB |
Updated | 2024-09-18 |
Maintainer | cognitivecomputations |
Model Type | llama |
Instruction-Based | Yes |
Model Files | |
Supported Languages | en |
Model Architecture | LlamaForCausalLM |
License | llama2 |
Context Length | 4096 |
Model Max Length | 4096 |
Transformers Version | 4.36.2 |
Tokenizer Class | LlamaTokenizer |
Padding Token | </s> |
Vocabulary Size | 32002 |
Torch Data Type | float16 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
MegaDolphin 120B AWQ | 2 | 170 | 63 GB |
MegaDolphin 120B GGUF | 23 | 2 | 0 GB |
MegaDolphin 120B GPTQ | 4 | 7 | 61 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
... 3 70B Instruct Gradient 1048K | 1024K / 141.9 GB | 1134 | 119 |
... Chat 1048K Chinese Llama3 70B | 1024K / 141.9 GB | 3261 | 5 |
Llama3 Function Calling 1048K | 1024K / 141.9 GB | 2 | 1 |
...a 3 70B Instruct Gradient 524K | 512K / 141.9 GB | 169 | 23 |
...a 3 70B Instruct Gradient 262K | 256K / 141.9 GB | 200 | 55 |
...ama 3 70B Arimas Story RP V2.0 | 256K / 141.1 GB | 152 | 3 |
...ama 3 70B Arimas Story RP V1.5 | 256K / 141.2 GB | 146 | 2 |
...ama 3 70B Arimas Story RP V1.6 | 256K / 141.2 GB | 92 | 0 |
Meta Llama 3.1 70B Instruct | 128K / 141.9 GB | 358970 | 483 |
... 3.1 SauerkrautLM 70B Instruct | 128K / 141.1 GB | 2942 | 12 |
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