Hugging Face's logo

chutesai
/
Llama-3.1-Tulu-3-405B-FP8-dynamic

Safetensors
llama
compressed-tensors
Model card Files Community
jondurbin commited on
Commit
decbda6
·
verified ·
1 Parent(s): 4d179b4

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. .gitattributes +1 -0
  2. config.json +78 -0
  3. generation_config.json +9 -0
  4. model-00001-of-00086.safetensors +3 -0
  5. model-00002-of-00086.safetensors +3 -0
  6. model-00003-of-00086.safetensors +3 -0
  7. model-00004-of-00086.safetensors +3 -0
  8. model-00005-of-00086.safetensors +3 -0
  9. model-00006-of-00086.safetensors +3 -0
  10. model-00007-of-00086.safetensors +3 -0
  11. model-00008-of-00086.safetensors +3 -0
  12. model-00009-of-00086.safetensors +3 -0
  13. model-00010-of-00086.safetensors +3 -0
  14. model-00011-of-00086.safetensors +3 -0
  15. model-00012-of-00086.safetensors +3 -0
  16. model-00013-of-00086.safetensors +3 -0
  17. model-00014-of-00086.safetensors +3 -0
  18. model-00015-of-00086.safetensors +3 -0
  19. model-00016-of-00086.safetensors +3 -0
  20. model-00017-of-00086.safetensors +3 -0
  21. model-00018-of-00086.safetensors +3 -0
  22. model-00019-of-00086.safetensors +3 -0
  23. model-00020-of-00086.safetensors +3 -0
  24. model-00021-of-00086.safetensors +3 -0
  25. model-00022-of-00086.safetensors +3 -0
  26. model-00023-of-00086.safetensors +3 -0
  27. model-00024-of-00086.safetensors +3 -0
  28. model-00025-of-00086.safetensors +3 -0
  29. model-00026-of-00086.safetensors +3 -0
  30. model-00027-of-00086.safetensors +3 -0
  31. model-00028-of-00086.safetensors +3 -0
  32. model-00029-of-00086.safetensors +3 -0
  33. model-00030-of-00086.safetensors +3 -0
  34. model-00031-of-00086.safetensors +3 -0
  35. model-00032-of-00086.safetensors +3 -0
  36. model-00033-of-00086.safetensors +3 -0
  37. model-00034-of-00086.safetensors +3 -0
  38. model-00035-of-00086.safetensors +3 -0
  39. model-00036-of-00086.safetensors +3 -0
  40. model-00037-of-00086.safetensors +3 -0
  41. model-00038-of-00086.safetensors +3 -0
  42. model-00039-of-00086.safetensors +3 -0
  43. model-00040-of-00086.safetensors +3 -0
  44. model-00041-of-00086.safetensors +3 -0
  45. model-00042-of-00086.safetensors +3 -0
  46. model-00043-of-00086.safetensors +3 -0
  47. model-00044-of-00086.safetensors +3 -0
  48. model-00045-of-00086.safetensors +3 -0
  49. model-00046-of-00086.safetensors +3 -0
  50. model-00047-of-00086.safetensors +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/Llama-3.1-Tulu-3-405B",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 16384,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 53248,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 128,
19
+ "num_hidden_layers": 126,
20
+ "num_key_value_heads": 8,
21
+ "pretraining_tp": 1,
22
+ "quantization_config": {
23
+ "config_groups": {
24
+ "group_0": {
25
+ "input_activations": {
26
+ "actorder": null,
27
+ "block_structure": null,
28
+ "dynamic": true,
29
+ "group_size": null,
30
+ "num_bits": 8,
31
+ "observer": null,
32
+ "observer_kwargs": {},
33
+ "strategy": "token",
34
+ "symmetric": true,
35
+ "type": "float"
36
+ },
37
+ "output_activations": null,
38
+ "targets": [
39
+ "Linear"
40
+ ],
41
+ "weights": {
42
+ "actorder": null,
43
+ "block_structure": null,
44
+ "dynamic": false,
45
+ "group_size": null,
46
+ "num_bits": 8,
47
+ "observer": "minmax",
48
+ "observer_kwargs": {},
49
+ "strategy": "channel",
50
+ "symmetric": true,
51
+ "type": "float"
52
+ }
53
+ }
54
+ },
55
+ "format": "float-quantized",
56
+ "global_compression_ratio": 1.5358243277028012,
57
+ "ignore": [
58
+ "lm_head"
59
+ ],
60
+ "kv_cache_scheme": null,
61
+ "quant_method": "compressed-tensors",
62
+ "quantization_status": "compressed"
63
+ },
64
