Models
Docs
Pricing
Sign in
Download
Models
Download
Docs
Pricing
Sign in
michaelmontuori
/
gemma-4-E4B-it-GGUF
:UD-Q4_K_XL-128k
14
Downloads
Updated
3 days ago
Initially built this E4B model to fit in my RTX 4060 with 8GB
Initially built this E4B model to fit in my RTX 4060 with 8GB
Cancel
vision
tools
thinking
gemma-4-E4B-it-GGUF:UD-Q4_K_XL-128k
...
/
projector
ee01cba03fd9 · 992MB
Metadata
general.architecture
clip
clip
general.file_type
BF16
BF16
clip.audio.attention.head_count
8
8
clip.audio.attention.layer_norm_epsilon
1e-05
1e-05
clip.audio.block_count
12
12
clip.audio.embedding_length
1024
1024
clip.audio.feed_forward_length
4096
4096
clip.audio.num_mel_bins
128
128
clip.audio.projection_dim
2560
2560
clip.audio.projector_type
gemma4a
gemma4a
clip.has_audio_encoder
true
true
clip.has_vision_encoder
true
true
clip.vision.attention.head_count
12
12
clip.vision.attention.layer_norm_epsilon
1e-06
1e-06
clip.vision.block_count
16
16
clip.vision.embedding_length
768
768
clip.vision.feed_forward_length
3072
3072
clip.vision.image_mean
[0, 0, 0]
[0, 0, 0]
clip.vision.image_size
224
224
clip.vision.image_std
[1, 1, 1]
[1, 1, 1]
clip.vision.patch_size
16
16
clip.vision.projection_dim
2560
2560
clip.vision.projector_type
gemma4v
gemma4v
Tensor
Name
Type
Shape
a.blk.0
a.blk.0.attn_k.input_max
F32
F32
[1]
a.blk.0.attn_k.input_min
F32
F32
[1]
a.blk.0.attn_k.output_max
F32
F32
[1]
a.blk.0.attn_k.output_min
F32
F32
[1]
a.blk.0.attn_k.weight
BF16
BF16
[1024, 1024]
a.blk.0.attn_k_rel.weight
BF16
BF16
[1024, 1024]
a.blk.0.attn_out.input_max
F32
F32
[1]
a.blk.0.attn_out.input_min
F32
F32
[1]
a.blk.0.attn_out.output_max
F32
F32
[1]
a.blk.0.attn_out.output_min
F32
F32
[1]
a.blk.0.attn_out.weight
BF16
BF16
[1024, 1024]
a.blk.0.attn_post_norm.weight
F32
F32
[1024]
a.blk.0.attn_pre_norm.weight
F32
F32
[1024]
a.blk.0.attn_q.input_max
F32
F32
[1]
a.blk.0.attn_q.input_min
F32
F32
[1]
a.blk.0.attn_q.output_max
F32
F32
[1]
a.blk.0.attn_q.output_min
F32
F32
[1]
a.blk.0.attn_q.weight
BF16
BF16
[1024, 1024]
a.blk.0.attn_v.input_max
F32
F32
[1]
a.blk.0.attn_v.input_min
F32
F32
[1]
a.blk.0.attn_v.output_max
F32
F32
[1]
a.blk.0.attn_v.output_min
F32
F32
[1]
a.blk.0.attn_v.weight
BF16
BF16
[1024, 1024]
a.blk.0.conv_dw.weight
F32
F32
[5, 1024]
a.blk.0.conv_norm.weight
F32
F32
[1024]
a.blk.0.conv_pw1.input_max
F32
F32
[1]
a.blk.0.conv_pw1.input_min
F32
F32
[1]
a.blk.0.conv_pw1.output_max
F32
F32
[1]
a.blk.0.conv_pw1.output_min
F32
F32
[1]
a.blk.0.conv_pw1.weight
BF16
BF16
[1024, 2048]
a.blk.0.conv_pw2.input_max
F32
F32
[1]
a.blk.0.conv_pw2.input_min
F32
F32
[1]
a.blk.0.conv_pw2.output_max
F32
F32
[1]
a.blk.0.conv_pw2.output_min
F32
F32
[1]
a.blk.0.conv_pw2.weight
BF16
BF16
[1024, 1024]
a.blk.0.ffn_down.input_max
F32
F32
[1]
a.blk.0.ffn_down.input_min
F32
F32
[1]
a.blk.0.ffn_down.output_max
F32
F32
[1]
a.blk.0.ffn_down.output_min
F32
F32
[1]
a.blk.0.ffn_down.weight
BF16
BF16
[4096, 1024]
a.blk.0.ffn_down_1.input_max
F32
F32
[1]
a.blk.0.ffn_down_1.input_min
F32
F32
[1]
a.blk.0.ffn_down_1.output_max
F32
F32
[1]
a.blk.0.ffn_down_1.output_min
F32
F32
[1]
a.blk.0.ffn_down_1.weight
BF16
BF16
[4096, 1024]
a.blk.0.ffn_norm.weight
F32
F32
[1024]
a.blk.0.ffn_norm_1.weight
F32
F32
[1024]
a.blk.0.ffn_post_norm.weight
F32
F32
[1024]
a.blk.0.ffn_post_norm_1.weight
F32
F32
[1024]
a.blk.0.ffn_up.input_max
F32
F32
[1]
a.blk.0.ffn_up.input_min
F32
F32
[1]
a.blk.0.ffn_up.output_max
F32
F32
[1]
a.blk.0.ffn_up.output_min
F32
F32
[1]
a.blk.0.ffn_up.weight
BF16
BF16
[1024, 4096]
a.blk.0.ffn_up_1.input_max
F32
F32
[1]
a.blk.0.ffn_up_1.input_min
F32
F32
[1]
a.blk.0.ffn_up_1.output_max
F32
F32
[1]
a.blk.0.ffn_up_1.output_min
F32
F32
[1]
a.blk.0.ffn_up_1.weight
BF16
BF16
[1024, 4096]
a.blk.0.ln2.weight
F32
F32
[1024]
a.blk.0.norm_conv.weight
F32
F32
[1024]
a.blk.0.per_dim_scale.weight
F32
F32
[128]
a.blk.1
a.blk.1.attn_k.input_max
F32
F32
[1]
a.blk.1.attn_k.input_min
F32
F32
[1]
a.blk.1.attn_k.output_max
F32
F32
[1]
a.blk.1.attn_k.output_min
F32
F32
[1]
a.blk.1.attn_k.weight
BF16
BF16
[1024, 1024]
a.blk.1.attn_k_rel.weight
BF16
BF16
[1024, 1024]
a.blk.1.attn_out.input_max
F32
F32
[1]
a.blk.1.attn_out.input_min
F32
F32
[1]
a.blk.1.attn_out.output_max
F32
F32
[1]
a.blk.1.attn_out.output_min
F32
F32
[1]
a.blk.1.attn_out.weight
BF16
BF16
[1024, 1024]
a.blk.1.attn_post_norm.weight
F32
F32
[1024]
a.blk.1.attn_pre_norm.weight
F32
F32
[1024]
a.blk.1.attn_q.input_max
F32
F32
[1]
a.blk.1.attn_q.input_min
F32
F32
[1]
a.blk.1.attn_q.output_max
F32
F32
[1]
a.blk.1.attn_q.output_min
F32
F32
[1]
a.blk.1.attn_q.weight
BF16
BF16
[1024, 1024]
a.blk.1.attn_v.input_max
F32
F32
[1]
a.blk.1.attn_v.input_min
F32
F32
[1]
a.blk.1.attn_v.output_max
F32
F32
[1]
a.blk.1.attn_v.output_min
F32
F32
[1]
a.blk.1.attn_v.weight
BF16
BF16
[1024, 1024]
a.blk.1.conv_dw.weight
F32
F32
[5, 1024]
a.blk.1.conv_norm.weight
F32
F32
[1024]
a.blk.1.conv_pw1.input_max
F32
F32
[1]
a.blk.1.conv_pw1.input_min
F32
F32
[1]
a.blk.1.conv_pw1.output_max
F32
F32
[1]
a.blk.1.conv_pw1.output_min
F32
F32
[1]
a.blk.1.conv_pw1.weight
BF16
BF16
[1024, 2048]
a.blk.1.conv_pw2.input_max
F32
F32
[1]
a.blk.1.conv_pw2.input_min
F32
F32
[1]
a.blk.1.conv_pw2.output_max
F32
F32
[1]
a.blk.1.conv_pw2.output_min
F32
F32
[1]
a.blk.1.conv_pw2.weight
BF16
BF16
[1024, 1024]
a.blk.1.ffn_down.input_max
F32
F32
[1]
a.blk.1.ffn_down.input_min
F32
F32
[1]
a.blk.1.ffn_down.output_max
F32
F32
[1]
a.blk.1.ffn_down.output_min
F32
F32
[1]
a.blk.1.ffn_down.weight
BF16
BF16
[4096, 1024]
a.blk.1.ffn_down_1.input_max
F32
F32
[1]
a.blk.1.ffn_down_1.input_min
F32
F32
[1]
a.blk.1.ffn_down_1.output_max
F32
F32
[1]
a.blk.1.ffn_down_1.output_min
F32
F32
[1]
a.blk.1.ffn_down_1.weight
BF16
BF16
[4096, 1024]
a.blk.1.ffn_norm.weight
F32
F32
[1024]
a.blk.1.ffn_norm_1.weight
F32
F32
[1024]
a.blk.1.ffn_post_norm.weight
F32
F32
[1024]
a.blk.1.ffn_post_norm_1.weight
F32
F32
[1024]
a.blk.1.ffn_up.input_max
F32
F32
[1]
a.blk.1.ffn_up.input_min
F32
F32
[1]
a.blk.1.ffn_up.output_max
F32
F32
[1]
a.blk.1.ffn_up.output_min
F32
F32
[1]
a.blk.1.ffn_up.weight
BF16
BF16
[1024, 4096]
a.blk.1.ffn_up_1.input_max
F32
F32
[1]
a.blk.1.ffn_up_1.input_min
F32
F32
[1]
a.blk.1.ffn_up_1.output_max
F32
F32
[1]
a.blk.1.ffn_up_1.output_min
F32
F32
[1]
a.blk.1.ffn_up_1.weight
BF16
BF16
[1024, 4096]
a.blk.1.ln2.weight
F32
F32
[1024]
a.blk.1.norm_conv.weight
F32
F32
[1024]
a.blk.1.per_dim_scale.weight
F32
F32
[128]
a.blk.2
a.blk.2.attn_k.input_max
F32
F32
[1]
a.blk.2.attn_k.input_min
F32
F32
[1]
a.blk.2.attn_k.output_max
F32
F32
[1]
a.blk.2.attn_k.output_min
F32
F32
[1]
a.blk.2.attn_k.weight
BF16
BF16
[1024, 1024]
a.blk.2.attn_k_rel.weight
BF16
BF16
[1024, 1024]
a.blk.2.attn_out.input_max
F32
F32
[1]
a.blk.2.attn_out.input_min
F32
F32
[1]
a.blk.2.attn_out.output_max
F32
F32
[1]
a.blk.2.attn_out.output_min
F32
F32
[1]
a.blk.2.attn_out.weight
BF16
BF16
[1024, 1024]
a.blk.2.attn_post_norm.weight
F32
F32
[1024]
a.blk.2.attn_pre_norm.weight
F32
F32
[1024]
a.blk.2.attn_q.input_max
F32
F32
[1]
a.blk.2.attn_q.input_min
F32
F32
[1]
a.blk.2.attn_q.output_max
F32
F32
[1]
a.blk.2.attn_q.output_min
F32
F32
[1]
a.blk.2.attn_q.weight
BF16
BF16
[1024, 1024]
a.blk.2.attn_v.input_max
F32
F32
[1]
a.blk.2.attn_v.input_min
F32
F32
[1]
a.blk.2.attn_v.output_max
F32
F32
[1]
a.blk.2.attn_v.output_min
F32
F32
[1]
a.blk.2.attn_v.weight
BF16
BF16
[1024, 1024]
a.blk.2.conv_dw.weight
F32
F32
[5, 1024]
