Hugging Face's logo

Intel
/
GLM-5-int4-mixed-AutoRound

Safetensors
glm_moe_dsa
text-generation-inference
4-bit precision
auto-round
Model card Files
xet
 Community
2
xinhe commited on
Commit
3b094f4
·
verified ·
1 Parent(s): 8f3a474

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. config.json +100 -6
  2. generation_config.json +1 -1
  3. model-00001-of-00081.safetensors +3 -0
  4. model-00002-of-00081.safetensors +3 -0
  5. model-00003-of-00081.safetensors +3 -0
  6. model-00004-of-00081.safetensors +3 -0
  7. model-00005-of-00081.safetensors +3 -0
  8. model-00006-of-00081.safetensors +3 -0
  9. model-00007-of-00081.safetensors +3 -0
  10. model-00008-of-00081.safetensors +3 -0
  11. model-00009-of-00081.safetensors +3 -0
  12. model-00010-of-00081.safetensors +3 -0
  13. model-00011-of-00081.safetensors +3 -0
  14. model-00012-of-00081.safetensors +3 -0
  15. model-00013-of-00081.safetensors +3 -0
  16. model-00014-of-00081.safetensors +3 -0
  17. model-00015-of-00081.safetensors +3 -0
  18. model-00016-of-00081.safetensors +3 -0
  19. model-00017-of-00081.safetensors +3 -0
  20. model-00018-of-00081.safetensors +3 -0
  21. model-00019-of-00081.safetensors +3 -0
  22. model-00020-of-00081.safetensors +3 -0
  23. model-00021-of-00081.safetensors +3 -0
  24. model-00022-of-00081.safetensors +3 -0
  25. model-00023-of-00081.safetensors +3 -0
  26. model-00024-of-00081.safetensors +3 -0
  27. model-00025-of-00081.safetensors +3 -0
  28. model-00026-of-00081.safetensors +3 -0
  29. model-00027-of-00081.safetensors +3 -0
  30. model-00028-of-00081.safetensors +3 -0
  31. model-00029-of-00081.safetensors +3 -0
  32. model-00030-of-00081.safetensors +3 -0
  33. model-00031-of-00081.safetensors +3 -0
  34. model-00032-of-00081.safetensors +3 -0
  35. model-00033-of-00081.safetensors +3 -0
  36. model-00034-of-00081.safetensors +3 -0
  37. model-00035-of-00081.safetensors +3 -0
  38. model-00036-of-00081.safetensors +3 -0
  39. model-00037-of-00081.safetensors +3 -0
  40. model-00038-of-00081.safetensors +3 -0
  41. model-00039-of-00081.safetensors +3 -0
  42. model-00040-of-00081.safetensors +3 -0
  43. model-00041-of-00081.safetensors +3 -0
  44. model-00042-of-00081.safetensors +3 -0
  45. model-00043-of-00081.safetensors +3 -0
  46. model-00044-of-00081.safetensors +3 -0
  47. model-00045-of-00081.safetensors +3 -0
  48. model-00046-of-00081.safetensors +3 -0
  49. model-00047-of-00081.safetensors +3 -0
  50. model-00048-of-00081.safetensors +3 -0
config.json CHANGED
@@ -127,6 +127,46 @@
127
  "bits": 4,
128
  "data_type": "int",
129
  "extra_config": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
130
  "model.layers.0.mlp.down_proj": {
131
  "bits": 16,
132
  "data_type": "float"
@@ -3558,13 +3598,68 @@
3558
  "model.layers.9.self_attn.q_b_proj": {
3559
  "bits": 16,
3560
  "data_type": "float"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3561
  }
3562
  },
3563
- "group_size": 128,
3564
  "iters": 0,
3565
- "packing_format": "auto_round:auto_awq",
3566
  "quant_method": "auto-round",
3567
- "sym": false
 
 
 
