opt-13b / flax_model.msgpack.index.json
ArthurZ's picture
ArthurZ HF staff
Add Flax weights (#5)
203cc9f
raw
history blame
56.8 kB
{
"metadata": {
"total_size": 25706946560
},
"weight_map": {
"model/decoder/embed_positions/embedding": "flax_model-00001-of-00003.msgpack",
"model/decoder/embed_tokens/embedding": "flax_model-00001-of-00003.msgpack",
"model/decoder/final_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/final_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/0/fc1/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/0/fc1/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/0/fc2/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/0/fc2/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/0/final_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/0/final_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/0/self_attn/k_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/0/self_attn/k_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/0/self_attn/out_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/0/self_attn/out_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/0/self_attn/q_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/0/self_attn/q_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/0/self_attn/v_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/0/self_attn/v_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/0/self_attn_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/0/self_attn_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/1/fc1/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/1/fc1/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/1/fc2/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/1/fc2/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/1/final_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/1/final_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/1/self_attn/k_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/1/self_attn/k_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/1/self_attn/out_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/1/self_attn/out_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/1/self_attn/q_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/1/self_attn/q_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/1/self_attn/v_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/1/self_attn/v_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/1/self_attn_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/1/self_attn_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/10/fc1/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/10/fc1/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/10/fc2/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/10/fc2/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/10/final_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/10/final_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/10/self_attn/k_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/10/self_attn/k_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/10/self_attn/out_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/10/self_attn/out_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/10/self_attn/q_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/10/self_attn/q_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/10/self_attn/v_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/10/self_attn/v_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/10/self_attn_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/10/self_attn_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/11/fc1/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/11/fc1/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/11/fc2/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/11/fc2/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/11/final_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/11/final_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/11/self_attn/k_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/11/self_attn/k_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/11/self_attn/out_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/11/self_attn/out_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/11/self_attn/q_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/11/self_attn/q_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/11/self_attn/v_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/11/self_attn/v_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/11/self_attn_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/11/self_attn_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/12/fc1/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/12/fc1/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/12/fc2/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/12/fc2/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/12/final_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/12/final_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/12/self_attn/k_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/12/self_attn/k_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/12/self_attn/out_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/12/self_attn/out_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/12/self_attn/q_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/12/self_attn/q_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/12/self_attn/v_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/12/self_attn/v_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/12/self_attn_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/12/self_attn_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/13/fc1/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/13/fc1/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/13/fc2/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/13/fc2/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/13/final_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/13/final_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/13/self_attn/k_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/13/self_attn/k_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/13/self_attn/out_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/13/self_attn/out_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/13/self_attn/q_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/13/self_attn/q_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/13/self_attn/v_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/13/self_attn/v_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/13/self_attn_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/13/self_attn_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/14/fc1/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/14/fc1/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/14/fc2/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/14/fc2/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/14/final_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/14/final_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/14/self_attn/k_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/14/self_attn/k_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/14/self_attn/out_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/14/self_attn/out_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/14/self_attn/q_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/14/self_attn/q_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/14/self_attn/v_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/14/self_attn/v_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/14/self_attn_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/14/self_attn_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/15/fc1/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/15/fc1/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/15/fc2/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/15/fc2/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/15/final_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/15/final_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/15/self_attn/k_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/15/self_attn/k_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/15/self_attn/out_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/15/self_attn/out_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/15/self_attn/q_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/15/self_attn/q_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/15/self_attn/v_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/15/self_attn/v_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/15/self_attn_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/15/self_attn_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/16/fc1/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/16/fc1/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/16/fc2/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/16/fc2/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/16/final_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/16/final_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/16/self_attn/k_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/16/self_attn/k_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/16/self_attn/out_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/16/self_attn/out_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/16/self_attn/q_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/16/self_attn/q_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/16/self_attn/v_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/16/self_attn/v_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/16/self_attn_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/16/self_attn_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/17/fc1/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/17/fc1/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/17/fc2/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/17/fc2/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/17/final_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/17/final_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/17/self_attn/k_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/17/self_attn/k_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/17/self_attn/out_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/17/self_attn/out_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/17/self_attn/q_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/17/