Hugging Face's logo

paulml
/
Qwen2-125B-Instruct

Text Generation
Transformers
Safetensors
qwen2
Merge
mergekit
lazymergekit
Qwen/Qwen2-72B-Instruct
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
paulml commited on
Commit
abe8d89
•
1 Parent(s): 9befbd4

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. README.md +21 -0
  2. added_tokens.json +5 -0
  3. config.json +28 -0
  4. mergekit_config.yml +38 -0
  5. merges.txt +0 -0
  6. model-00001-of-00140.safetensors +3 -0
  7. model-00002-of-00140.safetensors +3 -0
  8. model-00003-of-00140.safetensors +3 -0
  9. model-00004-of-00140.safetensors +3 -0
  10. model-00005-of-00140.safetensors +3 -0
  11. model-00006-of-00140.safetensors +3 -0
  12. model-00007-of-00140.safetensors +3 -0
  13. model-00008-of-00140.safetensors +3 -0
  14. model-00009-of-00140.safetensors +3 -0
  15. model-00010-of-00140.safetensors +3 -0
  16. model-00011-of-00140.safetensors +3 -0
  17. model-00012-of-00140.safetensors +3 -0
  18. model-00013-of-00140.safetensors +3 -0
  19. model-00014-of-00140.safetensors +3 -0
  20. model-00015-of-00140.safetensors +3 -0
  21. model-00016-of-00140.safetensors +3 -0
  22. model-00017-of-00140.safetensors +3 -0
  23. model-00018-of-00140.safetensors +3 -0
  24. model-00019-of-00140.safetensors +3 -0
  25. model-00020-of-00140.safetensors +3 -0
  26. model-00021-of-00140.safetensors +3 -0
  27. model-00022-of-00140.safetensors +3 -0
  28. model-00023-of-00140.safetensors +3 -0
  29. model-00024-of-00140.safetensors +3 -0
  30. model-00025-of-00140.safetensors +3 -0
  31. model-00026-of-00140.safetensors +3 -0
  32. model-00027-of-00140.safetensors +3 -0
  33. model-00028-of-00140.safetensors +3 -0
  34. model-00029-of-00140.safetensors +3 -0
  35. model-00030-of-00140.safetensors +3 -0
  36. model-00031-of-00140.safetensors +3 -0
  37. model-00032-of-00140.safetensors +3 -0
  38. model-00033-of-00140.safetensors +3 -0
  39. model-00034-of-00140.safetensors +3 -0
  40. model-00035-of-00140.safetensors +3 -0
  41. model-00036-of-00140.safetensors +3 -0
  42. model-00037-of-00140.safetensors +3 -0
  43. model-00038-of-00140.safetensors +3 -0
  44. model-00039-of-00140.safetensors +3 -0
  45. model-00040-of-00140.safetensors +3 -0
  46. model-00041-of-00140.safetensors +3 -0
  47. model-00042-of-00140.safetensors +3 -0
  48. model-00043-of-00140.safetensors +3 -0
  49. model-00044-of-00140.safetensors +3 -0
  50. model-00045-of-00140.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - merge
5
+ - mergekit
6
+ - lazymergekit
7
+ - Qwen/Qwen2-72B-Instruct
8
+ ---
9
+
10
+ # Qwen2-110B-Instruct
11
+
12
+ Qwen2-110B-Instruct is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
13
+ * [Qwen/Qwen2-72B-Instruct](https://huggingface.co/Qwen/Qwen2-72B-Instruct)
14
+ * [Qwen/Qwen2-72B-Instruct](https://huggingface.co/Qwen/Qwen2-72B-Instruct)
15
+ * [Qwen/Qwen2-72B-Instruct](https://huggingface.co/Qwen/Qwen2-72B-Instruct)
16
+ * [Qwen/Qwen2-72B-Instruct](https://huggingface.co/Qwen/Qwen2-72B-Instruct)
17
+ * [Qwen/Qwen2-72B-Instruct](https://huggingface.co/Qwen/Qwen2-72B-Instruct)
18
+ * [Qwen/Qwen2-72B-Instruct](https://huggingface.co/Qwen/Qwen2-72B-Instruct)
19
+ * [Qwen/Qwen2-72B-Instruct](https://huggingface.co/Qwen/Qwen2-72B-Instruct)
20
+
21
+ ## 🧩 Configuration
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen2-72B-Instruct",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 8192,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 29568,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 80,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 64,
17
+ "num_hidden_layers": 140,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": 131072,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "float16",
24
+ "transformers_version": "4.41.2",