+ "rms_norm_eps": 1e-05,
65
+ "rope_scaling": {
66
+ "factor": 8.0,
67
+ "high_freq_factor": 4.0,
68
+ "low_freq_factor": 1.0,
69
+ "original_max_position_embeddings": 8192,
70
+ "rope_type": "llama3"
71
+ },
72
+ "rope_theta": 500000.0,
73
+ "tie_word_embeddings": false,
74
+ "torch_dtype": "bfloat16",
75
+ "transformers_version": "4.48.1",
76
+ "use_cache": false,
77
+ "vocab_size": 128264
78
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.48.1"
9
+ }
model-00001-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c46b63226d0478c42f8d27ee8d6a1c099248cc17750b863f7e3009c4cd6d19e
3
+ size 4773450840
model-00002-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0439a93087c808004471c940d870f21e6a9af0207cf99b4e5c1d3d1792465103
3
+ size 4933097744
model-00003-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e8be4c79853223e84eacc8593148197c607bda41974c22bc33247fc6d13f468
3
+ size 4631063728
model-00004-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff1ca49cb51e545f8de6ded1179f49bde69885b3b7eb07a7a659cad0c2c6f981
3
+ size 4933097744
model-00005-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f47c039a30f31438c2bd66093314676aae0dfc71d479b2cc954072c344349e81
3
+ size 4631063728
model-00006-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcd43f67e1abdc431ff9c73ebbc1280ad61c8e653e2c1e3e576833915300e77c
3
+ size 4933097744
model-00007-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f512d46d3378f42aded3c02f8b49874c0267e5192153f83ddf9b5b4ef6ab971f
3
+ size 4631063728
model-00008-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d8e20449b3463d10e6fbf1803eac8b770a95649455bdd96bd7b2de735b876e2
3
+ size 4933097760
model-00009-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dfbed7d4452f6c7ab41825d8c8935af1d8d0e242c468fc0284d1c211aa8d9b3
3
+ size 4631063752
model-00010-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d11be0fc4c2acac94593b2b7759023f03f75312481c26b8f640b1eb0f497df8a
3
+ size 4933097760
model-00011-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5703c9ed58a935e98e08200cb4a046ab934ce1e61ec94cd7f87007b0d459ab1b
3
+ size 4631063752
model-00012-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4ee5925adf43c1b48df67952a168ab7f9686e8058f77232c28d3749b28affd8
3
+ size 4933097760
model-00013-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27f62da2b39ddf3e03dad1d69ba9d07ee1628d5d8e919c32b3da319025e5a208
3
+ size 4631063752
model-00014-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83522d2b72c0206f46165259e2a4ce38c4ea4195e58f7a94f58a291784127c8e
3
+ size 4933097760
model-00015-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cf7d08606906d3a4f279337fd77dc977b4fb772768df591a16e565e81d94f15
3
+ size 4631063752
model-00016-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db909fc808835052ada8ce62c4883d6e91d97c76808261f25314cd3d4f6c72d9
3
+ size 4933097760
model-00017-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07b63ca3326dbc7b6e0c72401985568f73f70117b592117c99d60e571873ee89
3
+ size 4631063752
model-00018-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fc91c89700b618da56b35d9c577da406a9b1f8c5e2eeb4ac626baae6456fb5b
3
+ size 4933097760
model-00019-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ad952490a6c1cbe5355bc81bfdc1724df1f917e14af5a0f0351a56769e28d9a
3
+ size 4631063752
model-00020-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f550ab7daf8e3309a0107228dd44603a60f4a5ccdf7a05136e562acb41c44769
3
+ size 4933097760
model-00021-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0c1427ea40221f24f7053444f698fbf592e23443ed20361070389526ff807fa
3
+ size 4631063752
model-00022-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab5367ea72915f6ad1fb766c8c64508b0e4aa508d1c8bf9c757ebee5d2b7616d
3
+ size 4933097760