self_attn/q_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/17/self_attn/v_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/17/self_attn/v_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/17/self_attn_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/17/self_attn_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/18/fc1/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/18/fc1/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/18/fc2/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/18/fc2/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/18/final_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/18/final_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/18/self_attn/k_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/18/self_attn/k_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/18/self_attn/out_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/18/self_attn/out_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/18/self_attn/q_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/18/self_attn/q_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/18/self_attn/v_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/18/self_attn/v_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/18/self_attn_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/18/self_attn_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/19/fc1/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/19/fc1/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/19/fc2/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/19/fc2/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/19/final_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/19/final_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/19/self_attn/k_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/19/self_attn/k_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/19/self_attn/out_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/19/self_attn/out_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/19/self_attn/q_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/19/self_attn/q_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/19/self_attn/v_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/19/self_attn/v_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/19/self_attn_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/19/self_attn_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/2/fc1/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/2/fc1/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/2/fc2/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/2/fc2/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/2/final_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/2/final_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/2/self_attn/k_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/2/self_attn/k_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/2/self_attn/out_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/2/self_attn/out_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/2/self_attn/q_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/2/self_attn/q_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/2/self_attn/v_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/2/self_attn/v_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/2/self_attn_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/2/self_attn_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/20/fc1/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/20/fc1/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/20/fc2/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/20/fc2/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/20/final_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/20/final_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/20/self_attn/k_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/20/self_attn/k_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/20/self_attn/out_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/20/self_attn/out_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/20/self_attn/q_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/20/self_attn/q_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/20/self_attn/v_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/20/self_attn/v_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/20/self_attn_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/20/self_attn_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/21/fc1/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/21/fc1/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/21/fc2/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/21/fc2/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/21/final_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/21/final_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/21/self_attn/k_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/21/self_attn/k_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/21/self_attn/out_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/21/self_attn/out_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/21/self_attn/q_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/21/self_attn/q_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/21/self_attn/v_proj/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/21/self_attn/v_proj/kernel": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/21/self_attn_layer_norm/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/21/self_attn_layer_norm/scale": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/22/fc1/bias": "flax_model-00001-of-00003.msgpack",
"model/decoder/layers/22/fc1/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/22/fc2/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/22/fc2/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/22/final_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/22/final_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/22/self_attn/k_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/22/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/22/self_attn/out_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/22/self_attn/out_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/22/self_attn/q_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/22/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/22/self_attn/v_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/22/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/22/self_attn_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/22/self_attn_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/23/fc1/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/23/fc1/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/23/fc2/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/23/fc2/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/23/final_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/23/final_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/23/self_attn/k_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/23/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/23/self_attn/out_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/23/self_attn/out_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/23/self_attn/q_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/23/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/23/self_attn/v_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/23/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/23/self_attn_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/23/self_attn_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/24/fc1/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/24/fc1/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/24/fc2/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/24/fc2/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/24/final_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/24/final_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/24/self_attn/k_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/24/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/24/self_attn/out_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/24/self_attn/out_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/24/self_attn/q_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/24/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/24/self_attn/v_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/24/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/24/self_attn_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/24/self_attn_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/25/fc1/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/25/fc1/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/25/fc2/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/25/fc2/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/25/final_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/25/final_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/25/self_attn/k_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/25/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/25/self_attn/out_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/25/self_attn/out_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/25/self_attn/q_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/25/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/25/self_attn/v_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/25/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/25/self_attn_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/25/self_attn_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/26/fc1/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/26/fc1/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/26/fc2/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/26/fc2/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/26/final_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/26/final_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/26/self_attn/k_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/26/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/26/self_attn/out_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/26/self_attn/out_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/26/self_attn/q_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/26/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/26/self_attn/v_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/26/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/26/self_attn_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