3568
  },
3569
  "rms_norm_eps": 1e-05,
3570
  "rope_interleave": true,
@@ -3577,9 +3672,8 @@
3577
  "tie_word_embeddings": false,
3578
  "topk_group": 1,
3579
  "topk_method": "noaux_tc",
3580
- "transformers_version": "5.2.0",
3581
  "use_cache": true,
3582
  "v_head_dim": 256,
3583
- "vocab_size": 154880,
3584
- "torch_dtype": "float16"
3585
  }
 
127
  "bits": 4,
128
  "data_type": "int",
129
  "extra_config": {
130
+ ".*eh_proj.*": {
131
+ "bits": 16,
132
+ "data_type": "float"
133
+ },
134
+ ".*layers\\.0\\..*": {
135
+ "bits": 16,
136
+ "data_type": "float"
137
+ },
138
+ ".*layers\\.0\\.mlp.*": {
139
+ "bits": 16,
140
+ "data_type": "float"
141
+ },
142
+ ".*layers\\.1\\..*": {
143
+ "bits": 16,
144
+ "data_type": "float"
145
+ },
146
+ ".*layers\\.1\\.mlp.*": {
147
+ "bits": 16,
148
+ "data_type": "float"
149
+ },
150
+ ".*layers\\.2\\..*": {
151
+ "bits": 16,
152
+ "data_type": "float"
153
+ },
154
+ ".*layers\\.2\\.mlp.*": {
155
+ "bits": 16,
156
+ "data_type": "float"
157
+ },
158
+ ".*self_attn.*": {
159
+ "bits": 16,
160
+ "data_type": "float"
161
+ },
162
+ ".*shared_experts.*": {
163
+ "bits": 16,
164
+ "data_type": "float"
165
+ },
166
+ ".*weights_proj.*": {
167
+ "bits": 16,
168
+ "data_type": "float"
169
+ },
170
  "model.layers.0.mlp.down_proj": {
171
  "bits": 16,
172
  "data_type": "float"
 
3598
  "model.layers.9.self_attn.q_b_proj": {
3599
  "bits": 16,
3600
  "data_type": "float"
3601
+ },
3602
+ "model.layers.78.eh_proj": {
3603
+ "bits": 16,
3604
+ "data_type": "fp"
3605
+ },
3606
+ "model.layers.78.mlp.gate": {
3607
+ "bits": 16,
3608
+ "data_type": "fp"
3609
+ },
3610
+ "model.layers.78.mlp.shared_experts.down_proj": {
3611
+ "bits": 16,
3612
+ "data_type": "fp"
3613
+ },
3614
+ "model.layers.78.mlp.shared_experts.gate_proj": {
3615
+ "bits": 16,
3616
+ "data_type": "fp"
3617
+ },
3618
+ "model.layers.78.mlp.shared_experts.up_proj": {
3619
+ "bits": 16,
3620
+ "data_type": "fp"
3621
+ },
3622
+ "model.layers.78.self_attn.indexer.weights_proj": {
3623
+ "bits": 16,
3624
+ "data_type": "fp"
3625
+ },
3626
+ "model.layers.78.self_attn.indexer.wk": {
3627
+ "bits": 16,
3628
+ "data_type": "fp"
3629
+ },
3630
+ "model.layers.78.self_attn.indexer.wq_b": {
3631
+ "bits": 16,
3632
+ "data_type": "fp"
3633
+ },
3634
+ "model.layers.78.self_attn.kv_a_proj_with_mqa": {
3635
+ "bits": 16,
3636
+ "data_type": "fp"
3637
+ },
3638
+ "model.layers.78.self_attn.kv_b_proj": {
3639
+ "bits": 16,
3640
+ "data_type": "fp"
3641
+ },
3642
+ "model.layers.78.self_attn.o_proj": {
3643
+ "bits": 16,
3644
+ "data_type": "fp"
3645
+ },
3646
+ "model.layers.78.self_attn.q_a_proj": {
3647
+ "bits": 16,
3648
+ "data_type": "fp"
3649
+ },
3650
+ "model.layers.78.self_attn.q_b_proj": {
3651
+ "bits": 16,
3652
+ "data_type": "fp"
3653
  }
3654
  },
3655
+ "group_size": 64,
3656
  "iters": 0,
3657
+ "packing_format": "auto_round:auto_gptq",
3658
  "quant_method": "auto-round",
3659
+ "sym": true,
3660
+ "block_name_to_quantize": [
3661
+ "model.layers"
3662
+ ]
3663
  },
3664
  "rms_norm_eps": 1e-05,
3665
  "rope_interleave": true,
 
