LLM Name | Mixtral Instruct Seqlen 4096 Bs 4 Optimum 0 0 23 |
Repository | Open on ๐ค |
Updated | 2024-07-27 |
Maintainer | aws-neuron |
Model Type | mixtral |
Instruction-Based | Yes |
Model Architecture | MixtralForCausalLM |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.41.1 |
Tokenizer Class | LlamaTokenizer |
Vocabulary Size | 32000 |
Torch Data Type | bfloat16 |
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
---|---|---|---|---|
WizardLM 2 8x22B Beige | 0.2 | 64K / 221.4 GB | 23 | 3 |
Dolphin 2.7 Mixtral 8x7b | 0.3 | 32K / 93.6 GB | 8116 | 154 |
Dolphin 2.6 Mixtral 8x7b | 0.3 | 32K / 93.6 GB | 4852 | 184 |
...eqlen 4096 Bs 4 Optimum 0 0 23 | 0.3 | 32K / GB | 166 | 0 |
Mixtral 8x7B Instruct V0.1 HF | 0.2 | 32K / 93.6 GB | 29939 | 2 |
Empower Functions Medium | 0.2 | 32K / 93.6 GB | 5 | 1 |
...ral 8x7b Instruct V0.1 Int4 Ov | 0.2 | 32K / 0 GB | 150 | 2 |
Mixtral 8x7B Instruct V0.1 | 0.2 | 32K / GB | 7 | 0 |
...ct V0.1 Agent Function Calling | 0.2 | 32K / 44.3 GB | 7 | 2 |
...tral 8x7B Instruct V0.1 Polish | 0.2 | 32K / 93.6 GB | 7 | 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