Hugging Face's logo

inventbot
/
Mixtral-8x7B-Instruct-v0.1-offloading-demo

Text Generation
Transformers
Safetensors
5 languages
mixtral
text-generation-inference
conversational
Inference Endpoints
8-bit precision
Model card Files Community
inventbot commited on
Commit
7eed62f
•
1 Parent(s): ccea462

Upload 266 files

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +15 -0
  2. config.json +30 -0
  3. generation_config.json +6 -0
  4. model-00001-of-00257.safetensors +3 -0
  5. model-00002-of-00257.safetensors +3 -0
  6. model-00003-of-00257.safetensors +3 -0
  7. model-00004-of-00257.safetensors +3 -0
  8. model-00005-of-00257.safetensors +3 -0
  9. model-00006-of-00257.safetensors +3 -0
  10. model-00007-of-00257.safetensors +3 -0
  11. model-00008-of-00257.safetensors +3 -0
  12. model-00009-of-00257.safetensors +3 -0
  13. model-00010-of-00257.safetensors +3 -0
  14. model-00011-of-00257.safetensors +3 -0
  15. model-00012-of-00257.safetensors +3 -0
  16. model-00013-of-00257.safetensors +3 -0
  17. model-00014-of-00257.safetensors +3 -0
  18. model-00015-of-00257.safetensors +3 -0
  19. model-00016-of-00257.safetensors +3 -0
  20. model-00017-of-00257.safetensors +3 -0
  21. model-00018-of-00257.safetensors +3 -0
  22. model-00019-of-00257.safetensors +3 -0
  23. model-00020-of-00257.safetensors +3 -0
  24. model-00021-of-00257.safetensors +3 -0
  25. model-00022-of-00257.safetensors +3 -0
  26. model-00023-of-00257.safetensors +3 -0
  27. model-00024-of-00257.safetensors +3 -0
  28. model-00025-of-00257.safetensors +3 -0
  29. model-00026-of-00257.safetensors +3 -0
  30. model-00027-of-00257.safetensors +3 -0
  31. model-00028-of-00257.safetensors +3 -0
  32. model-00029-of-00257.safetensors +3 -0
  33. model-00030-of-00257.safetensors +3 -0
  34. model-00031-of-00257.safetensors +3 -0
  35. model-00032-of-00257.safetensors +3 -0
  36. model-00033-of-00257.safetensors +3 -0
  37. model-00034-of-00257.safetensors +3 -0
  38. model-00035-of-00257.safetensors +3 -0
  39. model-00036-of-00257.safetensors +3 -0
  40. model-00037-of-00257.safetensors +3 -0
  41. model-00038-of-00257.safetensors +3 -0
  42. model-00039-of-00257.safetensors +3 -0
  43. model-00040-of-00257.safetensors +3 -0
  44. model-00041-of-00257.safetensors +3 -0
  45. model-00042-of-00257.safetensors +3 -0
  46. model-00043-of-00257.safetensors +3 -0
  47. model-00044-of-00257.safetensors +3 -0
  48. model-00045-of-00257.safetensors +3 -0
  49. model-00046-of-00257.safetensors +3 -0
  50. model-00047-of-00257.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ language:
4
+ - en
5
+ - fr
6
+ - it
7
+ - de
8
+ - es
9
+ library_name: transformers
10
+ tags:
11
+ - mixtral
12
+ - text-generation-inference
13
+ ---
14
+ Attention quantization: HQQ 4-bit, groupsize 64, compress zero, compress scale with groupsize 256 \
15
+ Experts quantization: HQQ 2-bit, groupsize 16, compress zero, compress scale with groupsize 128
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 32,
16
+ "num_experts_per_tok": 2,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 8,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 1000000.0,
23
+ "router_aux_loss_coef": 0.02,
24
+ "sliding_window": null,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float16",
27
+ "transformers_version": "4.36.1",
28
+ "use_cache": true,
29
+ "vocab_size": 32000
30
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.36.1"
6
+ }
model-00001-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e6b8e8b3d0cff8718ef3622766c6a514e5da9b6034def6265af4f2028f2f84a
3
+ size 1240395944
model-00002-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7d64d0681dc3b644868a2608324937e7d4b89dbcf1b3dd7cb2ff3364b10ce4c
3
+ size 66406180
model-00003-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac2f0fd2561d539711607f0e9b5a70754087c59d4b489489ef509327f3d60dd1
3
+ size 66406180
model-00004-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2e07f4e55eaa03f831a8443a2d94f343bd1ac0c687f94864ca390b53043a4dc
3
+ size 66406180
model-00005-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d17866532858321f69d3bdcb3f156126e84cdd04e8f9f64fae9ebdaa3040ed83
3
+ size 66406180
model-00006-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20897eb7d77423952a5a5934436854b1ca18d75b8af21d2f6bcb5a4ca0cfbe7
3
+ size 66406180
model-00007-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:893957a77d157d34bd3eed289374d09f6c02a8579e17e777682e6101f212df00
3
+ size 66406180
model-00008-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee11951b29f515551fea8fe8343c0c97d4229b555106358a9de10274290ac8ff
3
+ size 66406180
model-00009-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d8308fb6a9a1fc8759b3fe3a6db7fc42ad75bfd60646f69bda0e9134f6e60bf
3
+ size 66406180
model-00010-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df9fa88c718fcd21ac1e45d5c00b2eaefb61e0052b3e2f2f675a8b3a72ef006d
3
+ size 66406180
model-00011-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e030deeedfc014beef893422aa365b41d94968412922677cd6c1ee6596c0656d
3
+ size 66406180
model-00012-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfbde69ce0a6eada1b0a39ec120ff35655baa70482c560e419063b580d36bc5e
3