a.blk.2.conv_norm.weight
F32
F32
[1024]
a.blk.2.conv_pw1.input_max
F32
F32
[1]
a.blk.2.conv_pw1.input_min
F32
F32
[1]
a.blk.2.conv_pw1.output_max
F32
F32
[1]
a.blk.2.conv_pw1.output_min
F32
F32
[1]
a.blk.2.conv_pw1.weight
BF16
BF16
[1024, 2048]
a.blk.2.conv_pw2.input_max
F32
F32
[1]
a.blk.2.conv_pw2.input_min
F32
F32
[1]
a.blk.2.conv_pw2.output_max
F32
F32
[1]
a.blk.2.conv_pw2.output_min
F32
F32
[1]
a.blk.2.conv_pw2.weight
BF16
BF16
[1024, 1024]
a.blk.2.ffn_down.input_max
F32
F32
[1]
a.blk.2.ffn_down.input_min
F32
F32
[1]
a.blk.2.ffn_down.output_max
F32
F32
[1]
a.blk.2.ffn_down.output_min
F32
F32
[1]
a.blk.2.ffn_down.weight
BF16
BF16
[4096, 1024]
a.blk.2.ffn_down_1.input_max
F32
F32
[1]
a.blk.2.ffn_down_1.input_min
F32
F32
[1]
a.blk.2.ffn_down_1.output_max
F32
F32
[1]
a.blk.2.ffn_down_1.output_min
F32
F32
[1]
a.blk.2.ffn_down_1.weight
BF16
BF16
[4096, 1024]
a.blk.2.ffn_norm.weight
F32
F32
[1024]
a.blk.2.ffn_norm_1.weight
F32
F32
[1024]
a.blk.2.ffn_post_norm.weight
F32
F32
[1024]
a.blk.2.ffn_post_norm_1.weight
F32
F32
[1024]
a.blk.2.ffn_up.input_max
F32
F32
[1]
a.blk.2.ffn_up.input_min
F32
F32
[1]
a.blk.2.ffn_up.output_max
F32
F32
[1]
a.blk.2.ffn_up.output_min
F32
F32
[1]
a.blk.2.ffn_up.weight
BF16
BF16
[1024, 4096]
a.blk.2.ffn_up_1.input_max
F32
F32
[1]
a.blk.2.ffn_up_1.input_min
F32
F32
[1]
a.blk.2.ffn_up_1.output_max
F32
F32
[1]
a.blk.2.ffn_up_1.output_min
F32
F32
[1]
a.blk.2.ffn_up_1.weight
BF16
BF16
[1024, 4096]
a.blk.2.ln2.weight
F32
F32
[1024]
a.blk.2.norm_conv.weight
F32
F32
[1024]
a.blk.2.per_dim_scale.weight
F32
F32
[128]
a.blk.3
a.blk.3.attn_k.input_max
F32
F32
[1]
a.blk.3.attn_k.input_min
F32
F32
[1]
a.blk.3.attn_k.output_max
F32
F32
[1]
a.blk.3.attn_k.output_min
F32
F32
[1]
a.blk.3.attn_k.weight
BF16
BF16
[1024, 1024]
a.blk.3.attn_k_rel.weight
BF16
BF16
[1024, 1024]
a.blk.3.attn_out.input_max
F32
F32
[1]
a.blk.3.attn_out.input_min
F32
F32
[1]
a.blk.3.attn_out.output_max
F32
F32
[1]
a.blk.3.attn_out.output_min
F32
F32
[1]
a.blk.3.attn_out.weight
BF16
BF16
[1024, 1024]
a.blk.3.attn_post_norm.weight
F32
F32
[1024]
a.blk.3.attn_pre_norm.weight
F32
F32
[1024]
a.blk.3.attn_q.input_max
F32
F32
[1]
a.blk.3.attn_q.input_min
F32
F32
[1]
a.blk.3.attn_q.output_max
F32
F32
[1]
a.blk.3.attn_q.output_min
F32
F32
[1]
a.blk.3.attn_q.weight
BF16
BF16
[1024, 1024]
a.blk.3.attn_v.input_max
F32
F32
[1]
a.blk.3.attn_v.input_min
F32
F32
[1]
a.blk.3.attn_v.output_max
F32
F32
[1]
a.blk.3.attn_v.output_min
F32
F32
[1]
a.blk.3.attn_v.weight
BF16
BF16
[1024, 1024]
a.blk.3.conv_dw.weight
F32
F32
[5, 1024]
a.blk.3.conv_norm.weight
F32
F32
[1024]
a.blk.3.conv_pw1.input_max
F32
F32
[1]
a.blk.3.conv_pw1.input_min
F32
F32
[1]
a.blk.3.conv_pw1.output_max
F32
F32
[1]
a.blk.3.conv_pw1.output_min
F32
F32
[1]
a.blk.3.conv_pw1.weight
BF16
BF16
[1024, 2048]
a.blk.3.conv_pw2.input_max
F32
F32
[1]
a.blk.3.conv_pw2.input_min
F32
F32
[1]
a.blk.3.conv_pw2.output_max
F32
F32
[1]
a.blk.3.conv_pw2.output_min
F32
F32
[1]
a.blk.3.conv_pw2.weight
BF16
BF16
[1024, 1024]
a.blk.3.ffn_down.input_max
F32
F32
[1]
a.blk.3.ffn_down.input_min
F32
F32
[1]
a.blk.3.ffn_down.output_max
F32
F32
[1]
a.blk.3.ffn_down.output_min
F32
F32
[1]
a.blk.3.ffn_down.weight
BF16
BF16
[4096, 1024]
a.blk.3.ffn_down_1.input_max
F32
F32
[1]
a.blk.3.ffn_down_1.input_min
F32
F32
[1]
a.blk.3.ffn_down_1.output_max
F32
F32
[1]
a.blk.3.ffn_down_1.output_min
F32
F32
[1]
a.blk.3.ffn_down_1.weight
BF16
BF16
[4096, 1024]
a.blk.3.ffn_norm.weight
F32
F32
[1024]
a.blk.3.ffn_norm_1.weight
F32
F32
[1024]
a.blk.3.ffn_post_norm.weight
F32
F32
[1024]
a.blk.3.ffn_post_norm_1.weight
F32
F32
[1024]
a.blk.3.ffn_up.input_max
F32
F32
[1]
a.blk.3.ffn_up.input_min
F32
F32
[1]
a.blk.3.ffn_up.output_max
F32
F32
[1]
a.blk.3.ffn_up.output_min
F32
F32
[1]
a.blk.3.ffn_up.weight
BF16
BF16
[1024, 4096]
a.blk.3.ffn_up_1.input_max
F32
F32
[1]
a.blk.3.ffn_up_1.input_min
F32
F32
[1]
a.blk.3.ffn_up_1.output_max
F32
F32
[1]
a.blk.3.ffn_up_1.output_min
F32
F32
[1]
a.blk.3.ffn_up_1.weight
BF16
BF16
[1024, 4096]
a.blk.3.ln2.weight
F32
F32
[1024]
a.blk.3.norm_conv.weight
F32
F32
[1024]
a.blk.3.per_dim_scale.weight
F32
F32
[128]
a.blk.4
a.blk.4.attn_k.input_max
F32
F32
[1]
a.blk.4.attn_k.input_min
F32
F32
[1]
a.blk.4.attn_k.output_max
F32
F32
[1]
a.blk.4.attn_k.output_min
F32
F32
[1]
a.blk.4.attn_k.weight
BF16
BF16
[1024, 1024]
a.blk.4.attn_k_rel.weight
BF16
BF16
[1024, 1024]
a.blk.4.attn_out.input_max
F32
F32
[1]
a.blk.4.attn_out.input_min
F32
F32
[1]
a.blk.4.attn_out.output_max
F32
F32
[1]
a.blk.4.attn_out.output_min
F32
F32
[1]
a.blk.4.attn_out.weight
BF16
BF16
[1024, 1024]
a.blk.4.attn_post_norm.weight
F32
F32
[1024]
a.blk.4.attn_pre_norm.weight
F32
F32
[1024]
a.blk.4.attn_q.input_max
F32
F32
[1]
a.blk.4.attn_q.input_min
F32
F32
[1]
a.blk.4.attn_q.output_max
F32
F32
[1]
a.blk.4.attn_q.output_min
F32
F32
[1]
a.blk.4.attn_q.weight
BF16
BF16
[1024, 1024]
a.blk.4.attn_v.input_max
F32
F32
[1]
a.blk.4.attn_v.input_min
F32
F32
[1]
a.blk.4.attn_v.output_max
F32
F32
[1]
a.blk.4.attn_v.output_min
F32
F32
[1]
a.blk.4.attn_v.weight
BF16
BF16
[1024, 1024]
a.blk.4.conv_dw.weight
F32
F32
[5, 1024]
a.blk.4.conv_norm.weight
F32
F32
[1024]
a.blk.4.conv_pw1.input_max
F32
F32
[1]
a.blk.4.conv_pw1.input_min
F32
F32
[1]
a.blk.4.conv_pw1.output_max
F32
F32
[1]
a.blk.4.conv_pw1.output_min
F32
F32
[1]
a.blk.4.conv_pw1.weight
BF16
BF16
[1024, 2048]
a.blk.4.conv_pw2.input_max
F32
F32
[1]
a.blk.4.conv_pw2.input_min
F32
F32
[1]
a.blk.4.conv_pw2.output_max
F32
F32
[1]
a.blk.4.conv_pw2.output_min
F32
F32
[1]
a.blk.4.conv_pw2.weight
BF16
BF16
[1024, 1024]
a.blk.4.ffn_down.input_max
F32
F32
[1]
a.blk.4.ffn_down.input_min
F32
F32
[1]
a.blk.4.ffn_down.output_max
F32
F32
[1]
a.blk.4.ffn_down.output_min
F32
F32
[1]
a.blk.4.ffn_down.weight
BF16
BF16
[4096, 1024]
a.blk.4.ffn_down_1.input_max
F32
F32
[1]
a.blk.4.ffn_down_1.input_min
F32
F32
[1]
a.blk.4.ffn_down_1.output_max
F32
F32
[1]
a.blk.4.ffn_down_1.output_min
F32
F32
[1]
a.blk.4.ffn_down_1.weight
BF16
BF16
[4096, 1024]
a.blk.4.ffn_norm.weight
F32
F32
[1024]
a.blk.4.ffn_norm_1.weight
F32
F32
[1024]
a.blk.4.ffn_post_norm.weight
F32
F32
[1024]
a.blk.4.ffn_post_norm_1.weight
F32
F32
[1024]
a.blk.4.ffn_up.input_max
F32
F32
[1]
a.blk.4.ffn_up.input_min
F32
F32
[1]
a.blk.4.ffn_up.output_max
F32
F32
[1]
a.blk.4.ffn_up.output_min
F32
F32
[1]
a.blk.4.ffn_up.weight
BF16
BF16
[1024, 4096]
a.blk.4.ffn_up_1.input_max
F32
F32
[1]
a.blk.4.ffn_up_1.input_min
F32
F32
[1]
a.blk.4.ffn_up_1.output_max
F32
F32
[1]
a.blk.4.ffn_up_1.output_min
F32
F32
[1]
a.blk.4.ffn_up_1.weight
BF16
BF16
[1024, 4096]
a.blk.4.ln2.weight
F32
F32
[1024]
a.blk.4.norm_conv.weight
F32
F32
[1024]
a.blk.4.per_dim_scale.weight
F32
F32
[128]
a.blk.5
a.blk.5.attn_k.input_max
F32
F32
[1]
a.blk.5.attn_k.input_min
F32
F32
[1]
a.blk.5.attn_k.output_max
F32
F32
[1]
a.blk.5.attn_k.output_min
F32
F32
[1]
a.blk.5.attn_k.weight
BF16
BF16
[1024, 1024]
a.blk.5.attn_k_rel.weight
BF16
BF16
[1024, 1024]
a.blk.5.attn_out.input_max
F32
F32
[1]
a.blk.5.attn_out.input_min
F32
F32
[1]
a.blk.5.attn_out.output_max
F32
F32
[1]
a.blk.5.attn_out.output_min
F32
F32
[1]
a.blk.5.attn_out.weight
BF16
BF16
[1024, 1024]
a.blk.5.attn_post_norm.weight
F32
F32
[1024]
a.blk.5.attn_pre_norm.weight
F32
F32
[1024]
a.blk.5.attn_q.input_max
F32
F32
[1]
a.blk.5.attn_q.input_min
F32
F32
[1]
a.blk.5.attn_q.output_max
F32
F32
[1]
a.blk.5.attn_q.output_min
F32