25
+ "use_cache": true,
26
+ "use_sliding_window": false,
27
+ "vocab_size": 152064
28
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ dtype: float16
2
+ merge_method: passthrough
3
+ slices:
4
+ - sources:
5
+ - layer_range:
6
+ - 0
7
+ - 20
8
+ model: Qwen/Qwen2-72B-Instruct
9
+ - sources:
10
+ - layer_range:
11
+ - 10
12
+ - 30
13
+ model: Qwen/Qwen2-72B-Instruct
14
+ - sources:
15
+ - layer_range:
16
+ - 20
17
+ - 40
18
+ model: Qwen/Qwen2-72B-Instruct
19
+ - sources:
20
+ - layer_range:
21
+ - 30
22
+ - 50
23
+ model: Qwen/Qwen2-72B-Instruct
24
+ - sources:
25
+ - layer_range:
26
+ - 40
27
+ - 60
28
+ model: Qwen/Qwen2-72B-Instruct
29
+ - sources:
30
+ - layer_range:
31
+ - 50
32
+ - 70
33
+ model: Qwen/Qwen2-72B-Instruct
34
+ - sources:
35
+ - layer_range:
36
+ - 60
37
+ - 80
38
+ model: Qwen/Qwen2-72B-Instruct
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3160d40855c9f3cb7e2876ebed85843d704076bc04d3f522da44d81a30aca6f6
3
+ size 1270895632
model-00002-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10ea747718731605ab6e84cfd992ed1ba7ddf9f67840a4d63f0a75c1f2d16142
3
+ size 2491416712
model-00003-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4824d62baadbe74b9e86fafd9900b2f9e1ccb7a534c04c625dc6749995bd29f
3
+ size 1906384672
model-00004-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2790d5e3df8db207bf3dabc7f9c7bdb306719b709c79fb3a4d17c4c4bef62cd1
3
+ size 1604373520
model-00005-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f303f7e83c4fe19badf1992b079d9427aaa82a4b332e62c8680696f5281bfc19
3
+ size 1572939776
model-00006-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2820faec910ff80942faf04e133f528d31edfdb2b363df2022baa846bc6f495b
3
+ size 1755370848
model-00007-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be5a48645d799b1d299ed9a7a81f8a7f167d368f415db3c4c46051e2c9b2d4d6
3
+ size 1906368176
model-00008-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eb4e4de056c16e64e60dc59ce9a5d0b77ad6080d0bc470f11bd8c5342e214ca
3
+ size 1604373520
model-00009-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c116f92a44b22563045ce41eaa80c3982c59683b122192820825785eedc66550
3
+ size 1755354352
model-00010-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bed04cee357c070bba6e98d59571424892ccaa5e4293912935af191c3e388fd
3
+ size 1755354352
model-00011-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:062f559649a36fb6ad77df3c9e52e90f7bfe04f0d724e9cdb89d4a1da6be2536
3
+ size 1971377376
model-00012-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b76317d48073dfb2428ed4292bcdb5f732c754d8bd7b3a1b80caf88cf020afa
3
+ size 1539380832
model-00013-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1ccb63a8dab5676f9fbbc08f7ee9a0cd23fc8fd0becf43da2eaf2125eb63c4f
3
+ size 1971360888
model-00014-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5ceba322c5e84fd549e7d5d9c0f44fa4c4570440db4dff326591c1615ed2708
3
+ size 1539380832
model-00015-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc300f5d0068c75f59737d7ca82be53703f11136c65ae5f114ea2eca016fe839
3
+ size 1937818416
model-00016-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab28b32db87ddf93fd02b71afcf0f515a05e25487f18a9b4762c5f7d04b97386
3
+ size 1692536360
model-00017-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86d2202d609232b542b291a9651a2a05d7cce4cd29d905c3de9147fd81911266
3
+ size 1937768936
model-00018-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50857c1bd800f6399db1d16543bd7b9c2977d682caa2d59596ffa60e7f2269ce
3
+ size 1572972768
model-00019-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3b6e38de7433855d9d2282a3d211f3734806e7d88156d8687cede20031deb4c
3
+ size 1937768936
model-00020-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da6abf6fb207599a83e9426cd8dd5238803273bbcda2c1a451dff5cb7b39994f
