Model Type |
| ||||||||||||
Supported Languages |
| ||||||||||||
Training Details |
|
LLM Name | Llama 3 IMPACTS 2x8B 64K MLX |
Repository ๐ค | https://huggingface.co/Severian/Llama-3-IMPACTS-2x8B-64k-MLX |
Required VRAM | 27.4 GB |
Updated | 2025-02-22 |
Maintainer | Severian |
Model Type | mixtral |
Model Files | |
Supported Languages | en |
Model Architecture | MixtralForCausalLM |
License | mit |
Context Length | 65536 |
Model Max Length | 65536 |
Transformers Version | 4.41.0.dev0 |
Tokenizer Class | PreTrainedTokenizerFast |
Padding Token | <|begin_of_text|> |
Vocabulary Size | 128256 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
BiMediX Bi | 32K / 93.6 GB | 12147 | 5 |
Dolphin 2.7 Mixtral 8x7b | 32K / 93.6 GB | 4073 | 169 |
Dolphin 2.6 Mixtral 8x7b | 32K / 93.6 GB | 4058 | 206 |
...eqlen 4096 Bs 4 Optimum 0 0 23 | 32K / GB | 5 | 0 |
...eqlen 4096 Bs 4 Optimum 0 0 23 | 32K / GB | 6 | 1 |
Empower Functions Medium | 32K / 93.6 GB | 12 | 1 |
Synatra Mixtral 8x7B | 32K / 93.6 GB | 1791 | 14 |
Mixtral 8x7B Instruct V0.1 | 32K / GB | 7 | 0 |
...ral 8x7b Instruct V0.1 Int4 Ov | 32K / 0 GB | 56 | 4 |
Mixtral Megamerge Dare 8x7b V1 | 32K / 93.6 GB | 2031 | 1 |
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