F32
[1]
a.blk.5.attn_q.weight
BF16
BF16
[1024, 1024]
a.blk.5.attn_v.input_max
F32
F32
[1]
a.blk.5.attn_v.input_min
F32
F32
[1]
a.blk.5.attn_v.output_max
F32
F32
[1]
a.blk.5.attn_v.output_min
F32
F32
[1]
a.blk.5.attn_v.weight
BF16
BF16
[1024, 1024]
a.blk.5.conv_dw.weight
F32
F32
[5, 1024]
a.blk.5.conv_norm.weight
F32
F32
[1024]
a.blk.5.conv_pw1.input_max
F32
F32
[1]
a.blk.5.conv_pw1.input_min
F32
F32
[1]
a.blk.5.conv_pw1.output_max
F32
F32
[1]
a.blk.5.conv_pw1.output_min
F32
F32
[1]
a.blk.5.conv_pw1.weight
BF16
BF16
[1024, 2048]
a.blk.5.conv_pw2.input_max
F32
F32
[1]
a.blk.5.conv_pw2.input_min
F32
F32
[1]
a.blk.5.conv_pw2.output_max
F32
F32
[1]
a.blk.5.conv_pw2.output_min
F32
F32
[1]
a.blk.5.conv_pw2.weight
BF16
BF16
[1024, 1024]
a.blk.5.ffn_down.input_max
F32
F32
[1]
a.blk.5.ffn_down.input_min
F32
F32
[1]
a.blk.5.ffn_down.output_max
F32
F32
[1]
a.blk.5.ffn_down.output_min
F32
F32
[1]
a.blk.5.ffn_down.weight
BF16
BF16
[4096, 1024]
a.blk.5.ffn_down_1.input_max
F32
F32
[1]
a.blk.5.ffn_down_1.input_min
F32
F32
[1]
a.blk.5.ffn_down_1.output_max
F32
F32
[1]
a.blk.5.ffn_down_1.output_min
F32
F32
[1]
a.blk.5.ffn_down_1.weight
BF16
BF16
[4096, 1024]
a.blk.5.ffn_norm.weight
F32
F32
[1024]
a.blk.5.ffn_norm_1.weight
F32
F32
[1024]
a.blk.5.ffn_post_norm.weight
F32
F32
[1024]
a.blk.5.ffn_post_norm_1.weight
F32
F32
[1024]
a.blk.5.ffn_up.input_max
F32
F32
[1]
a.blk.5.ffn_up.input_min
F32
F32
[1]
a.blk.5.ffn_up.output_max
F32
F32
[1]
a.blk.5.ffn_up.output_min
F32
F32
[1]
a.blk.5.ffn_up.weight
BF16
BF16
[1024, 4096]
a.blk.5.ffn_up_1.input_max
F32
F32
[1]
a.blk.5.ffn_up_1.input_min
F32
F32
[1]
a.blk.5.ffn_up_1.output_max
F32
F32
[1]
a.blk.5.ffn_up_1.output_min
F32
F32
[1]
a.blk.5.ffn_up_1.weight
BF16
BF16
[1024, 4096]
a.blk.5.ln2.weight
F32
F32
[1024]
a.blk.5.norm_conv.weight
F32
F32
[1024]
a.blk.5.per_dim_scale.weight
F32
F32
[128]
a.blk.6
a.blk.6.attn_k.input_max
F32
F32
[1]
a.blk.6.attn_k.input_min
F32
F32
[1]
a.blk.6.attn_k.output_max
F32
F32
[1]
a.blk.6.attn_k.output_min
F32
F32
[1]
a.blk.6.attn_k.weight
BF16
BF16
[1024, 1024]
a.blk.6.attn_k_rel.weight
BF16
BF16
[1024, 1024]
a.blk.6.attn_out.input_max
F32
F32
[1]
a.blk.6.attn_out.input_min
F32
F32
[1]
a.blk.6.attn_out.output_max
F32
F32
[1]
a.blk.6.attn_out.output_min
F32
F32
[1]
a.blk.6.attn_out.weight
BF16
BF16
[1024, 1024]
a.blk.6.attn_post_norm.weight
F32
F32
[1024]
a.blk.6.attn_pre_norm.weight
F32
F32
[1024]
a.blk.6.attn_q.input_max
F32
F32
[1]
a.blk.6.attn_q.input_min
F32
F32
[1]
a.blk.6.attn_q.output_max
F32
F32
[1]
a.blk.6.attn_q.output_min
F32
F32
[1]
a.blk.6.attn_q.weight
BF16
BF16
[1024, 1024]
a.blk.6.attn_v.input_max
F32
F32
[1]
a.blk.6.attn_v.input_min
F32
F32
[1]
a.blk.6.attn_v.output_max
F32
F32
[1]
a.blk.6.attn_v.output_min
F32
F32
[1]
a.blk.6.attn_v.weight
BF16
BF16
[1024, 1024]
a.blk.6.conv_dw.weight
F32
F32
[5, 1024]
a.blk.6.conv_norm.weight
F32
F32
[1024]
a.blk.6.conv_pw1.input_max
F32
F32
[1]
a.blk.6.conv_pw1.input_min
F32
F32
[1]
a.blk.6.conv_pw1.output_max
F32
F32
[1]
a.blk.6.conv_pw1.output_min
F32
F32
[1]
a.blk.6.conv_pw1.weight
BF16
BF16
[1024, 2048]
a.blk.6.conv_pw2.input_max
F32
F32
[1]
a.blk.6.conv_pw2.input_min
F32
F32
[1]
a.blk.6.conv_pw2.output_max
F32
F32
[1]
a.blk.6.conv_pw2.output_min
F32
F32
[1]
a.blk.6.conv_pw2.weight
BF16
BF16
[1024, 1024]
a.blk.6.ffn_down.input_max
F32
F32
[1]
a.blk.6.ffn_down.input_min
F32
F32
[1]
a.blk.6.ffn_down.output_max
F32
F32
[1]
a.blk.6.ffn_down.output_min
F32
F32
[1]
a.blk.6.ffn_down.weight
BF16
BF16
[4096, 1024]
a.blk.6.ffn_down_1.input_max
F32
F32
[1]
a.blk.6.ffn_down_1.input_min
F32
F32
[1]
a.blk.6.ffn_down_1.output_max
F32
F32
[1]
a.blk.6.ffn_down_1.output_min
F32
F32
[1]
a.blk.6.ffn_down_1.weight
BF16
BF16
[4096, 1024]
a.blk.6.ffn_norm.weight
F32
F32
[1024]
a.blk.6.ffn_norm_1.weight
F32
F32
[1024]
a.blk.6.ffn_post_norm.weight
F32
F32
[1024]
a.blk.6.ffn_post_norm_1.weight
F32
F32
[1024]
a.blk.6.ffn_up.input_max
F32
F32
[1]
a.blk.6.ffn_up.input_min
F32
F32
[1]
a.blk.6.ffn_up.output_max
F32
F32
[1]
a.blk.6.ffn_up.output_min
F32
F32
[1]
a.blk.6.ffn_up.weight
BF16
BF16
[1024, 4096]
a.blk.6.ffn_up_1.input_max
F32
F32
[1]
a.blk.6.ffn_up_1.input_min
F32
F32
[1]
a.blk.6.ffn_up_1.output_max
F32
F32
[1]
a.blk.6.ffn_up_1.output_min
F32
F32
[1]
a.blk.6.ffn_up_1.weight
BF16
BF16
[1024, 4096]
a.blk.6.ln2.weight
F32
F32
[1024]
a.blk.6.norm_conv.weight
F32
F32
[1024]
a.blk.6.per_dim_scale.weight
F32
F32
[128]
a.blk.7
a.blk.7.attn_k.input_max
F32
F32
[1]
a.blk.7.attn_k.input_min
F32
F32
[1]
a.blk.7.attn_k.output_max
F32
F32
[1]
a.blk.7.attn_k.output_min
F32
F32
[1]
a.blk.7.attn_k.weight
BF16
BF16
[1024, 1024]
a.blk.7.attn_k_rel.weight
BF16
BF16
[1024, 1024]
a.blk.7.attn_out.input_max
F32
F32
[1]
a.blk.7.attn_out.input_min
F32
F32
[1]
a.blk.7.attn_out.output_max
F32
F32
[1]
a.blk.7.attn_out.output_min
F32
F32
[1]
a.blk.7.attn_out.weight
BF16
BF16
[1024, 1024]
a.blk.7.attn_post_norm.weight
F32
F32
[1024]
a.blk.7.attn_pre_norm.weight
F32
F32
[1024]
a.blk.7.attn_q.input_max
F32
F32
[1]
a.blk.7.attn_q.input_min
F32
F32
[1]
a.blk.7.attn_q.output_max
F32
F32
[1]
a.blk.7.attn_q.output_min
F32
F32
[1]
a.blk.7.attn_q.weight
BF16
BF16
[1024, 1024]
a.blk.7.attn_v.input_max
F32
F32
[1]
a.blk.7.attn_v.input_min
F32
F32
[1]
a.blk.7.attn_v.output_max
F32
F32
[1]
a.blk.7.attn_v.output_min
F32
F32
[1]
a.blk.7.attn_v.weight
BF16
BF16
[1024, 1024]
a.blk.7.conv_dw.weight
F32
F32
[5, 1024]
a.blk.7.conv_norm.weight
F32
F32
[1024]
a.blk.7.conv_pw1.input_max
F32
F32
[1]
a.blk.7.conv_pw1.input_min
F32
F32
[1]
a.blk.7.conv_pw1.output_max
F32
F32
[1]
a.blk.7.conv_pw1.output_min
F32
F32
[1]
a.blk.7.conv_pw1.weight
BF16
BF16
[1024, 2048]
a.blk.7.conv_pw2.input_max
F32
F32
[1]
a.blk.7.conv_pw2.input_min
F32
F32
[1]
a.blk.7.conv_pw2.output_max
F32
F32
[1]
a.blk.7.conv_pw2.output_min
F32
F32
[1]
a.blk.7.conv_pw2.weight
BF16
BF16
[1024, 1024]
a.blk.7.ffn_down.input_max
F32
F32
[1]
a.blk.7.ffn_down.input_min
F32
F32
[1]
a.blk.7.ffn_down.output_max
F32
F32
[1]
a.blk.7.ffn_down.output_min
F32
F32
[1]
a.blk.7.ffn_down.weight
BF16
BF16
[4096, 1024]
a.blk.7.ffn_down_1.input_max
F32
F32
[1]
a.blk.7.ffn_down_1.input_min
F32
F32
[1]
a.blk.7.ffn_down_1.output_max
F32
F32
[1]
a.blk.7.ffn_down_1.output_min
F32
F32
[1]
a.blk.7.ffn_down_1.weight
BF16
BF16
[4096, 1024]
a.blk.7.ffn_norm.weight
F32
F32
[1024]
a.blk.7.ffn_norm_1.weight
F32
F32
[1024]
a.blk.7.ffn_post_norm.weight
F32
F32
[1024]
a.blk.7.ffn_post_norm_1.weight
F32
F32
[1024]
a.blk.7.ffn_up.input_max
F32
F32
[1]
a.blk.7.ffn_up.input_min
F32
F32
[1]
a.blk.7.ffn_up.output_max
F32
F32
[1]
a.blk.7.ffn_up.output_min
F32
F32
[1]
a.blk.7.ffn_up.weight
BF16
BF16
[1024, 4096]
a.blk.7.ffn_up_1.input_max
F32
F32
[1]
a.blk.7.ffn_up_1.input_min
F32
F32
[1]
a.blk.7.ffn_up_1.output_max
F32
F32
[1]
a.blk.7.ffn_up_1.output_min
F32
F32
[1]
a.blk.7.ffn_up_1.weight
BF16
BF16
[1024, 4096]
a.blk.7.ln2.weight
F32
F32
[1024]
a.blk.7.norm_conv.weight
F32
F32
[1024]
a.blk.7.per_dim_scale.weight
F32
F32
[128]
a.blk.8
a.blk.8.attn_k.input_max
F32
F32
[1]
a.blk.8.attn_k.input_min
F32
F32
[1]
a.blk.8.attn_k.output_max
F32
F32
[1]
a.blk.8.attn_k.output_min
F32
F32
[1]
a.blk.8.attn_k.weight
BF16
BF16
[1024, 1024]
a.blk.8.attn_k_rel.weight
BF16
BF16
[1024, 1024]
a.blk.8.attn_out.input_max
F32
F32
[1]
a.blk.8.attn_out.input_min
F32
F32
[1]
a.blk.8.attn_out.output_max
F32
F32
[1]
a.blk.8.attn_out.output_min
F32
F32