3672
  "tie_word_embeddings": false,
3673
  "topk_group": 1,
3674
  "topk_method": "noaux_tc",
3675
+ "transformers_version": "5.3.0.dev0",
3676
  "use_cache": true,
3677
  "v_head_dim": 256,
3678
+ "vocab_size": 154880
 
3679
  }
generation_config.json CHANGED
@@ -9,5 +9,5 @@
9
  "pad_token_id": 154820,
10
  "temperature": 1.0,
11
  "top_p": 0.95,
12
- "transformers_version": "5.2.0"
13
  }
 
9
  "pad_token_id": 154820,
10
  "temperature": 1.0,
11
  "top_p": 0.95,
12
+ "transformers_version": "5.3.0.dev0"
13
  }
model-00001-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b1197f76af0e5fd34095f0b153d6e47a3525c2e930b0e7d01e832f33e43c1eb
3
+ size 5365774416
model-00002-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a875080d271a6b6003e08afba16a0e5a2df25fdc7cfdc7229d150c6a2a7da08
3
+ size 5365732064
model-00003-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d36f352b0159aa275fb4eb17df8d77e79ebff249d8eaa8e687d597252a43a798
3
+ size 5365732064
model-00004-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed8b576ba3a07b265a7e05b6087ba43f5f15580908515d0722300e20a8bf4159
3
+ size 5365732176
model-00005-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fed86fb47c3d25d5ed87a703f28a8d45623d1c0e9039e0cb404732a7a6e63b30
3
+ size 5365732184
model-00006-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9657cc99336c9cbffb10648930f4b6b3c8368abdb80e630f346ce86f4d00e865
3
+ size 5365732184
model-00007-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:407ef6771d1e40a5af4057a59a5bade69e088a891f38b1fcc96eb42e743ca869
3
+ size 5365732184
model-00008-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1cf6cec1630e08d520fd178ad4129d7aebea8467e8a704a453104e75e0047b7
3
+ size 5365732512
model-00009-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:481455a5aae7805dbaad86bb79d7fc2e4eac70b03b5872d06c4ca3ab99392660
3
+ size 5365734384
model-00010-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fa4553377afdabdde9e77666b91b83943f54489b1c435580d5f0393ac04f592
3
+ size 5365734408
model-00011-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d22ed9a62d1dcd851c71439bda774f498801a1b42b6092e4fb5486ffbee78247
3
+ size 5247413488
model-00012-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02cbc14536522d7235f142ee5a97cc245ea818de5aa3578bcec6d1bd9aebf500
3
+ size 5368629832
model-00013-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec2517b5b27952713b1246f384a284649a4962d2ef36c4cb6e53d7a2d63c068d
3
+ size 5365734264
model-00014-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5196a9def170211598f323aa923f83ab414e4228d33170b3bb771fb1560efa08
3
+ size 5365734272
model-00015-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d48e4452e95de54f7d8d9685ee3e17f9e6d6dd835c4308c4854b08100285216f
3
+ size 5365734264
model-00016-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e018b0661f1c5c8ea1ff1844391e1e173d8f7d557aa04a396446624975d255ae
3
+ size 5365734264
model-00017-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cadadb60928c58a524319fe1302e6aa4c8a0b9b42b40984193fd4944ff0d8ecc
3
+ size 5365734272
model-00018-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:095945ddf50b9d2937836b60e3ef92fd08543f0136166c0ec422eccdb5636c29
3
+ size 5365734264
model-00019-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84e5ab9d0b63c9350dab81fac7126d49ecd3ce0177700c96671d0d80028efee7
3
+ size 5365734264
model-00020-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bcb8ad254d324e0a498a972a5db9ab445c46e6b52f6e64904e9beac4b91c8ed
3
+ size 5365734272
model-00021-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b2b1f19b9692b4711f8ea347bf36f6b18d8e5c9d2d39461a46be80534d796a1
3
+ size 5365734264
model-00022-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b69db1f9ca66783117f9bdf6adb4a03c884844be732a090f2e2aad874e574b13
3
+ size 5365734264
