e52be9bba2
Deepseek V2 is a MoE model from Deepseek. Relevant variations
compared to other models:
- Grouped top-K in expert selection.
- mscale in yarn is calculated using the `mscale` and `mscale_all_dim`
configuration options.
- `mscale_all_dim` is also used in scaling attention softmax.
- Permuting of the query/key representations before applying rotary
embeddings.
- Some projections cannot be sharded (`q_a_proj`, `kv_a_proj_with_mqa`).
So, we need weight loads that supports quantized weights. To this
end `{Weights,WeightLoader}.get_weight` was added.
- The query/key head dimensionality differs from that of the value,
so we need to pad during attention.
- Heads with size 192, needs an extension to our paged attention
fork and we need to ensure that the KV cache is allocated with the
correct size.
- Shared experts.
|
||
|---|---|---|
| .. | ||
| custom_modeling | ||
| __init__.py | ||
| bloom.py | ||
| causal_lm.py | ||
| flash_causal_lm.py | ||
| flash_mistral.py | ||
| galactica.py | ||
| globals.py | ||
| idefics.py | ||
| idefics_causal_lm.py | ||
| mamba.py | ||
| model.py | ||
| pali_gemma.py | ||
| seq2seq_lm.py | ||
| types.py | ||
| vlm_causal_lm.py | ||