/26/self_attn_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/27/fc1/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/27/fc1/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/27/fc2/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/27/fc2/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/27/final_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/27/final_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/27/self_attn/k_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/27/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/27/self_attn/out_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/27/self_attn/out_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/27/self_attn/q_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/27/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/27/self_attn/v_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/27/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/27/self_attn_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/27/self_attn_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/28/fc1/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/28/fc1/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/28/fc2/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/28/fc2/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/28/final_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/28/final_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/28/self_attn/k_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/28/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/28/self_attn/out_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/28/self_attn/out_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/28/self_attn/q_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/28/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/28/self_attn/v_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/28/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/28/self_attn_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/28/self_attn_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/29/fc1/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/29/fc1/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/29/fc2/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/29/fc2/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/29/final_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/29/final_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/29/self_attn/k_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/29/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/29/self_attn/out_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/29/self_attn/out_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/29/self_attn/q_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/29/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/29/self_attn/v_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/29/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/29/self_attn_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/29/self_attn_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/3/fc1/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/3/fc1/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/3/fc2/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/3/fc2/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/3/final_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/3/final_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/3/self_attn/k_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/3/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/3/self_attn/out_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/3/self_attn/out_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/3/self_attn/q_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/3/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/3/self_attn/v_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/3/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/3/self_attn_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/3/self_attn_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/30/fc1/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/30/fc1/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/30/fc2/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/30/fc2/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/30/final_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/30/final_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/30/self_attn/k_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/30/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/30/self_attn/out_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/30/self_attn/out_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/30/self_attn/q_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/30/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/30/self_attn/v_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/30/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/30/self_attn_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/30/self_attn_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/31/fc1/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/31/fc1/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/31/fc2/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/31/fc2/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/31/final_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/31/final_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/31/self_attn/k_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/31/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/31/self_attn/out_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/31/self_attn/out_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/31/self_attn/q_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/31/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/31/self_attn/v_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/31/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/31/self_attn_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/31/self_attn_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/32/fc1/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/32/fc1/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/32/fc2/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/32/fc2/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/32/final_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/32/final_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/32/self_attn/k_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/32/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/32/self_attn/out_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/32/self_attn/out_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/32/self_attn/q_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/32/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/32/self_attn/v_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/32/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/32/self_attn_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/32/self_attn_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/33/fc1/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/33/fc1/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/33/fc2/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/33/fc2/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/33/final_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/33/final_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/33/self_attn/k_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/33/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/33/self_attn/out_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/33/self_attn/out_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/33/self_attn/q_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/33/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/33/self_attn/v_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/33/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/33/self_attn_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/33/self_attn_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/34/fc1/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/34/fc1/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/34/fc2/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/34/fc2/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/34/final_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/34/final_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/34/self_attn/k_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/34/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/34/self_attn/out_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/34/self_attn/out_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/34/self_attn/q_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/34/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/34/self_attn/v_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/34/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/34/self_attn_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/34/self_attn_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/35/fc1/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/35/fc1/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/35/fc2/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/35/fc2/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/35/final_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/35/final_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/35/self_attn/k_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/35/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/35/self_attn/out_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/35/self_attn/out_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/35/self_attn/q_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/35/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/35/self_attn/v_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/35/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/35/self_attn_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/35/self_attn_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/36/fc1/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/36/fc1/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/36/fc2/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/36/fc2/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/36/final_layer_norm/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/36/final_layer_norm/scale": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/36/self_attn/k_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/36/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/36/self_attn/out_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/36/self_attn/out_proj/kernel": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/36/self_attn/q_proj/bias": "flax_model-00002-of-00003.msgpack",
