Hugging Face's logo

radi-cho
/
Meta-Llama-3.1-405B-Instruct-FLUTE

Model card Files Community
Radostin Cholakov commited on
Commit
6e84fad
•
1 Parent(s): 37baa0b

Add nf_w4g64.

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 +39 -0
  2. flute_config.json +5 -0
  3. generation_config.json +12 -0
  4. model-00001-of-00047.safetensors +3 -0
  5. model-00002-of-00047.safetensors +3 -0
  6. model-00003-of-00047.safetensors +3 -0
  7. model-00004-of-00047.safetensors +3 -0
  8. model-00005-of-00047.safetensors +3 -0
  9. model-00006-of-00047.safetensors +3 -0
  10. model-00007-of-00047.safetensors +3 -0
  11. model-00008-of-00047.safetensors +3 -0
  12. model-00009-of-00047.safetensors +3 -0
  13. model-00010-of-00047.safetensors +3 -0
  14. model-00011-of-00047.safetensors +3 -0
  15. model-00012-of-00047.safetensors +3 -0
  16. model-00013-of-00047.safetensors +3 -0
  17. model-00014-of-00047.safetensors +3 -0
  18. model-00015-of-00047.safetensors +3 -0
  19. model-00016-of-00047.safetensors +3 -0
  20. model-00017-of-00047.safetensors +3 -0
  21. model-00018-of-00047.safetensors +3 -0
  22. model-00019-of-00047.safetensors +3 -0
  23. model-00020-of-00047.safetensors +3 -0
  24. model-00021-of-00047.safetensors +3 -0
  25. model-00022-of-00047.safetensors +3 -0
  26. model-00023-of-00047.safetensors +3 -0
  27. model-00024-of-00047.safetensors +3 -0
  28. model-00025-of-00047.safetensors +3 -0
  29. model-00026-of-00047.safetensors +3 -0
  30. model-00027-of-00047.safetensors +3 -0
  31. model-00028-of-00047.safetensors +3 -0
  32. model-00029-of-00047.safetensors +3 -0
  33. model-00030-of-00047.safetensors +3 -0
  34. model-00031-of-00047.safetensors +3 -0
  35. model-00032-of-00047.safetensors +3 -0
  36. model-00033-of-00047.safetensors +3 -0
  37. model-00034-of-00047.safetensors +3 -0
  38. model-00035-of-00047.safetensors +3 -0
  39. model-00036-of-00047.safetensors +3 -0
  40. model-00037-of-00047.safetensors +3 -0
  41. model-00038-of-00047.safetensors +3 -0
  42. model-00039-of-00047.safetensors +3 -0
  43. model-00040-of-00047.safetensors +3 -0
  44. model-00041-of-00047.safetensors +3 -0
  45. model-00042-of-00047.safetensors +3 -0
  46. model-00043-of-00047.safetensors +3 -0
  47. model-00044-of-00047.safetensors +3 -0
  48. model-00045-of-00047.safetensors +3 -0
  49. model-00046-of-00047.safetensors +3 -0
  50. model-00047-of-00047.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/cl/scratch/model_weights/Meta-Llama-3.1-405B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "hidden_act": "silu",
15
+ "hidden_size": 16384,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 53248,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 128,
22
+ "num_hidden_layers": 126,
23
+ "num_key_value_heads": 16,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_scaling": {
27
+ "factor": 8.0,
28
+ "high_freq_factor": 4.0,
29
+ "low_freq_factor": 1.0,
30
+ "original_max_position_embeddings": 8192,
31
+ "rope_type": "llama3"
32
+ },
33
+ "rope_theta": 500000.0,
34
+ "tie_word_embeddings": false,
35
+ "torch_dtype": "float16",
36
+ "transformers_version": "4.44.2",
37
+ "use_cache": true,
38
+ "vocab_size": 128256
39
+ }
flute_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "num_sms": 108,
3
+ "num_bits": 4,
4
+ "group_size": 64
5
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.44.2"
12
+ }
model-00001-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:495dcbdec465c627fff4bfc2fc00f031dcd0be35672c610edf844fe48321d0fb
3
+ size 4987035088
model-00002-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f30d9c03f342b8e260f426fd1a3b839e5c40df250eed0af50e04f57b8103f58e
3
+ size 4670584640
model-00003-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e4741c471a0d2a36531424baf2f50caafa0bfc1f42f8d40e6e867ad2f2642ef
3
+ size 4991448880
model-00004-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:579a254b5ce4e667e8f5a234a74640326c23772a1cf87d2e74adce669546053a
3
+ size 4955794296
model-00005-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87cc88fe5037ba89272bdff95b1b63715ef9a07557361f83effa9cf5332a51f0
3
+ size 4670518920
model-00006-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b130b5adc7914694846923aea96783535d31b9e17f2c9334bd6fb150adefb223
3
+ size 4670584728
model-00007-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a66603cf388fb8bd163c38eaf94b1730ff5ea57856d04d15e8ec2d534dcc0b02
3
+ size 4670584720
model-00008-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f40b97c2788325ebe23b61e5fadd59c25e5a0cf1b6fff492b84951a358695079
3
+ size 4991448968
model-00009-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc0b595c0c2ad39205d40eb0f7fcfc771628e7a07d97e24059c3ead421c1b641
3
+ size 4955794376
model-00010-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ad4d71a08f167bddbc6ca5271c95b52a2d71c5729650f607b43f3a14d057ef4
3
+ size 4670518952
model-00011-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02d2ee43a6e3a32ed8a6727ea384c83e188d0723db35ab962ebe8966958c3042
3
+ size 4670584728
model-00012-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b482b70c133ed65f25413c8095127d5bbfeaf80052bd9bfef814ab6f12b65606
3
+ size 4670584720