[1]
a.blk.8.attn_out.weight
BF16
BF16
[1024, 1024]
a.blk.8.attn_post_norm.weight
F32
F32
[1024]
a.blk.8.attn_pre_norm.weight
F32
F32
[1024]
a.blk.8.attn_q.input_max
F32
F32
[1]
a.blk.8.attn_q.input_min
F32
F32
[1]
a.blk.8.attn_q.output_max
F32
F32
[1]
a.blk.8.attn_q.output_min
F32
F32
[1]
a.blk.8.attn_q.weight
BF16
BF16
[1024, 1024]
a.blk.8.attn_v.input_max
F32
F32
[1]
a.blk.8.attn_v.input_min
F32
F32
[1]
a.blk.8.attn_v.output_max
F32
F32
[1]
a.blk.8.attn_v.output_min
F32
F32
[1]
a.blk.8.attn_v.weight
BF16
BF16
[1024, 1024]
a.blk.8.conv_dw.weight
F32
F32
[5, 1024]
a.blk.8.conv_norm.weight
F32
F32
[1024]
a.blk.8.conv_pw1.input_max
F32
F32
[1]
a.blk.8.conv_pw1.input_min
F32
F32
[1]
a.blk.8.conv_pw1.output_max
F32
F32
[1]
a.blk.8.conv_pw1.output_min
F32
F32
[1]
a.blk.8.conv_pw1.weight
BF16
BF16
[1024, 2048]
a.blk.8.conv_pw2.input_max
F32
F32
[1]
a.blk.8.conv_pw2.input_min
F32
F32
[1]
a.blk.8.conv_pw2.output_max
F32
F32
[1]
a.blk.8.conv_pw2.output_min
F32
F32
[1]
a.blk.8.conv_pw2.weight
BF16
BF16
[1024, 1024]
a.blk.8.ffn_down.input_max
F32
F32
[1]
a.blk.8.ffn_down.input_min
F32
F32
[1]
a.blk.8.ffn_down.output_max
F32
F32
[1]
a.blk.8.ffn_down.output_min
F32
F32
[1]
a.blk.8.ffn_down.weight
BF16
BF16
[4096, 1024]
a.blk.8.ffn_down_1.input_max
F32
F32
[1]
a.blk.8.ffn_down_1.input_min
F32
F32
[1]
a.blk.8.ffn_down_1.output_max
F32
F32
[1]
a.blk.8.ffn_down_1.output_min
F32
F32
[1]
a.blk.8.ffn_down_1.weight
BF16
BF16
[4096, 1024]
a.blk.8.ffn_norm.weight
F32
F32
[1024]
a.blk.8.ffn_norm_1.weight
F32
F32
[1024]
a.blk.8.ffn_post_norm.weight
F32
F32
[1024]
a.blk.8.ffn_post_norm_1.weight
F32
F32
[1024]
a.blk.8.ffn_up.input_max
F32
F32
[1]
a.blk.8.ffn_up.input_min
F32
F32
[1]
a.blk.8.ffn_up.output_max
F32
F32
[1]
a.blk.8.ffn_up.output_min
F32
F32
[1]
a.blk.8.ffn_up.weight
BF16
BF16
[1024, 4096]
a.blk.8.ffn_up_1.input_max
F32
F32
[1]
a.blk.8.ffn_up_1.input_min
F32
F32
[1]
a.blk.8.ffn_up_1.output_max
F32
F32
[1]
a.blk.8.ffn_up_1.output_min
F32
F32
[1]
a.blk.8.ffn_up_1.weight
BF16
BF16
[1024, 4096]
a.blk.8.ln2.weight
F32
F32
[1024]
a.blk.8.norm_conv.weight
F32
F32
[1024]
a.blk.8.per_dim_scale.weight
F32
F32
[128]
a.blk.9
a.blk.9.attn_k.input_max
F32
F32
[1]
a.blk.9.attn_k.input_min
F32
F32
[1]
a.blk.9.attn_k.output_max
F32
F32
[1]
a.blk.9.attn_k.output_min
F32
F32
[1]
a.blk.9.attn_k.weight
BF16
BF16
[1024, 1024]
a.blk.9.attn_k_rel.weight
BF16
BF16
[1024, 1024]
a.blk.9.attn_out.input_max
F32
F32
[1]
a.blk.9.attn_out.input_min
F32
F32
[1]
a.blk.9.attn_out.output_max
F32
F32
[1]
a.blk.9.attn_out.output_min
F32
F32
[1]
a.blk.9.attn_out.weight
BF16
BF16
[1024, 1024]
a.blk.9.attn_post_norm.weight
F32
F32
[1024]
a.blk.9.attn_pre_norm.weight
F32
F32
[1024]
a.blk.9.attn_q.input_max
F32
F32
[1]
a.blk.9.attn_q.input_min
F32
F32
[1]
a.blk.9.attn_q.output_max
F32
F32
[1]
a.blk.9.attn_q.output_min
F32
F32
[1]
a.blk.9.attn_q.weight
BF16
BF16
[1024, 1024]
a.blk.9.attn_v.input_max
F32
F32
[1]
a.blk.9.attn_v.input_min
F32
F32
[1]
a.blk.9.attn_v.output_max
F32
F32
[1]
a.blk.9.attn_v.output_min
F32
F32
[1]
a.blk.9.attn_v.weight
BF16
BF16
[1024, 1024]
a.blk.9.conv_dw.weight
F32
F32
[5, 1024]
a.blk.9.conv_norm.weight
F32
F32
[1024]
a.blk.9.conv_pw1.input_max
F32
F32
[1]
a.blk.9.conv_pw1.input_min
F32
F32
[1]
a.blk.9.conv_pw1.output_max
F32
F32
[1]
a.blk.9.conv_pw1.output_min
F32
F32
[1]
a.blk.9.conv_pw1.weight
BF16
BF16
[1024, 2048]
a.blk.9.conv_pw2.input_max
F32
F32
[1]
a.blk.9.conv_pw2.input_min
F32
F32
[1]
a.blk.9.conv_pw2.output_max
F32
F32
[1]
a.blk.9.conv_pw2.output_min
F32
F32
[1]
a.blk.9.conv_pw2.weight
BF16
BF16
[1024, 1024]
a.blk.9.ffn_down.input_max
F32
F32
[1]
a.blk.9.ffn_down.input_min
F32
F32
[1]
a.blk.9.ffn_down.output_max
F32
F32
[1]
a.blk.9.ffn_down.output_min
F32
F32
[1]
a.blk.9.ffn_down.weight
BF16
BF16
[4096, 1024]
a.blk.9.ffn_down_1.input_max
F32
F32
[1]
a.blk.9.ffn_down_1.input_min
F32
F32
[1]
a.blk.9.ffn_down_1.output_max
F32
F32
[1]
a.blk.9.ffn_down_1.output_min
F32
F32
[1]
a.blk.9.ffn_down_1.weight
BF16
BF16
[4096, 1024]
a.blk.9.ffn_norm.weight
F32
F32
[1024]
a.blk.9.ffn_norm_1.weight
F32
F32
[1024]
a.blk.9.ffn_post_norm.weight
F32
F32
[1024]
a.blk.9.ffn_post_norm_1.weight
F32
F32
[1024]
a.blk.9.ffn_up.input_max
F32
F32
[1]
a.blk.9.ffn_up.input_min
F32
F32
[1]
a.blk.9.ffn_up.output_max
F32
F32
[1]
a.blk.9.ffn_up.output_min
F32
F32
[1]
a.blk.9.ffn_up.weight
BF16
BF16
[1024, 4096]
a.blk.9.ffn_up_1.input_max
F32
F32
[1]
a.blk.9.ffn_up_1.input_min
F32
F32
[1]
a.blk.9.ffn_up_1.output_max
F32
F32
[1]
a.blk.9.ffn_up_1.output_min
F32
F32
[1]
a.blk.9.ffn_up_1.weight
BF16
BF16
[1024, 4096]
a.blk.9.ln2.weight
F32
F32
[1024]
a.blk.9.norm_conv.weight
F32
F32
[1024]
a.blk.9.per_dim_scale.weight
F32
F32
[128]
a.blk.10
a.blk.10.attn_k.input_max
F32
F32
[1]
a.blk.10.attn_k.input_min
F32
F32
[1]
a.blk.10.attn_k.output_max
F32
F32
[1]
a.blk.10.attn_k.output_min
F32
F32
[1]
a.blk.10.attn_k.weight
BF16
BF16
[1024, 1024]
a.blk.10.attn_k_rel.weight
BF16
BF16
[1024, 1024]
a.blk.10.attn_out.input_max
F32
F32
[1]
a.blk.10.attn_out.input_min
F32
F32
[1]
a.blk.10.attn_out.output_max
F32
F32
[1]
a.blk.10.attn_out.output_min
F32
F32
[1]
a.blk.10.attn_out.weight
BF16
BF16
[1024, 1024]
a.blk.10.attn_post_norm.weight
F32
F32
[1024]
a.blk.10.attn_pre_norm.weight
F32
F32
[1024]
a.blk.10.attn_q.input_max
F32
F32
[1]
a.blk.10.attn_q.input_min
F32
F32
[1]
a.blk.10.attn_q.output_max
F32
F32
[1]
a.blk.10.attn_q.output_min
F32
F32
[1]
a.blk.10.attn_q.weight
BF16
BF16
[1024, 1024]
a.blk.10.attn_v.input_max
F32
F32
[1]
a.blk.10.attn_v.input_min
F32
F32
[1]
a.blk.10.attn_v.output_max
F32
F32
[1]
a.blk.10.attn_v.output_min
F32
F32
[1]
a.blk.10.attn_v.weight
BF16
BF16
[1024, 1024]
a.blk.10.conv_dw.weight
F32
F32
[5, 1024]
a.blk.10.conv_norm.weight
F32
F32
[1024]
a.blk.10.conv_pw1.input_max
F32
F32
[1]
a.blk.10.conv_pw1.input_min
F32
F32
[1]
a.blk.10.conv_pw1.output_max
F32
F32
[1]
a.blk.10.conv_pw1.output_min
F32
F32
[1]
a.blk.10.conv_pw1.weight
BF16
BF16
[1024, 2048]
a.blk.10.conv_pw2.input_max
F32
F32
[1]
a.blk.10.conv_pw2.input_min
F32
F32
[1]
a.blk.10.conv_pw2.output_max
F32
F32
[1]
a.blk.10.conv_pw2.output_min
F32
F32
[1]
a.blk.10.conv_pw2.weight
BF16
BF16
[1024, 1024]
a.blk.10.ffn_down.input_max
F32
F32
[1]
a.blk.10.ffn_down.input_min
F32
F32
[1]
a.blk.10.ffn_down.output_max
F32
F32
[1]
a.blk.10.ffn_down.output_min
F32
F32
[1]
a.blk.10.ffn_down.weight
BF16
BF16
[4096, 1024]
a.blk.10.ffn_down_1.input_max
F32
F32
[1]
a.blk.10.ffn_down_1.input_min
F32
F32
[1]
a.blk.10.ffn_down_1.output_max
F32
F32
[1]
a.blk.10.ffn_down_1.output_min
F32
F32
[1]
a.blk.10.ffn_down_1.weight
BF16
BF16
[4096, 1024]
a.blk.10.ffn_norm.weight
F32
F32
[1024]
a.blk.10.ffn_norm_1.weight
F32
F32
[1024]
a.blk.10.ffn_post_norm.weight
F32
F32
[1024]
a.blk.10.ffn_post_norm_1.weight
F32
F32
[1024]
a.blk.10.ffn_up.input_max
F32
F32
[1]
a.blk.10.ffn_up.input_min
F32
F32
[1]
a.blk.10.ffn_up.output_max
F32
F32
[1]
a.blk.10.ffn_up.output_min
F32
F32
[1]
a.blk.10.ffn_up.weight
BF16
BF16
[1024, 4096]
a.blk.10.ffn_up_1.input_max
F32
F32
[1]
a.blk.10.ffn_up_1.input_min
F32
F32
[1]
a.blk.10.ffn_up_1.output_max
F32
F32
[1]
a.blk.10.ffn_up_1.output_min
F32
F32
[1]
a.blk.10.ffn_up_1.weight
BF16
BF16
[1024, 4096]
a.blk.10.ln2.weight
F32
F32
[1024]
a.blk.10.norm_conv.weight
F32
F32
[1024]
a.blk.10.per_dim_scale.weight
F32
F32
[128]
a.blk.11
a.blk.11.attn_k.input_max
F32
F32
[1]