"model/decoder/layers/36/self_attn/q_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/36/self_attn/v_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/36/self_attn/v_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/36/self_attn_layer_norm/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/36/self_attn_layer_norm/scale": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/37/fc1/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/37/fc1/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/37/fc2/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/37/fc2/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/37/final_layer_norm/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/37/final_layer_norm/scale": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/37/self_attn/k_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/37/self_attn/k_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/37/self_attn/out_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/37/self_attn/out_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/37/self_attn/q_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/37/self_attn/q_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/37/self_attn/v_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/37/self_attn/v_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/37/self_attn_layer_norm/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/37/self_attn_layer_norm/scale": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/38/fc1/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/38/fc1/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/38/fc2/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/38/fc2/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/38/final_layer_norm/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/38/final_layer_norm/scale": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/38/self_attn/k_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/38/self_attn/k_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/38/self_attn/out_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/38/self_attn/out_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/38/self_attn/q_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/38/self_attn/q_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/38/self_attn/v_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/38/self_attn/v_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/38/self_attn_layer_norm/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/38/self_attn_layer_norm/scale": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/39/fc1/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/39/fc1/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/39/fc2/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/39/fc2/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/39/final_layer_norm/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/39/final_layer_norm/scale": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/39/self_attn/k_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/39/self_attn/k_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/39/self_attn/out_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/39/self_attn/out_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/39/self_attn/q_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/39/self_attn/q_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/39/self_attn/v_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/39/self_attn/v_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/39/self_attn_layer_norm/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/39/self_attn_layer_norm/scale": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/4/fc1/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/4/fc1/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/4/fc2/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/4/fc2/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/4/final_layer_norm/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/4/final_layer_norm/scale": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/4/self_attn/k_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/4/self_attn/k_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/4/self_attn/out_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/4/self_attn/out_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/4/self_attn/q_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/4/self_attn/q_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/4/self_attn/v_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/4/self_attn/v_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/4/self_attn_layer_norm/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/4/self_attn_layer_norm/scale": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/5/fc1/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/5/fc1/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/5/fc2/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/5/fc2/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/5/final_layer_norm/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/5/final_layer_norm/scale": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/5/self_attn/k_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/5/self_attn/k_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/5/self_attn/out_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/5/self_attn/out_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/5/self_attn/q_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/5/self_attn/q_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/5/self_attn/v_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/5/self_attn/v_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/5/self_attn_layer_norm/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/5/self_attn_layer_norm/scale": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/6/fc1/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/6/fc1/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/6/fc2/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/6/fc2/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/6/final_layer_norm/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/6/final_layer_norm/scale": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/6/self_attn/k_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/6/self_attn/k_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/6/self_attn/out_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/6/self_attn/out_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/6/self_attn/q_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/6/self_attn/q_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/6/self_attn/v_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/6/self_attn/v_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/6/self_attn_layer_norm/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/6/self_attn_layer_norm/scale": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/7/fc1/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/7/fc1/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/7/fc2/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/7/fc2/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/7/final_layer_norm/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/7/final_layer_norm/scale": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/7/self_attn/k_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/7/self_attn/k_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/7/self_attn/out_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/7/self_attn/out_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/7/self_attn/q_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/7/self_attn/q_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/7/self_attn/v_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/7/self_attn/v_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/7/self_attn_layer_norm/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/7/self_attn_layer_norm/scale": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/8/fc1/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/8/fc1/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/8/fc2/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/8/fc2/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/8/final_layer_norm/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/8/final_layer_norm/scale": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/8/self_attn/k_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/8/self_attn/k_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/8/self_attn/out_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/8/self_attn/out_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/8/self_attn/q_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/8/self_attn/q_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/8/self_attn/v_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/8/self_attn/v_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/8/self_attn_layer_norm/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/8/self_attn_layer_norm/scale": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/9/fc1/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/9/fc1/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/9/fc2/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/9/fc2/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/9/final_layer_norm/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/9/final_layer_norm/scale": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/9/self_attn/k_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/9/self_attn/k_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/9/self_attn/out_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/9/self_attn/out_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/9/self_attn/q_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/9/self_attn/q_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/9/self_attn/v_proj/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/9/self_attn/v_proj/kernel": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/9/self_attn_layer_norm/bias": "flax_model-00003-of-00003.msgpack",
"model/decoder/layers/9/self_attn_layer_norm/scale": "flax_model-00003-of-00003.msgpack"
}
}