model-00013-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41eae7b5b6fe0b0bee87b6201d0180502f29b2d7cf9c6979b28f692d939bd044
3
+ size 4991448968
model-00014-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdbe39de3eed4154710cc66c51f1398cdd9ff305f78daf46836f2f15ff0d64a6
3
+ size 4955794376
model-00015-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80f493012ec20197abfce1ed51c64e78a3d859485b66980ec6818ba6eb4927e8
3
+ size 4670518952
model-00016-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21c60e876e7adc58e1ecc6f1365a6425444d14e72d856837dfe1a27045b1c693
3
+ size 4670584728
model-00017-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04b5487ae1c0dd41ec3b26e2be9ccc4b458cc7477bcbbd39dfe4e0998900ee19
3
+ size 4670584720
model-00018-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6bfbdfe61bc72eda15693fcd9ea65192cd3ca51949e3b40aea4a623d8f5ebcb
3
+ size 4991448968
model-00019-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b07be7d043bfb7fc0ada6ff6d3edfa9e3f336be0f98b2482b418612ff0fcddaa
3
+ size 4955794376
model-00020-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a95f1715ddeea09e709b37daf695c8f18fa61f49c1cdb0f74847944dc87c4684
3
+ size 4670518952
model-00021-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7d9068b777f7d38ed9b5e292cf9c74fc03bb2c40fbe64f236494e02ed732f09
3
+ size 4670584728
model-00022-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aab7531f7c810cbdabd3c2b0a88ca682c585a7ca63ee0e2a6f3ec1ae41d657a7
3
+ size 4670584720
model-00023-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b95f97a12518390eea5feb46e264d8073f6cfb8fa8180fcc1bd8a2cc5146a6a
3
+ size 4991448968
model-00024-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad6c7a4380df7e01151b6b72f239ef78631f9ae31c37e19a72db59a4f586f561
3
+ size 4955794376
model-00025-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dfef1c3f49d8bd140f9d9ec9da6b7916be115c4c14d3b6b5ef94e41c839ad1f
3
+ size 4670518952
model-00026-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20bfe584172cdfdafd0e7b7fdf9b0398ade0648079cc11cfe8150df70f1dd1bd
3
+ size 4670584728
model-00027-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c23e5ad6f2c0ad51d31540e1a33bb860f307b84068422c130645969cfa0c596
3
+ size 4670584720
model-00028-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a52e31f73dfd028abbf3bfa7444cfc12a6fbbdadd3f3fe9070866ac3ef309a4f
3
+ size 4991448968
model-00029-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f715e036a265aec816b4cd59da6aa1c2b48b3c97ca7c1f2c13b865374d1f9f3
3
+ size 4955794376
model-00030-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b2563157a7103839327f7cf6c777239232556d559b15ac751949fa288473631
3
+ size 4670518952
model-00031-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3b80b6ead51494ae5fccbd331729aabc6c3968d621615544377cf2797c6a561
3
+ size 4670584728
model-00032-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:751279fd463a80381cc217df25d7902fc5377d85999202acfe56b5e140bc1908
3
+ size 4670584720
model-00033-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f7ee873f06aa2d9caceea66c47930736cad143117003178f31592fa486f8ef5
3
+ size 4991448968
model-00034-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98d90f0ee70a97f5e87d24be83268694619e1840b2f61ae87355b61658a8c251
3
+ size 4955794376
model-00035-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58c8ce057b106c074fb7234a3da9cadb158987f98997c477a4f57622020ae531
3
+ size 4670518952
model-00036-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4550b0c3c2d70c113eae6088821c73cb59e97c26e2441f364d12b56a6c0a8bf
3
+ size 4670584728
model-00037-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ded90644f6b7446e0a2edb77c4ba40492535c6c35a1ea029151debe502621ed9
3
+ size 4670584760
model-00038-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccb762690eba441f3dca87e7ef3256bedcb45ceafd686c7ae908dafaef55a685
3
+ size 4991449056
model-00039-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b8ca1f19ce114ee1ba608f18da35185766b4e8bfa742f120063132b6e0dacbe
3
+ size 4955794456
model-00040-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d53bfc16505c0a94cc7b11d69beb8684d0830ea639628ee45f81fa986103b040
3
+ size 4670519032
model-00041-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a3e5251b394bc18aad2f7dccd37b5ad20a26327fcf17c9b130f4c70a791d71e
3
+ size 4670584816
model-00042-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52669921944ce039b80e0c37ce9267b853b0903e80b6460941386d5366b9f2f5
3
+ size 4670584808
model-00043-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad14fa4064f39cfad7d70a85c257440620882f452f941c69683683655b17d842
3
+ size 4991449056
model-00044-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49cc063874d78aa9737263f6a9d79eb59b021268054676df9fa222caa35de35e
3
+ size 4955794456
model-00045-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d56bb26080b9ef93eb550efc755c9c8cb100660d288d2dba16bf6787ad65fd30
3
+ size 4670519032
model-00046-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40998c0dad827e3474d41666db710ba3521eeef7e3a69046fa75ee8c7e3ca5ee
3
+ size 3886275304
model-00047-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56b10aec9a93280980a830629be8161bacec7e0f741f7b87e5fcb3de68104edb
3
+ size 4202692736