a.blk.11.attn_k.input_min
F32
F32
[1]
a.blk.11.attn_k.output_max
F32
F32
[1]
a.blk.11.attn_k.output_min
F32
F32
[1]
a.blk.11.attn_k.weight
BF16
BF16
[1024, 1024]
a.blk.11.attn_k_rel.weight
BF16
BF16
[1024, 1024]
a.blk.11.attn_out.input_max
F32
F32
[1]
a.blk.11.attn_out.input_min
F32
F32
[1]
a.blk.11.attn_out.output_max
F32
F32
[1]
a.blk.11.attn_out.output_min
F32
F32
[1]
a.blk.11.attn_out.weight
BF16
BF16
[1024, 1024]
a.blk.11.attn_post_norm.weight
F32
F32
[1024]
a.blk.11.attn_pre_norm.weight
F32
F32
[1024]
a.blk.11.attn_q.input_max
F32
F32
[1]
a.blk.11.attn_q.input_min
F32
F32
[1]
a.blk.11.attn_q.output_max
F32
F32
[1]
a.blk.11.attn_q.output_min
F32
F32
[1]
a.blk.11.attn_q.weight
BF16
BF16
[1024, 1024]
a.blk.11.attn_v.input_max
F32
F32
[1]
a.blk.11.attn_v.input_min
F32
F32
[1]
a.blk.11.attn_v.output_max
F32
F32
[1]
a.blk.11.attn_v.output_min
F32
F32
[1]
a.blk.11.attn_v.weight
BF16
BF16
[1024, 1024]
a.blk.11.conv_dw.weight
F32
F32
[5, 1024]
a.blk.11.conv_norm.weight
F32
F32
[1024]
a.blk.11.conv_pw1.input_max
F32
F32
[1]
a.blk.11.conv_pw1.input_min
F32
F32
[1]
a.blk.11.conv_pw1.output_max
F32
F32
[1]
a.blk.11.conv_pw1.output_min
F32
F32
[1]
a.blk.11.conv_pw1.weight
BF16
BF16
[1024, 2048]
a.blk.11.conv_pw2.input_max
F32
F32
[1]
a.blk.11.conv_pw2.input_min
F32
F32
[1]
a.blk.11.conv_pw2.output_max
F32
F32
[1]
a.blk.11.conv_pw2.output_min
F32
F32
[1]
a.blk.11.conv_pw2.weight
BF16
BF16
[1024, 1024]
a.blk.11.ffn_down.input_max
F32
F32
[1]
a.blk.11.ffn_down.input_min
F32
F32
[1]
a.blk.11.ffn_down.output_max
F32
F32
[1]
a.blk.11.ffn_down.output_min
F32
F32
[1]
a.blk.11.ffn_down.weight
BF16
BF16
[4096, 1024]
a.blk.11.ffn_down_1.input_max
F32
F32
[1]
a.blk.11.ffn_down_1.input_min
F32
F32
[1]
a.blk.11.ffn_down_1.output_max
F32
F32
[1]
a.blk.11.ffn_down_1.output_min
F32
F32
[1]
a.blk.11.ffn_down_1.weight
BF16
BF16
[4096, 1024]
a.blk.11.ffn_norm.weight
F32
F32
[1024]
a.blk.11.ffn_norm_1.weight
F32
F32
[1024]
a.blk.11.ffn_post_norm.weight
F32
F32
[1024]
a.blk.11.ffn_post_norm_1.weight
F32
F32
[1024]
a.blk.11.ffn_up.input_max
F32
F32
[1]
a.blk.11.ffn_up.input_min
F32
F32
[1]
a.blk.11.ffn_up.output_max
F32
F32
[1]
a.blk.11.ffn_up.output_min
F32
F32
[1]
a.blk.11.ffn_up.weight
BF16
BF16
[1024, 4096]
a.blk.11.ffn_up_1.input_max
F32
F32
[1]
a.blk.11.ffn_up_1.input_min
F32
F32
[1]
a.blk.11.ffn_up_1.output_max
F32
F32
[1]
a.blk.11.ffn_up_1.output_min
F32
F32
[1]
a.blk.11.ffn_up_1.weight
BF16
BF16
[1024, 4096]
a.blk.11.ln2.weight
F32
F32
[1024]
a.blk.11.norm_conv.weight
F32
F32
[1024]
a.blk.11.per_dim_scale.weight
F32
F32
[128]
a.conv1d.0.norm.weight
F32
F32
[128]
a.conv1d.0.weight
F32
F32
[3, 3, 1, 128]
a.conv1d.1.norm.weight
F32
F32
[32]
a.conv1d.1.weight
F32
F32
[3, 3, 128, 32]
a.input_projection.weight
F32
F32
[1024, 1024]
a.pre_encode.out.bias
F32
F32
[1536]
a.pre_encode.out.weight
BF16
BF16
[1024, 1536]
mm.a.input_projection.weight
BF16
BF16
[1536, 2560]
mm.input_projection.weight
BF16
BF16
[768, 2560]
v.blk.0
v.blk.0.attn_k.input_max
F32
F32
[1]
v.blk.0.attn_k.input_min
F32
F32
[1]
v.blk.0.attn_k.output_max
F32
F32
[1]
v.blk.0.attn_k.output_min
F32
F32
[1]
v.blk.0.attn_k.weight
BF16
BF16
[768, 768]
v.blk.0.attn_k_norm.weight
F32
F32
[64]
v.blk.0.attn_out.input_max
F32
F32
[1]
v.blk.0.attn_out.input_min
F32
F32
[1]
v.blk.0.attn_out.output_max
F32
F32
[1]
v.blk.0.attn_out.output_min
F32
F32
[1]
v.blk.0.attn_out.weight
BF16
BF16
[768, 768]
v.blk.0.attn_post_norm.weight
F32
F32
[768]
v.blk.0.attn_q.input_max
F32
F32
[1]
v.blk.0.attn_q.input_min
F32
F32
[1]
v.blk.0.attn_q.output_max
F32
F32
[1]
v.blk.0.attn_q.output_min
F32
F32
[1]
v.blk.0.attn_q.weight
BF16
BF16
[768, 768]
v.blk.0.attn_q_norm.weight
F32
F32
[64]
v.blk.0.attn_v.input_max
F32
F32
[1]
v.blk.0.attn_v.input_min
F32
F32
[1]
v.blk.0.attn_v.output_max
F32
F32
[1]
v.blk.0.attn_v.output_min
F32
F32
[1]
v.blk.0.attn_v.weight
BF16
BF16
[768, 768]
v.blk.0.ffn_down.input_max
F32
F32
[1]
v.blk.0.ffn_down.input_min
F32
F32
[1]
v.blk.0.ffn_down.output_max
F32
F32
[1]
v.blk.0.ffn_down.output_min
F32
F32
[1]
v.blk.0.ffn_down.weight
BF16
BF16
[3072, 768]
v.blk.0.ffn_gate.input_max
F32
F32
[1]
v.blk.0.ffn_gate.input_min
F32
F32
[1]
v.blk.0.ffn_gate.output_max
F32
F32
[1]
v.blk.0.ffn_gate.output_min
F32
F32
[1]
v.blk.0.ffn_gate.weight
BF16
BF16
[768, 3072]
v.blk.0.ffn_post_norm.weight
F32
F32
[768]
v.blk.0.ffn_up.input_max
F32
F32
[1]
v.blk.0.ffn_up.input_min
F32
F32
[1]
v.blk.0.ffn_up.output_max
F32
F32
[1]
v.blk.0.ffn_up.output_min
F32
F32
[1]
v.blk.0.ffn_up.weight
BF16
BF16
[768, 3072]
v.blk.0.ln1.weight
F32
F32
[768]
v.blk.0.ln2.weight
F32
F32
[768]
v.blk.1
v.blk.1.attn_k.input_max
F32
F32
[1]
v.blk.1.attn_k.input_min
F32
F32
[1]
v.blk.1.attn_k.output_max
F32
F32
[1]
v.blk.1.attn_k.output_min
F32
F32
[1]
v.blk.1.attn_k.weight
BF16
BF16
[768, 768]
v.blk.1.attn_k_norm.weight
F32
F32
[64]
v.blk.1.attn_out.input_max
F32
F32
[1]
v.blk.1.attn_out.input_min
F32
F32
[1]
v.blk.1.attn_out.output_max
F32
F32
[1]
v.blk.1.attn_out.output_min
F32
F32
[1]
v.blk.1.attn_out.weight
BF16
BF16
[768, 768]
v.blk.1.attn_post_norm.weight
F32
F32
[768]
v.blk.1.attn_q.input_max
F32
F32
[1]
v.blk.1.attn_q.input_min
F32
F32
[1]
v.blk.1.attn_q.output_max
F32
F32
[1]
v.blk.1.attn_q.output_min
F32
F32
[1]
v.blk.1.attn_q.weight
BF16
BF16
[768, 768]
v.blk.1.attn_q_norm.weight
F32
F32
[64]
v.blk.1.attn_v.input_max
F32
F32
[1]
v.blk.1.attn_v.input_min
F32
F32
[1]
v.blk.1.attn_v.output_max
F32
F32
[1]
v.blk.1.attn_v.output_min
F32
F32
[1]
v.blk.1.attn_v.weight
BF16
BF16
[768, 768]
v.blk.1.ffn_down.input_max
F32
F32
[1]
v.blk.1.ffn_down.input_min
F32
F32
[1]
v.blk.1.ffn_down.output_max
F32
F32
[1]
v.blk.1.ffn_down.output_min
F32
F32
[1]
v.blk.1.ffn_down.weight
BF16
BF16
[3072, 768]
v.blk.1.ffn_gate.input_max
F32
F32
[1]
v.blk.1.ffn_gate.input_min
F32
F32
[1]
v.blk.1.ffn_gate.output_max
F32
F32
[1]
v.blk.1.ffn_gate.output_min
F32
F32
[1]
v.blk.1.ffn_gate.weight
BF16
BF16
[768, 3072]
v.blk.1.ffn_post_norm.weight
F32
F32
[768]
v.blk.1.ffn_up.input_max
F32
F32
[1]
v.blk.1.ffn_up.input_min
F32
F32
[1]
v.blk.1.ffn_up.output_max
F32
F32
[1]
v.blk.1.ffn_up.output_min
F32
F32
[1]
v.blk.1.ffn_up.weight
BF16
BF16
[768, 3072]
v.blk.1.ln1.weight
F32
F32
[768]
v.blk.1.ln2.weight
F32
F32
[768]
v.blk.2
v.blk.2.attn_k.input_max
F32
F32
[1]
v.blk.2.attn_k.input_min
F32
F32
[1]
v.blk.2.attn_k.output_max
F32
F32
[1]
v.blk.2.attn_k.output_min
F32
F32
[1]
v.blk.2.attn_k.weight
BF16
BF16
[768, 768]
v.blk.2.attn_k_norm.weight
F32
F32
[64]
v.blk.2.attn_out.input_max
F32
F32
[1]
v.blk.2.attn_out.input_min
F32
F32
[1]
v.blk.2.attn_out.output_max
F32
F32
[1]
v.blk.2.attn_out.output_min
F32
F32
[1]
v.blk.2.attn_out.weight
BF16
BF16
[768, 768]
v.blk.2.attn_post_norm.weight
F32
F32
[768]
v.blk.2.attn_q.input_max
F32
F32
[1]
v.blk.2.attn_q.input_min
F32
F32
[1]
v.blk.2.attn_q.output_max
F32
F32
[1]
v.blk.2.attn_q.output_min
F32
F32
[1]
v.blk.2.attn_q.weight
BF16
BF16
[768, 768]
v.blk.2.attn_q_norm.weight
F32
F32
[64]
v.blk.2.attn_v.input_max
F32
F32
[1]
v.blk.2.attn_v.input_min
F32
F32
[1]
v.blk.2.attn_v.output_max
F32
F32
[1]
v.blk.2.attn_v.output_min
F32
F32
[1]
v.blk.2.attn_v.weight
BF16
BF16
[768, 768]
v.blk.2.ffn_down.input_max
F32
F32
[1]
v.blk.2.ffn_down.input_min
F32
F32
[1]
v.blk.2.ffn_down.output_max
F32
F32
[1]
v.blk.2.ffn_down.output_min
F32
F32
[1]
v.blk.2.ffn_down.weight
BF16
BF16
[3072, 768]
v.blk.2.ffn_gate.input_max
