Hugging Face's logo

OpenTransformer
/
unary-quantization-research

Safetensors
English
quantization
unary
thermometer-encoding
inference-engine
low-bit
Model card Files
xet
Community
OpenTransformer commited on
Commit
dacba62
·
verified ·
1 Parent(s): a23121d

Add files using upload-large-folder tool

Browse files
Files changed (20) hide show
  1. qwen3-4b-thinking-unary/model_layers_0_self_attn_o_proj_weight.scales +0 -0
  2. qwen3-4b-thinking-unary/model_layers_0_self_attn_v_proj_weight.scales +0 -0
  3. qwen3-4b-thinking-unary/model_layers_12_mlp_gate_proj_weight.scales +0 -0
  4. qwen3-4b-thinking-unary/model_layers_13_mlp_up_proj_weight.scales +0 -0
  5. qwen3-4b-thinking-unary/model_layers_15_self_attn_o_proj_weight.scales +0 -0
  6. qwen3-4b-thinking-unary/model_layers_18_self_attn_q_norm_weight.fp16 +0 -0
  7. qwen3-4b-thinking-unary/model_layers_20_mlp_down_proj_weight.scales +0 -0
  8. qwen3-4b-thinking-unary/model_layers_20_self_attn_k_proj_weight.scales +0 -0
  9. qwen3-4b-thinking-unary/model_layers_23_self_attn_q_norm_weight.fp16 +0 -0
  10. qwen3-4b-thinking-unary/model_layers_24_post_attention_layernorm_weight.fp16 +0 -0
  11. qwen3-4b-thinking-unary/model_layers_28_self_attn_v_proj_weight.scales +0 -0
  12. qwen3-4b-thinking-unary/model_layers_2_self_attn_o_proj_weight.scales +0 -0
  13. qwen3-4b-thinking-unary/model_layers_32_self_attn_v_proj_weight.scales +0 -0
  14. qwen3-4b-thinking-unary/model_layers_33_mlp_down_proj_weight.scales +0 -0
  15. qwen3-4b-thinking-unary/model_layers_33_mlp_up_proj_weight.scales +0 -0
  16. qwen3-4b-thinking-unary/model_layers_33_self_attn_k_norm_weight.fp16 +0 -0
  17. qwen3-4b-thinking-unary/model_layers_35_mlp_down_proj_weight.scales +0 -0
  18. qwen3-4b-thinking-unary/model_layers_5_mlp_up_proj_weight.scales +0 -0
  19. qwen3-4b-thinking-unary/model_layers_5_self_attn_k_norm_weight.fp16 +0 -0
  20. qwen3-4b-thinking-unary/model_layers_8_self_attn_o_proj_weight.scales +0 -0
qwen3-4b-thinking-unary/model_layers_0_self_attn_o_proj_weight.scales ADDED
Binary file (10.2 kB). View file
 
qwen3-4b-thinking-unary/model_layers_0_self_attn_v_proj_weight.scales ADDED
Binary file (4.1 kB). View file
 
qwen3-4b-thinking-unary/model_layers_12_mlp_gate_proj_weight.scales ADDED
Binary file (38.9 kB). View file
 
qwen3-4b-thinking-unary/model_layers_13_mlp_up_proj_weight.scales ADDED
Binary file (38.9 kB). View file
 
qwen3-4b-thinking-unary/model_layers_15_self_attn_o_proj_weight.scales ADDED
Binary file (10.2 kB). View file
 
qwen3-4b-thinking-unary/model_layers_18_self_attn_q_norm_weight.fp16 ADDED
Binary file (256 Bytes). View file
 
qwen3-4b-thinking-unary/model_layers_20_mlp_down_proj_weight.scales ADDED
Binary file (10.2 kB). View file
 
qwen3-4b-thinking-unary/model_layers_20_self_attn_k_proj_weight.scales ADDED
Binary file (4.1 kB). View file
 
qwen3-4b-thinking-unary/model_layers_23_self_attn_q_norm_weight.fp16 ADDED
Binary file (256 Bytes). View file
 
qwen3-4b-thinking-unary/model_layers_24_post_attention_layernorm_weight.fp16 ADDED
Binary file (5.12 kB). View file
 
qwen3-4b-thinking-unary/model_layers_28_self_attn_v_proj_weight.scales ADDED
Binary file (4.1 kB). View file
 
qwen3-4b-thinking-unary/model_layers_2_self_attn_o_proj_weight.scales ADDED
Binary file (10.2 kB). View file
 
qwen3-4b-thinking-unary/model_layers_32_self_attn_v_proj_weight.scales ADDED
Binary file (4.1 kB). View file
 
qwen3-4b-thinking-unary/model_layers_33_mlp_down_proj_weight.scales ADDED
Binary file (10.2 kB). View file
 
qwen3-4b-thinking-unary/model_layers_33_mlp_up_proj_weight.scales ADDED
Binary file (38.9 kB). View file
 
qwen3-4b-thinking-unary/model_layers_33_self_attn_k_norm_weight.fp16 ADDED
Binary file (256 Bytes). View file
 
qwen3-4b-thinking-unary/model_layers_35_mlp_down_proj_weight.scales ADDED
Binary file (10.2 kB). View file
 
qwen3-4b-thinking-unary/model_layers_5_mlp_up_proj_weight.scales ADDED
Binary file (38.9 kB). View file
 
qwen3-4b-thinking-unary/model_layers_5_self_attn_k_norm_weight.fp16 ADDED
Binary file (256 Bytes). View file
 
qwen3-4b-thinking-unary/model_layers_8_self_attn_o_proj_weight.scales ADDED
Binary file (10.2 kB). View file