+ size 66406180
model-00013-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a15939d8797f9a105cdafa5244c6797673c74fe755d8e74cfaaf92e759f8d680
3
+ size 66406180
model-00014-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8e8ba089c01a132fd83a4cdf0057d376fc41ea6e23c06c1378416eb520861af
3
+ size 66406180
model-00015-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abf7f2cdfec13b81617ddca234917e72ba7e19f395756f19000dbb13ecba4f15
3
+ size 66406180
model-00016-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f8e8da4bd05e87cf196c929add07c802d06d3efb9446664c2d26213f785e9da
3
+ size 66406180
model-00017-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83132b730a7c61d31625738935322f5d150fba431e2ca7bcde597e6c94905a6f
3
+ size 66406180
model-00018-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dccaa6806294214d7e2ae3a78ef8b42c93f01f6d3eafb6144e6afca0a95c11a6
3
+ size 66406180
model-00019-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98f970bfd49984b8e030e9f895beef190e0fdae3193741503702907ba793d498
3
+ size 66406180
model-00020-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:853660ffecbca507a55d964de38321c6f2830d5704810a1e19f2799b3f0817a2
3
+ size 66406180
model-00021-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7b4fdc4c8023f428f2ba79224aad8a97348fae8299e98c748d45b626d36c6cd
3
+ size 66406180
model-00022-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04e991c1d3b6e3344d982f49d6d3a4dcef38f44c243ef00723faddc811518ec3
3
+ size 66406180
model-00023-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c9ace78d7645114d6587b920f6396740bc3fdbba461a05f91d72afdaed81a94
3
+ size 66406180
model-00024-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b65172d7a40c36c31f9a47987dce8127420e71290966452bc63bf36083963a1
3
+ size 66406180
model-00025-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8a217c89357b7bac6fb439706080c0375a232e2a417aba6280159673d2eb8d3
3
+ size 66406180
model-00026-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3110c3f73f3082efd33a265664d3879508eb79ef3d0828d44e0faddef0c85b5c
3
+ size 66406180
model-00027-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3921ee7e27b576b68cb7dff8c085329391469f26876d5e15d4bb695fa1505e87
3
+ size 66406180
model-00028-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37cb0f986af753c7b7af54f42e9b665432daaacc31ae20baed69d049ef3eac04
3
+ size 66406180
model-00029-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a1d3e23c352d8fc5bfabe75bbfc09aed08a89c548936c6834249fd242fff39a
3
+ size 66406180
model-00030-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:666539b818696102cdb4b398836e0c3f3871b8252830371d159e3351b252a601
3
+ size 66406180
model-00031-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:036929e7af3644f82febcd96445b541824a353b4fff377cdf4a36324c49aa7b0
3
+ size 66406180
model-00032-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a307ceb9be505350f4c6170d7946cd6468fd3101f0a51edd5af40ddf88495a01
3
+ size 66406180
model-00033-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e43c3a49bee9f7d7d66d715b5ee4f9960fc58b01869c88f1d266f38ccc86a74d
3
+ size 66406180
model-00034-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b84107cbeddac74fbbd1a01c6d32692be05049f86e26b488a61b34413956b5ed
3
+ size 66406180
model-00035-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2e66e4e13e6b1593fa21319ae8eac0a5e67f111de81b8676cf7472275cc72d5
3
+ size 66406180
model-00036-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f56534a86cdbdcb88e3140a0ed57a3ffc117dd869e3dedd8bcd895144e71b7cd
3
+ size 66406180
model-00037-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79f45fcaeb36df38ecdc927d168e496121bb5959bca6d8f8d6bb36a0e6f9e95a
3
+ size 66406180
model-00038-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78ebb2c1fdca1b517ecf799ae8e66f95911b9d68b53bab5011258d278343b749
3
+ size 66406180
model-00039-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0c81ea4fcc820f1b4cffe76d68b4d51b4f29a5779d0655f7bf9873241b99700
3
+ size 66406180
model-00040-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a7e392025a6ea05ffbbc8a88a07b816c5ad423454a36c9f4f44982ce5864420
3
+ size 66406180
model-00041-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ea95b96fb1b80f55c2c3a176f48cf62aaff15c1580de515d5ca71fc666b5bbe
3
+ size 66406180
model-00042-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:429742ae668ea7e2f1f9c40d84fbff301ca93070f07ddecf837f0b19ea96bce6
3
+ size 66406180
model-00043-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cab00e5c6b422888817e8612cbd82d91139fee808ff7b38ba006a75560e52474
3
+ size 66406180
model-00044-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d00684b679d1b45e56a542fe01d677df0f11d064722805819d4d025e6f21223a
3
+ size 66406180
model-00045-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36f2466dba81b4fb74d2cf83f9379c9f8965f8980f2f176d84ae0b0a49f237fe
3
+ size 66406180
model-00046-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:298e7822f426e46299238485d38c9b883bb3309f214cbfb217d897d8e7c0519f
3
+ size 66406180
model-00047-of-00257.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8614bd8312acd4138cdc7fbf03e5a9af03e87107270cacfe2f02079c24384541
3
+ size 66406180