F32
F32
[1]
v.blk.2.ffn_gate.input_min
F32
F32
[1]
v.blk.2.ffn_gate.output_max
F32
F32
[1]
v.blk.2.ffn_gate.output_min
F32
F32
[1]
v.blk.2.ffn_gate.weight
BF16
BF16
[768, 3072]
v.blk.2.ffn_post_norm.weight
F32
F32
[768]
v.blk.2.ffn_up.input_max
F32
F32
[1]
v.blk.2.ffn_up.input_min
F32
F32
[1]
v.blk.2.ffn_up.output_max
F32
F32
[1]
v.blk.2.ffn_up.output_min
F32
F32
[1]
v.blk.2.ffn_up.weight
BF16
BF16
[768, 3072]
v.blk.2.ln1.weight
F32
F32
[768]
v.blk.2.ln2.weight
F32
F32
[768]
v.blk.3
v.blk.3.attn_k.input_max
F32
F32
[1]
v.blk.3.attn_k.input_min
F32
F32
[1]
v.blk.3.attn_k.output_max
F32
F32
[1]
v.blk.3.attn_k.output_min
F32
F32
[1]
v.blk.3.attn_k.weight
BF16
BF16
[768, 768]
v.blk.3.attn_k_norm.weight
F32
F32
[64]
v.blk.3.attn_out.input_max
F32
F32
[1]
v.blk.3.attn_out.input_min
F32
F32
[1]
v.blk.3.attn_out.output_max
F32
F32
[1]
v.blk.3.attn_out.output_min
F32
F32
[1]
v.blk.3.attn_out.weight
BF16
BF16
[768, 768]
v.blk.3.attn_post_norm.weight
F32
F32
[768]
v.blk.3.attn_q.input_max
F32
F32
[1]
v.blk.3.attn_q.input_min
F32
F32
[1]
v.blk.3.attn_q.output_max
F32
F32
[1]
v.blk.3.attn_q.output_min
F32
F32
[1]
v.blk.3.attn_q.weight
BF16
BF16
[768, 768]
v.blk.3.attn_q_norm.weight
F32
F32
[64]
v.blk.3.attn_v.input_max
F32
F32
[1]
v.blk.3.attn_v.input_min
F32
F32
[1]
v.blk.3.attn_v.output_max
F32
F32
[1]
v.blk.3.attn_v.output_min
F32
F32
[1]
v.blk.3.attn_v.weight
BF16
BF16
[768, 768]
v.blk.3.ffn_down.input_max
F32
F32
[1]
v.blk.3.ffn_down.input_min
F32
F32
[1]
v.blk.3.ffn_down.output_max
F32
F32
[1]
v.blk.3.ffn_down.output_min
F32
F32
[1]
v.blk.3.ffn_down.weight
BF16
BF16
[3072, 768]
v.blk.3.ffn_gate.input_max
F32
F32
[1]
v.blk.3.ffn_gate.input_min
F32
F32
[1]
v.blk.3.ffn_gate.output_max
F32
F32
[1]
v.blk.3.ffn_gate.output_min
F32
F32
[1]
v.blk.3.ffn_gate.weight
BF16
BF16
[768, 3072]
v.blk.3.ffn_post_norm.weight
F32
F32
[768]
v.blk.3.ffn_up.input_max
F32
F32
[1]
v.blk.3.ffn_up.input_min
F32
F32
[1]
v.blk.3.ffn_up.output_max
F32
F32
[1]
v.blk.3.ffn_up.output_min
F32
F32
[1]
v.blk.3.ffn_up.weight
BF16
BF16
[768, 3072]
v.blk.3.ln1.weight
F32
F32
[768]
v.blk.3.ln2.weight
F32
F32
[768]
v.blk.4
v.blk.4.attn_k.input_max
F32
F32
[1]
v.blk.4.attn_k.input_min
F32
F32
[1]
v.blk.4.attn_k.output_max
F32
F32
[1]
v.blk.4.attn_k.output_min
F32
F32
[1]
v.blk.4.attn_k.weight
BF16
BF16
[768, 768]
v.blk.4.attn_k_norm.weight
F32
F32
[64]
v.blk.4.attn_out.input_max
F32
F32
[1]
v.blk.4.attn_out.input_min
F32
F32
[1]
v.blk.4.attn_out.output_max
F32
F32
[1]
v.blk.4.attn_out.output_min
F32
F32
[1]
v.blk.4.attn_out.weight
BF16
BF16
[768, 768]
v.blk.4.attn_post_norm.weight
F32
F32
[768]
v.blk.4.attn_q.input_max
F32
F32
[1]
v.blk.4.attn_q.input_min
F32
F32
[1]
v.blk.4.attn_q.output_max
F32
F32
[1]
v.blk.4.attn_q.output_min
F32
F32
[1]
v.blk.4.attn_q.weight
BF16
BF16
[768, 768]
v.blk.4.attn_q_norm.weight
F32
F32
[64]
v.blk.4.attn_v.input_max
F32
F32
[1]
v.blk.4.attn_v.input_min
F32
F32
[1]
v.blk.4.attn_v.output_max
F32
F32
[1]
v.blk.4.attn_v.output_min
F32
F32
[1]
v.blk.4.attn_v.weight
BF16
BF16
[768, 768]
v.blk.4.ffn_down.input_max
F32
F32
[1]
v.blk.4.ffn_down.input_min
F32
F32
[1]
v.blk.4.ffn_down.output_max
F32
F32
[1]
v.blk.4.ffn_down.output_min
F32
F32
[1]
v.blk.4.ffn_down.weight
BF16
BF16
[3072, 768]
v.blk.4.ffn_gate.input_max
F32
F32
[1]
v.blk.4.ffn_gate.input_min
F32
F32
[1]
v.blk.4.ffn_gate.output_max
F32
F32
[1]
v.blk.4.ffn_gate.output_min
F32
F32
[1]
v.blk.4.ffn_gate.weight
BF16
BF16
[768, 3072]
v.blk.4.ffn_post_norm.weight
F32
F32
[768]
v.blk.4.ffn_up.input_max
F32
F32
[1]
v.blk.4.ffn_up.input_min
F32
F32
[1]
v.blk.4.ffn_up.output_max
F32
F32
[1]
v.blk.4.ffn_up.output_min
F32
F32
[1]
v.blk.4.ffn_up.weight
BF16
BF16
[768, 3072]
v.blk.4.ln1.weight
F32
F32
[768]
v.blk.4.ln2.weight
F32
F32
[768]
v.blk.5
v.blk.5.attn_k.input_max
F32
F32
[1]
v.blk.5.attn_k.input_min
F32
F32
[1]
v.blk.5.attn_k.output_max
F32
F32
[1]
v.blk.5.attn_k.output_min
F32
F32
[1]
v.blk.5.attn_k.weight
BF16
BF16
[768, 768]
v.blk.5.attn_k_norm.weight
F32
F32
[64]
v.blk.5.attn_out.input_max
F32
F32
[1]
v.blk.5.attn_out.input_min
F32
F32
[1]
v.blk.5.attn_out.output_max
F32
F32
[1]
v.blk.5.attn_out.output_min
F32
F32
[1]
v.blk.5.attn_out.weight
BF16
BF16
[768, 768]
v.blk.5.attn_post_norm.weight
F32
F32
[768]
v.blk.5.attn_q.input_max
F32
F32
[1]
v.blk.5.attn_q.input_min
F32
F32
[1]
v.blk.5.attn_q.output_max
F32
F32
[1]
v.blk.5.attn_q.output_min
F32
F32
[1]
v.blk.5.attn_q.weight
BF16
BF16
[768, 768]
v.blk.5.attn_q_norm.weight
F32
F32
[64]
v.blk.5.attn_v.input_max
F32
F32
[1]
v.blk.5.attn_v.input_min
F32
F32
[1]
v.blk.5.attn_v.output_max
F32
F32
[1]
v.blk.5.attn_v.output_min
F32
F32
[1]
v.blk.5.attn_v.weight
BF16
BF16
[768, 768]
v.blk.5.ffn_down.input_max
F32
F32
[1]
v.blk.5.ffn_down.input_min
F32
F32
[1]
v.blk.5.ffn_down.output_max
F32
F32
[1]
v.blk.5.ffn_down.output_min
F32
F32
[1]
v.blk.5.ffn_down.weight
BF16
BF16
[3072, 768]
v.blk.5.ffn_gate.input_max
F32
F32
[1]
v.blk.5.ffn_gate.input_min
F32
F32
[1]
v.blk.5.ffn_gate.output_max
F32
F32
[1]
v.blk.5.ffn_gate.output_min
F32
F32
[1]
v.blk.5.ffn_gate.weight
BF16
BF16
[768, 3072]
v.blk.5.ffn_post_norm.weight
F32
F32
[768]
v.blk.5.ffn_up.input_max
F32
F32
[1]
v.blk.5.ffn_up.input_min
F32
F32
[1]
v.blk.5.ffn_up.output_max
F32
F32
[1]
v.blk.5.ffn_up.output_min
F32
F32
[1]
v.blk.5.ffn_up.weight
BF16
BF16
[768, 3072]
v.blk.5.ln1.weight
F32
F32
[768]
v.blk.5.ln2.weight
F32
F32
[768]
v.blk.6
v.blk.6.attn_k.input_max
F32
F32
[1]
v.blk.6.attn_k.input_min
F32
F32
[1]
v.blk.6.attn_k.output_max
F32
F32
[1]
v.blk.6.attn_k.output_min
F32
F32
[1]
v.blk.6.attn_k.weight
BF16
BF16
[768, 768]
v.blk.6.attn_k_norm.weight
F32
F32
[64]
v.blk.6.attn_out.input_max
F32
F32
[1]
v.blk.6.attn_out.input_min
F32
F32
[1]
v.blk.6.attn_out.output_max
F32
F32
[1]
v.blk.6.attn_out.output_min
F32
F32
[1]
v.blk.6.attn_out.weight
BF16
BF16
[768, 768]
v.blk.6.attn_post_norm.weight
F32
F32
[768]
v.blk.6.attn_q.input_max
F32
F32
[1]
v.blk.6.attn_q.input_min
F32
F32
[1]
v.blk.6.attn_q.output_max
F32
F32
[1]
v.blk.6.attn_q.output_min
F32
F32
[1]
v.blk.6.attn_q.weight
BF16
BF16
[768, 768]
v.blk.6.attn_q_norm.weight
F32
F32
[64]
v.blk.6.attn_v.input_max
F32
F32
[1]
v.blk.6.attn_v.input_min
F32
F32
[1]
v.blk.6.attn_v.output_max
F32
F32
[1]
v.blk.6.attn_v.output_min
F32
F32
[1]
v.blk.6.attn_v.weight
BF16
BF16
[768, 768]
v.blk.6.ffn_down.input_max
F32
F32
[1]
v.blk.6.ffn_down.input_min
F32
F32
[1]
v.blk.6.ffn_down.output_max
F32
F32
[1]
v.blk.6.ffn_down.output_min
F32
F32
[1]
v.blk.6.ffn_down.weight
BF16
BF16
[3072, 768]
v.blk.6.ffn_gate.input_max
F32
F32
[1]
v.blk.6.ffn_gate.input_min
F32
F32
[1]
v.blk.6.ffn_gate.output_max
F32
F32
[1]
v.blk.6.ffn_gate.output_min
F32
F32
[1]
v.blk.6.ffn_gate.weight
BF16
BF16
[768, 3072]
v.blk.6.ffn_post_norm.weight
F32
F32
[768]
v.blk.6.ffn_up.input_max
F32
F32
[1]
v.blk.6.ffn_up.input_min
F32
F32
[1]
v.blk.6.ffn_up.output_max
F32
F32
[1]
v.blk.6.ffn_up.output_min
F32
F32
[1]
v.blk.6.ffn_up.weight
BF16
BF16
[768, 3072]
v.blk.6.ln1.weight
F32
F32
[768]
v.blk.6.ln2.weight
F32
F32
[768]
v.blk.7
v.blk.7.attn_k.input_max
F32
F32
[1]
v.blk.7.attn_k.input_min
F32
F32
[1]
v.blk.7.attn_k.output_max
F32
F32
[1]
v.blk.7.attn_k.output_min
F32
F32
[1]
v.blk.7.attn_k.weight
BF16
BF16
[768, 768]
v.blk.7.attn_k_norm.weight
F32
F32
[64]
v.blk.7.attn_out.input_max
F32
F32
[1]
v.blk.7.attn_out.input_min
F32
F32
[1]