model-00023-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7b19612e7c89ce57921fd953321656facf7e3996f75f7065d94f67b1c970807
3
+ size 5365734272
model-00024-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a4747b09af8ba3f5a695286084e66b2c2a208a12f71e6b6e61a9cbdb8889c8f
3
+ size 5365734328
model-00025-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:132af142adbdbe086481faa380772ed7eeb2d7ba4bc2ef1e8aacc9aaeeef12f9
3
+ size 5365734384
model-00026-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f46738a8455d686053125a094abea1cce28b3ccb921f742fb36fc563faf28d9
3
+ size 5365734392
model-00027-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cee2e736e2a7e363acf251d39b152ac3c112d599ec48db7900c77c33c4893306
3
+ size 5365734384
model-00028-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5af9571bb77313fcb776b1c77072612031ec0e1f88f0f82584a0a7b067c1b5db
3
+ size 5365734384
model-00029-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e66bd83cd3516fa2668ba75b1dd4ea0967462e49980f498eba0b0e8b3bdd8d9
3
+ size 5365734392
model-00030-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bed9157d14e0929091724310acb5fa425872a9bf284b8e631bab64914cb092b7
3
+ size 5365734384
model-00031-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7781dc5078ea16211d93dd3b135599d921c8cb96c00a581636571df9526769ff
3
+ size 5353773400
model-00032-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8f7dae429fb50432dce3553a509a6b913e656381923c64f0c051ab63c1d8bac
3
+ size 5332193040
model-00033-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:906e71bf3dae86967f335cd9d9e3d7828889caa172598b7904500ca53ca8637b
3
+ size 5363644672
model-00034-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:700543c4c04007998ed780a0fb7a180b31c3aa2cf07c4597b522200e71731641
3
+ size 5365734272
model-00035-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de6f4de39ee2a87bc8c53fa7c26c174e0d3f6885ff87e477e9e60e3599bfa470
3
+ size 5365734264
model-00036-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4eb2b296871f379c44de0672a415d164a9129ffb524f49a3cb3e4f26f483d9a
3
+ size 5365734264
model-00037-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b87d6781f20faad84abf1ed77ee33d9234ad5b96cebe8b84dccf57e1f6718edf
3
+ size 5365734272
model-00038-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed80736864bb9a38b49fd6127723b228009dcf175970cef47d467b34df500f57
3
+ size 5365734264
model-00039-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80f059915249a7e061f288b826ea8acf8e9d9fa087b3794a337e7b7f7631cb76
3
+ size 5365734264
model-00040-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4a1eb05f400c4135d61a19c87b59485542430854cb831fcfc322b06ca316c2d
3
+ size 5365734272
model-00041-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c76b5ceff7eaf533cf721dd97856da249ffe168fd54a99a6c20fd8e4d126fd4
3
+ size 5365734264
model-00042-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b57a502c3592e168c309fc5b6e0f787941bdff864bc75868f0d493c7e738698
3
+ size 5365734264
model-00043-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ee21f944255d4455d4e02332354bc0efcbb7461361bc14a11444f875251dc1c
3
+ size 5365734272
model-00044-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0196043da7c8f0f4b0866f0f468c7761173478ce7a05ccf8dade9fece015cfd4
3
+ size 5365734264
model-00045-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d2a41faef0a5ca06066ebef886bec281a055a13a761608d78af997dbc607513
3
+ size 5365734376
model-00046-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:194cf50429e9d0b2300f0a8637e68312ec73b04fd50ea116eb8b44113f148c25
3
+ size 5365734392
model-00047-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a73a340ec8e3d9d5b0603aa35bb060ebba01be201d521bbd4883a079449ef34
3
+ size 5365734384
model-00048-of-00081.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19be82586dcc749e19ede28423b4ead8cfe2249964c0e9df04698a9d7b27510a
3
+ size 5365734384