3
+ size 1572939784
model-00021-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d24c02020383f5480d9b9b61c702646a153101e7fbdbe64cd66cfa780f40fa32
3
+ size 1572939784
model-00022-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b61d479a8eeb9eaed48d49b2b25fa5b9c7f9f403f43d8e20b2ad93958eb359e
3
+ size 1937768936
model-00023-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:721bbf89f0130b34ae8b5881cdf0e04d4fdb7c1d7c02cf1d82aaa57f02f02b3d
3
+ size 1937834928
model-00024-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d7a2938d87faa166d2a319554f9e696dce569fc607ad9c638153ebac157f95a
3
+ size 1971360896
model-00025-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44a34f8cf7cb53970647cea07beea4900ed88e99ade17ad1823fbf3a6761ea93
3
+ size 1539347824
model-00026-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73caa28d9ec1379c628e5b986438768ddd53415e7588f0c4d7fad902f26c9af5
3
+ size 1572939784
model-00027-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:167be5ec42638e72b532033c879da8c549b479b4b1df0715a6837b4c42baec8b
3
+ size 1937768936
model-00028-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4695adba64731f96c51cf2b24f572a59cbf8eefa18f9f154ca6e3a3439846b06
3
+ size 1937834928
model-00029-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0249cd2e9a9d7884e643fb0ca5944cc71bc42303e282df94020d5680a0e632a
3
+ size 1572972800
model-00030-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:907b4117a550f38203cfb246888f1268f8160e72c72945ebf9371738efcb5a1c
3
+ size 1937768936
model-00031-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aba999760d34ad18f7e45353b6a61f1791078518f387d853850265bb3a83d4bd
3
+ size 1572972768
model-00032-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d51732a99e013d5ca1ab1f84f98b8b3989bc816d647ba186a4a7926958ed3d6
3
+ size 1937768936
model-00033-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc21a43ccd60998026fcc7c2b5104f26de3c949aace688b9726ff8190bf2375d
3
+ size 1971426896
model-00034-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af52e216a48d77dd942c30a095d64cb90421fa8082a270ad774f5c8ab64fbada
3
+ size 1658960904
model-00035-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31b88f0714e65875b6585837dc5f8f0da55cac6dcd2783affc07b4f1aab10663
3
+ size 1937768936
model-00036-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eedc437d5e351130d85404240fddc61bce53f3e5b53a2e5fffb78f74af4acd9
3
+ size 1572972776
model-00037-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f368551b5db2ad2f1462609d651665036dcc4bb6921dab856cd136e6dfa0cb9
3
+ size 1937768936
model-00038-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7643938696e780500dd19e81718b3cae2fca106709afa5b4055c2b380ba7770d
3
+ size 1572939784
model-00039-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:612c71c7a459e5d4d9825fe2b48bbc7a0004a207364e5f22beaa91d865f65f7f
3
+ size 1572939792
model-00040-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95525b30fecc40d3edde87b8f87f8b70dd49849d423668bf2fc78aaa2f62377f
3
+ size 1937768936
model-00041-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:479d4195fed10f4dc0ee6eb8b7dc89d80c609fbb2cc5d23a0eca14d8e8879805
3
+ size 1937834928
model-00042-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0572c9a1f6110f8fbe992b74694f5ac770373c32740e6b807ad9e9f0de7abb3b
3
+ size 1889605192
model-00043-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:652a58c2c095d01fb2cb6f2e2a228677baa7b94eee030097fb0bae8073477f47
3
+ size 1621103528
model-00044-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:752589c870c53242a4f5a8171bd5d0cfb1f4cd7fce12beabda6942090f076da0
3
+ size 1572939792
model-00045-of-00140.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbd4eaec46e30f029ca4dfd24a0194d7c3c86cc674d9027841887eb05af04e86
3
+ size 1937768936