v.blk.7.attn_out.output_max
F32
F32
[1]
v.blk.7.attn_out.output_min
F32
F32
[1]
v.blk.7.attn_out.weight
BF16
BF16
[768, 768]
v.blk.7.attn_post_norm.weight
F32
F32
[768]
v.blk.7.attn_q.input_max
F32
F32
[1]
v.blk.7.attn_q.input_min
F32
F32
[1]
v.blk.7.attn_q.output_max
F32
F32
[1]
v.blk.7.attn_q.output_min
F32
F32
[1]
v.blk.7.attn_q.weight
BF16
BF16
[768, 768]
v.blk.7.attn_q_norm.weight
F32
F32
[64]
v.blk.7.attn_v.input_max
F32
F32
[1]
v.blk.7.attn_v.input_min
F32
F32
[1]
v.blk.7.attn_v.output_max
F32
F32
[1]
v.blk.7.attn_v.output_min
F32
F32
[1]
v.blk.7.attn_v.weight
BF16
BF16
[768, 768]
v.blk.7.ffn_down.input_max
F32
F32
[1]
v.blk.7.ffn_down.input_min
F32
F32
[1]
v.blk.7.ffn_down.output_max
F32
F32
[1]
v.blk.7.ffn_down.output_min
F32
F32
[1]
v.blk.7.ffn_down.weight
BF16
BF16
[3072, 768]
v.blk.7.ffn_gate.input_max
F32
F32
[1]
v.blk.7.ffn_gate.input_min
F32
F32
[1]
v.blk.7.ffn_gate.output_max
F32
F32
[1]
v.blk.7.ffn_gate.output_min
F32
F32
[1]
v.blk.7.ffn_gate.weight
BF16
BF16
[768, 3072]
v.blk.7.ffn_post_norm.weight
F32
F32
[768]
v.blk.7.ffn_up.input_max
F32
F32
[1]
v.blk.7.ffn_up.input_min
F32
F32
[1]
v.blk.7.ffn_up.output_max
F32
F32
[1]
v.blk.7.ffn_up.output_min
F32
F32
[1]
v.blk.7.ffn_up.weight
BF16
BF16
[768, 3072]
v.blk.7.ln1.weight
F32
F32
[768]
v.blk.7.ln2.weight
F32
F32
[768]
v.blk.8
v.blk.8.attn_k.input_max
F32
F32
[1]
v.blk.8.attn_k.input_min
F32
F32
[1]
v.blk.8.attn_k.output_max
F32
F32
[1]
v.blk.8.attn_k.output_min
F32
F32
[1]
v.blk.8.attn_k.weight
BF16
BF16
[768, 768]
v.blk.8.attn_k_norm.weight
F32
F32
[64]
v.blk.8.attn_out.input_max
F32
F32
[1]
v.blk.8.attn_out.input_min
F32
F32
[1]
v.blk.8.attn_out.output_max
F32
F32
[1]
v.blk.8.attn_out.output_min
F32
F32
[1]
v.blk.8.attn_out.weight
BF16
BF16
[768, 768]
v.blk.8.attn_post_norm.weight
F32
F32
[768]
v.blk.8.attn_q.input_max
F32
F32
[1]
v.blk.8.attn_q.input_min
F32
F32
[1]
v.blk.8.attn_q.output_max
F32
F32
[1]
v.blk.8.attn_q.output_min
F32
F32
[1]
v.blk.8.attn_q.weight
BF16
BF16
[768, 768]
v.blk.8.attn_q_norm.weight
F32
F32
[64]
v.blk.8.attn_v.input_max
F32
F32
[1]
v.blk.8.attn_v.input_min
F32
F32
[1]
v.blk.8.attn_v.output_max
F32
F32
[1]
v.blk.8.attn_v.output_min
F32
F32
[1]
v.blk.8.attn_v.weight
BF16
BF16
[768, 768]
v.blk.8.ffn_down.input_max
F32
F32
[1]
v.blk.8.ffn_down.input_min
F32
F32
[1]
v.blk.8.ffn_down.output_max
F32
F32
[1]
v.blk.8.ffn_down.output_min
F32
F32
[1]
v.blk.8.ffn_down.weight
BF16
BF16
[3072, 768]
v.blk.8.ffn_gate.input_max
F32
F32
[1]
v.blk.8.ffn_gate.input_min
F32
F32
[1]
v.blk.8.ffn_gate.output_max
F32
F32
[1]
v.blk.8.ffn_gate.output_min
F32
F32
[1]
v.blk.8.ffn_gate.weight
BF16
BF16
[768, 3072]
v.blk.8.ffn_post_norm.weight
F32
F32
[768]
v.blk.8.ffn_up.input_max
F32
F32
[1]
v.blk.8.ffn_up.input_min
F32
F32
[1]
v.blk.8.ffn_up.output_max
F32
F32
[1]
v.blk.8.ffn_up.output_min
F32
F32
[1]
v.blk.8.ffn_up.weight
BF16
BF16
[768, 3072]
v.blk.8.ln1.weight
F32
F32
[768]
v.blk.8.ln2.weight
F32
F32
[768]
v.blk.9
v.blk.9.attn_k.input_max
F32
F32
[1]
v.blk.9.attn_k.input_min
F32
F32
[1]
v.blk.9.attn_k.output_max
F32
F32
[1]
v.blk.9.attn_k.output_min
F32
F32
[1]
v.blk.9.attn_k.weight
BF16
BF16
[768, 768]
v.blk.9.attn_k_norm.weight
F32
F32
[64]
v.blk.9.attn_out.input_max
F32
F32
[1]
v.blk.9.attn_out.input_min
F32
F32
[1]
v.blk.9.attn_out.output_max
F32
F32
[1]
v.blk.9.attn_out.output_min
F32
F32
[1]
v.blk.9.attn_out.weight
BF16
BF16
[768, 768]
v.blk.9.attn_post_norm.weight
F32
F32
[768]
v.blk.9.attn_q.input_max
F32
F32
[1]
v.blk.9.attn_q.input_min
F32
F32
[1]
v.blk.9.attn_q.output_max
F32
F32
[1]
v.blk.9.attn_q.output_min
F32
F32
[1]
v.blk.9.attn_q.weight
BF16
BF16
[768, 768]
v.blk.9.attn_q_norm.weight
F32
F32
[64]
v.blk.9.attn_v.input_max
F32
F32
[1]
v.blk.9.attn_v.input_min
F32
F32
[1]
v.blk.9.attn_v.output_max
F32
F32
[1]
v.blk.9.attn_v.output_min
F32
F32
[1]
v.blk.9.attn_v.weight
BF16
BF16
[768, 768]
v.blk.9.ffn_down.input_max
F32
F32
[1]
v.blk.9.ffn_down.input_min
F32
F32
[1]
v.blk.9.ffn_down.output_max
F32
F32
[1]
v.blk.9.ffn_down.output_min
F32
F32
[1]
v.blk.9.ffn_down.weight
BF16
BF16
[3072, 768]
v.blk.9.ffn_gate.input_max
F32
F32
[1]
v.blk.9.ffn_gate.input_min
F32
F32
[1]
v.blk.9.ffn_gate.output_max
F32
F32
[1]
v.blk.9.ffn_gate.output_min
F32
F32
[1]
v.blk.9.ffn_gate.weight
BF16
BF16
[768, 3072]
v.blk.9.ffn_post_norm.weight
F32
F32
[768]
v.blk.9.ffn_up.input_max
F32
F32
[1]
v.blk.9.ffn_up.input_min
F32
F32
[1]
v.blk.9.ffn_up.output_max
F32
F32
[1]
v.blk.9.ffn_up.output_min
F32
F32
[1]
v.blk.9.ffn_up.weight
BF16
BF16
[768, 3072]
v.blk.9.ln1.weight
F32
F32
[768]
v.blk.9.ln2.weight
F32
F32
[768]
v.blk.10
v.blk.10.attn_k.input_max
F32
F32
[1]
v.blk.10.attn_k.input_min
F32
F32
[1]
v.blk.10.attn_k.output_max
F32
F32
[1]
v.blk.10.attn_k.output_min
F32
F32
[1]
v.blk.10.attn_k.weight
BF16
BF16
[768, 768]
v.blk.10.attn_k_norm.weight
F32
F32
[64]
v.blk.10.attn_out.input_max
F32
F32
[1]
v.blk.10.attn_out.input_min
F32
F32
[1]
v.blk.10.attn_out.output_max
F32
F32
[1]
v.blk.10.attn_out.output_min
F32
F32
[1]
v.blk.10.attn_out.weight
BF16
BF16
[768, 768]
v.blk.10.attn_post_norm.weight
F32
F32
[768]
v.blk.10.attn_q.input_max
F32
F32
[1]
v.blk.10.attn_q.input_min
F32
F32
[1]
v.blk.10.attn_q.output_max
F32
F32
[1]
v.blk.10.attn_q.output_min
F32
F32
[1]
v.blk.10.attn_q.weight
BF16
BF16
[768, 768]
v.blk.10.attn_q_norm.weight
F32
F32
[64]
v.blk.10.attn_v.input_max
F32
F32
[1]
v.blk.10.attn_v.input_min
F32
F32
[1]
v.blk.10.attn_v.output_max
F32
F32
[1]
v.blk.10.attn_v.output_min
F32
F32
[1]
v.blk.10.attn_v.weight
BF16
BF16
[768, 768]
v.blk.10.ffn_down.input_max
F32
F32
[1]
v.blk.10.ffn_down.input_min
F32
F32
[1]
v.blk.10.ffn_down.output_max
F32
F32
[1]
v.blk.10.ffn_down.output_min
F32
F32
[1]
v.blk.10.ffn_down.weight
BF16
BF16
[3072, 768]
v.blk.10.ffn_gate.input_max
F32
F32
[1]
v.blk.10.ffn_gate.input_min
F32
F32
[1]
v.blk.10.ffn_gate.output_max
F32
F32
[1]
v.blk.10.ffn_gate.output_min
F32
F32
[1]
v.blk.10.ffn_gate.weight
BF16
BF16
[768, 3072]
v.blk.10.ffn_post_norm.weight
F32
F32
[768]
v.blk.10.ffn_up.input_max
F32
F32
[1]
v.blk.10.ffn_up.input_min
F32
F32
[1]
v.blk.10.ffn_up.output_max
F32
F32
[1]
v.blk.10.ffn_up.output_min
F32
F32
[1]
v.blk.10.ffn_up.weight
BF16
BF16
[768, 3072]
v.blk.10.ln1.weight
F32
F32
[768]
v.blk.10.ln2.weight
F32
F32
[768]
v.blk.11
v.blk.11.attn_k.input_max
F32
F32
[1]
v.blk.11.attn_k.input_min
F32
F32
[1]
v.blk.11.attn_k.output_max
F32
F32
[1]
v.blk.11.attn_k.output_min
F32
F32
[1]
v.blk.11.attn_k.weight
BF16
BF16
[768, 768]
v.blk.11.attn_k_norm.weight
F32
F32
[64]
v.blk.11.attn_out.input_max
F32
F32
[1]
v.blk.11.attn_out.input_min
F32
F32
[1]
v.blk.11.attn_out.output_max
F32
F32
[1]
v.blk.11.attn_out.output_min
F32
F32
[1]
v.blk.11.attn_out.weight
BF16
BF16
[768, 768]
v.blk.11.attn_post_norm.weight
F32
F32
[768]
v.blk.11.attn_q.input_max
F32
F32
[1]
v.blk.11.attn_q.input_min
F32
F32
[1]
v.blk.11.attn_q.output_max
F32
F32
[1]
v.blk.11.attn_q.output_min
F32
F32
[1]
v.blk.11.attn_q.weight
BF16
BF16
[768, 768]
v.blk.11.attn_q_norm.weight
F32
F32
[64]
v.blk.11.attn_v.input_max
F32
F32
[1]
v.blk.11.attn_v.input_min
F32
F32
[1]
v.blk.11.attn_v.output_max
F32
F32
[1]
v.blk.11.attn_v.output_min
F32
F32
[1]
v.blk.11.attn_v.weight
BF16
BF16
[768, 768]
v.blk.11.ffn_down.input_max
F32
F32
[1]
v.blk.11.ffn_down.input_min
F32
F32
[1]
v.blk.11.ffn_down.output_max
F32
F32
[1]
v.blk.11.ffn_down.output_min
F32
F32
[1]
