Available Models
Model | Video Model | CausalLM | AttentionModule | Parameters Quantization | Operation Bit Quantization |
---|---|---|---|---|---|
Gptj | ❌ | ✅ | ✅ | ✅ | ✅ |
LucidTransformer | ❌ | ✅ | ✅ | ✅ | ✅ |
Mixtral | ✅ | ✅ | ✅ | ✅ | ✅ |
Opt | ❌ | ✅ | ✅ | ✅ | ✅ |
Qwen2Moe | ❌ | ✅ | ✅ | ✅ | ✅ |
Stablelm | ❌ | ✅ | ✅ | ✅ | ✅ |
Cohere | ❌ | ✅ | ✅ | ✅ | ✅ |
Arctic | ❌ | ✅ | ✅ | ✅ | ✅ |
OpenELM | ❌ | ✅ | ✅ | ✅ | ✅ |
Gemma | ❌ | ✅ | ✅ | ✅ | ✅ |
GptNeoX | ❌ | ✅ | ✅ | ✅ | ✅ |
Jetmoe | ❌ | ✅ | ✅ | ✅ | ✅ |
Mamba | ❌ | ✅ | ❌ | ✅ | ✅ |
MosaicMpt | ❌ | ✅ | ✅ | ✅ | ✅ |
Palm | ❌ | ✅ | ✅ | ✅ | ✅ |
Qwen1 | ❌ | ✅ | ✅ | ✅ | ✅ |
Roberta | ❌ | ✅ | ✅ | ✅ | ✅ |
T5 | ❌ | ✅ | ✅ | ✅ | ✅ |
Dbrx | ❌ | ✅ | ✅ | ✅ | ✅ |
Falcon | ❌ | ✅ | ✅ | ✅ | ✅ |
Gpt2 | ❌ | ✅ | ✅ | ✅ | ✅ |
Grok1 | ❌ | ✅ | ✅ | ✅ | ✅ |
Llama | ✅ | ✅ | ✅ | ✅ | ✅ |
Mistral | ✅ | ✅ | ✅ | ✅ | ✅ |
Olmo | ❌ | ✅ | ✅ | ✅ | ✅ |
Phi | ❌ | ✅ | ✅ | ✅ | ✅ |
Phi 3 | ❌ | ✅ | ✅ | ✅ | ✅ |
Qwen2 | ❌ | ✅ | ✅ | ✅ | ✅ |
Rwkv | ❌ | ✅ | ❌ | ✅ | ✅ |
Whisper | ❌ | ✅ | ✅ | ✅ | ✅ |
you can also tell me the model you want in Flax/Jax version and ill try my best to build it ;)
More Models might have been added to
~HEAD
but not mentioned here