model-00023-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89943e2b47b0fc6d5751e2751f9911c434e7dc1b29f5c22b8733c35663f98155
3
+ size 4631063752
model-00024-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30e2ac30f1c4ec50d5ec0c7f553a3d439037fca9b6bf6c7a3f5d45603a80535c
3
+ size 4933097760
model-00025-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7520becc7adf57f413c0aae817dd376ef9d44677593dbae6a7fbeb5785b9158
3
+ size 4631063752
model-00026-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82733a936d7b6a4855b9b482d8bb8d97a64dead51a75b8590325f354a0627148
3
+ size 4933097760
model-00027-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:552cb54964e90c3c64e83fb854d1052bfe4102ae0d592a86b4b94836e88f20af
3
+ size 4631063752
model-00028-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:469355551869c706d62b2e21f88fe91dc23772210fab3c8966f717309e99912f
3
+ size 4933097760
model-00029-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8003feae6115d63f8733a149b2d1c6cec485ed0c7d6efa8d42445a766ff518d9
3
+ size 4631063752
model-00030-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a27d725b44fd676a1abbf2b4eb6dacfbd5e569a9c5aaf514da494b93dbd51cae
3
+ size 4933097760
model-00031-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e85074cf2ddf3b389ab5e1209e30f78c923e4b12067c079ebfda002e059000e0
3
+ size 4631063752
model-00032-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2e2b804cd839226cde121188db91b8df9e91480f714f50ef799b3f32a6cc52b
3
+ size 4933097760
model-00033-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3771556183bff4b88e31c330961ec60134e10da85399f3f06bd09a7c4c74a2e1
3
+ size 4631063752
model-00034-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c4c20d53b2df17e8345bc3d0790db582b3bd973776c2f48c9af0f0dd77b5355
3
+ size 4933097760
model-00035-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab3703f68582b5d1a1cc2a07daac406fae2de8461b82107649d21c72b5a1676e
3
+ size 4631063752
model-00036-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37da0e9dffab3afaa333dd8a37bf5b6d58d9a2d1246a71922eb9ba6d9c599d41
3
+ size 4933097760
model-00037-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d25c55ae81d5b957e4a8a9de9141f3a8d8f70fd5e750afee3be9e6776c8c952
3
+ size 4631063752
model-00038-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce2f96ff6d58f958c9ea000e8a2ace9ef6b77f18fcc35b6fccaf6ad15496f8b0
3
+ size 4933097760
model-00039-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ace23934e6bdd9eef92a2a2cf4b167daaebeabebab4cf0beac9700439e61b28
3
+ size 4631063752
model-00040-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d8d4c7858612fcb756d6cc3840556707f54cab2247d862b1585cf94e8b97a88
3
+ size 4933097760
model-00041-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b63b3e48dfd0957089d52239cb8fc10cacad15d2576a42e2e1c86dccdadf937e
3
+ size 4631063752
model-00042-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ea4e39718586a49acced4bd73e48625fb04b4f36f129efc72091d574b645bbd
3
+ size 4933097760
model-00043-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b854f3abadcad4e1e923d4a36abd1a1648234f14709f2866024f606c4faf0861
3
+ size 4631063752
model-00044-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7773a9e84447e9dcab1317a6440b1700b0390885fb6fceec661d4579904c63ea
3
+ size 4933097760
model-00045-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f33ccfc982a6917a8467245724f7b8c3214b7135da1c502e37c77ed6e235aff0
3
+ size 4631063752
model-00046-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3f68c8376c585271e0a60da98e69d5501f33a946004fff0c305617e1e4135de
3
+ size 4933097760
model-00047-of-00086.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56183217745985c16f12c7e2307334713b485973656d8590b27182e83b6b0da0
3
+ size 4631063752