v.blk.11.ffn_down.weight
BF16
BF16
[3072, 768]
v.blk.11.ffn_gate.input_max
F32
F32
[1]
v.blk.11.ffn_gate.input_min
F32
F32
[1]
v.blk.11.ffn_gate.output_max
F32
F32
[1]
v.blk.11.ffn_gate.output_min
F32
F32
[1]
v.blk.11.ffn_gate.weight
BF16
BF16
[768, 3072]
v.blk.11.ffn_post_norm.weight
F32
F32
[768]
v.blk.11.ffn_up.input_max
F32
F32
[1]
v.blk.11.ffn_up.input_min
F32
F32
[1]
v.blk.11.ffn_up.output_max
F32
F32
[1]
v.blk.11.ffn_up.output_min
F32
F32
[1]
v.blk.11.ffn_up.weight
BF16
BF16
[768, 3072]
v.blk.11.ln1.weight
F32
F32
[768]
v.blk.11.ln2.weight
F32
F32
[768]
v.blk.12
v.blk.12.attn_k.input_max
F32
F32
[1]
v.blk.12.attn_k.input_min
F32
F32
[1]
v.blk.12.attn_k.output_max
F32
F32
[1]
v.blk.12.attn_k.output_min
F32
F32
[1]
v.blk.12.attn_k.weight
BF16
BF16
[768, 768]
v.blk.12.attn_k_norm.weight
F32
F32
[64]
v.blk.12.attn_out.input_max
F32
F32
[1]
v.blk.12.attn_out.input_min
F32
F32
[1]
v.blk.12.attn_out.output_max
F32
F32
[1]
v.blk.12.attn_out.output_min
F32
F32
[1]
v.blk.12.attn_out.weight
BF16
BF16
[768, 768]
v.blk.12.attn_post_norm.weight
F32
F32
[768]
v.blk.12.attn_q.input_max
F32
F32
[1]
v.blk.12.attn_q.input_min
F32
F32
[1]
v.blk.12.attn_q.output_max
F32
F32
[1]
v.blk.12.attn_q.output_min
F32
F32
[1]
v.blk.12.attn_q.weight
BF16
BF16
[768, 768]
v.blk.12.attn_q_norm.weight
F32
F32
[64]
v.blk.12.attn_v.input_max
F32
F32
[1]
v.blk.12.attn_v.input_min
F32
F32
[1]
v.blk.12.attn_v.output_max
F32
F32
[1]
v.blk.12.attn_v.output_min
F32
F32
[1]
v.blk.12.attn_v.weight
BF16
BF16
[768, 768]
v.blk.12.ffn_down.input_max
F32
F32
[1]
v.blk.12.ffn_down.input_min
F32
F32
[1]
v.blk.12.ffn_down.output_max
F32
F32
[1]
v.blk.12.ffn_down.output_min
F32
F32
[1]
v.blk.12.ffn_down.weight
BF16
BF16
[3072, 768]
v.blk.12.ffn_gate.input_max
F32
F32
[1]
v.blk.12.ffn_gate.input_min
F32
F32
[1]
v.blk.12.ffn_gate.output_max
F32
F32
[1]
v.blk.12.ffn_gate.output_min
F32
F32
[1]
v.blk.12.ffn_gate.weight
BF16
BF16
[768, 3072]
v.blk.12.ffn_post_norm.weight
F32
F32
[768]
v.blk.12.ffn_up.input_max
F32
F32
[1]
v.blk.12.ffn_up.input_min
F32
F32
[1]
v.blk.12.ffn_up.output_max
F32
F32
[1]
v.blk.12.ffn_up.output_min
F32
F32
[1]
v.blk.12.ffn_up.weight
BF16
BF16
[768, 3072]
v.blk.12.ln1.weight
F32
F32
[768]
v.blk.12.ln2.weight
F32
F32
[768]
v.blk.13
v.blk.13.attn_k.input_max
F32
F32
[1]
v.blk.13.attn_k.input_min
F32
F32
[1]
v.blk.13.attn_k.output_max
F32
F32
[1]
v.blk.13.attn_k.output_min
F32
F32
[1]
v.blk.13.attn_k.weight
BF16
BF16
[768, 768]
v.blk.13.attn_k_norm.weight
F32
F32
[64]
v.blk.13.attn_out.input_max
F32
F32
[1]
v.blk.13.attn_out.input_min
F32
F32
[1]
v.blk.13.attn_out.output_max
F32
F32
[1]
v.blk.13.attn_out.output_min
F32
F32
[1]
v.blk.13.attn_out.weight
BF16
BF16
[768, 768]
v.blk.13.attn_post_norm.weight
F32
F32
[768]
v.blk.13.attn_q.input_max
F32
F32
[1]
v.blk.13.attn_q.input_min
F32
F32
[1]
v.blk.13.attn_q.output_max
F32
F32
[1]
v.blk.13.attn_q.output_min
F32
F32
[1]
v.blk.13.attn_q.weight
BF16
BF16
[768, 768]
v.blk.13.attn_q_norm.weight
F32
F32
[64]
v.blk.13.attn_v.input_max
F32
F32
[1]
v.blk.13.attn_v.input_min
F32
F32
[1]
v.blk.13.attn_v.output_max
F32
F32
[1]
v.blk.13.attn_v.output_min
F32
F32
[1]
v.blk.13.attn_v.weight
BF16
BF16
[768, 768]
v.blk.13.ffn_down.input_max
F32
F32
[1]
v.blk.13.ffn_down.input_min
F32
F32
[1]
v.blk.13.ffn_down.output_max
F32
F32
[1]
v.blk.13.ffn_down.output_min
F32
F32
[1]
v.blk.13.ffn_down.weight
BF16
BF16
[3072, 768]
v.blk.13.ffn_gate.input_max
F32
F32
[1]
v.blk.13.ffn_gate.input_min
F32
F32
[1]
v.blk.13.ffn_gate.output_max
F32
F32
[1]
v.blk.13.ffn_gate.output_min
F32
F32
[1]
v.blk.13.ffn_gate.weight
BF16
BF16
[768, 3072]
v.blk.13.ffn_post_norm.weight
F32
F32
[768]
v.blk.13.ffn_up.input_max
F32
F32
[1]
v.blk.13.ffn_up.input_min
F32
F32
[1]
v.blk.13.ffn_up.output_max
F32
F32
[1]
v.blk.13.ffn_up.output_min
F32
F32
[1]
v.blk.13.ffn_up.weight
BF16
BF16
[768, 3072]
v.blk.13.ln1.weight
F32
F32
[768]
v.blk.13.ln2.weight
F32
F32
[768]
v.blk.14
v.blk.14.attn_k.input_max
F32
F32
[1]
v.blk.14.attn_k.input_min
F32
F32
[1]
v.blk.14.attn_k.output_max
F32
F32
[1]
v.blk.14.attn_k.output_min
F32
F32
[1]
v.blk.14.attn_k.weight
BF16
BF16
[768, 768]
v.blk.14.attn_k_norm.weight
F32
F32
[64]
v.blk.14.attn_out.input_max
F32
F32
[1]
v.blk.14.attn_out.input_min
F32
F32
[1]
v.blk.14.attn_out.output_max
F32
F32
[1]
v.blk.14.attn_out.output_min
F32
F32
[1]
v.blk.14.attn_out.weight
BF16
BF16
[768, 768]
v.blk.14.attn_post_norm.weight
F32
F32
[768]
v.blk.14.attn_q.input_max
F32
F32
[1]
v.blk.14.attn_q.input_min
F32
F32
[1]
v.blk.14.attn_q.output_max
F32
F32
[1]
v.blk.14.attn_q.output_min
F32
F32
[1]
v.blk.14.attn_q.weight
BF16
BF16
[768, 768]
v.blk.14.attn_q_norm.weight
F32
F32
[64]
v.blk.14.attn_v.input_max
F32
F32
[1]
v.blk.14.attn_v.input_min
F32
F32
[1]
v.blk.14.attn_v.output_max
F32
F32
[1]
v.blk.14.attn_v.output_min
F32
F32
[1]
v.blk.14.attn_v.weight
BF16
BF16
[768, 768]
v.blk.14.ffn_down.input_max
F32
F32
[1]
v.blk.14.ffn_down.input_min
F32
F32
[1]
v.blk.14.ffn_down.output_max
F32
F32
[1]
v.blk.14.ffn_down.output_min
F32
F32
[1]
v.blk.14.ffn_down.weight
BF16
BF16
[3072, 768]
v.blk.14.ffn_gate.input_max
F32
F32
[1]
v.blk.14.ffn_gate.input_min
F32
F32
[1]
v.blk.14.ffn_gate.output_max
F32
F32
[1]
v.blk.14.ffn_gate.output_min
F32
F32
[1]
v.blk.14.ffn_gate.weight
BF16
BF16
[768, 3072]
v.blk.14.ffn_post_norm.weight
F32
F32
[768]
v.blk.14.ffn_up.input_max
F32
F32
[1]
v.blk.14.ffn_up.input_min
F32
F32
[1]
v.blk.14.ffn_up.output_max
F32
F32
[1]
v.blk.14.ffn_up.output_min
F32
F32
[1]
v.blk.14.ffn_up.weight
BF16
BF16
[768, 3072]
v.blk.14.ln1.weight
F32
F32
[768]
v.blk.14.ln2.weight
F32
F32
[768]
v.blk.15
v.blk.15.attn_k.input_max
F32
F32
[1]
v.blk.15.attn_k.input_min
F32
F32
[1]
v.blk.15.attn_k.output_max
F32
F32
[1]
v.blk.15.attn_k.output_min
F32
F32
[1]
v.blk.15.attn_k.weight
BF16
BF16
[768, 768]
v.blk.15.attn_k_norm.weight
F32
F32
[64]
v.blk.15.attn_out.input_max
F32
F32
[1]
v.blk.15.attn_out.input_min
F32
F32
[1]
v.blk.15.attn_out.output_max
F32
F32
[1]
v.blk.15.attn_out.output_min
F32
F32
[1]
v.blk.15.attn_out.weight
BF16
BF16
[768, 768]
v.blk.15.attn_post_norm.weight
F32
F32
[768]
v.blk.15.attn_q.input_max
F32
F32
[1]
v.blk.15.attn_q.input_min
F32
F32
[1]
v.blk.15.attn_q.output_max
F32
F32
[1]
v.blk.15.attn_q.output_min
F32
F32
[1]
v.blk.15.attn_q.weight
BF16
BF16
[768, 768]
v.blk.15.attn_q_norm.weight
F32
F32
[64]
v.blk.15.attn_v.input_max
F32
F32
[1]
v.blk.15.attn_v.input_min
F32
F32
[1]
v.blk.15.attn_v.output_max
F32
F32
[1]
v.blk.15.attn_v.output_min
F32
F32
[1]
v.blk.15.attn_v.weight
BF16
BF16
[768, 768]
v.blk.15.ffn_down.input_max
F32
F32
[1]
v.blk.15.ffn_down.input_min
F32
F32
[1]
v.blk.15.ffn_down.output_max
F32
F32
[1]
v.blk.15.ffn_down.output_min
F32
F32
[1]
v.blk.15.ffn_down.weight
BF16
BF16
[3072, 768]
v.blk.15.ffn_gate.input_max
F32
F32
[1]
v.blk.15.ffn_gate.input_min
F32
F32
[1]
v.blk.15.ffn_gate.output_max
F32
F32
[1]
v.blk.15.ffn_gate.output_min
F32
F32
[1]
v.blk.15.ffn_gate.weight
BF16
BF16
[768, 3072]
v.blk.15.ffn_post_norm.weight
F32
F32
[768]
v.blk.15.ffn_up.input_max
F32
F32
[1]
v.blk.15.ffn_up.input_min
F32
F32
[1]
v.blk.15.ffn_up.output_max
F32
F32
[1]
v.blk.15.ffn_up.output_min
F32
F32
[1]
v.blk.15.ffn_up.weight
BF16
BF16
[768, 3072]
v.blk.15.ln1.weight
F32
F32
[768]
v.blk.15.ln2.weight
F32
F32
[768]
v.patch_embd.weight
F32
F32
[16, 16, 3, 768]
v.position_embd.weight
F32
F32
[768, 10240, 2]