Hugging Face's logo

mlabonne
/
BigQwen2.5-125B-Instruct

Text Generation
Transformers
Safetensors
English
qwen2
mergekit
Merge
lazymergekit
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
mlabonne commited on
Commit
ef797d7
•
1 Parent(s): e030152

Add files using upload-large-folder tool

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 +54 -0
  2. added_tokens.json +24 -0
  3. config.json +28 -0
  4. mergekit_config.yml +24 -0
  5. merges.txt +0 -0
  6. model-00001-of-00052.safetensors +3 -0
  7. model-00002-of-00052.safetensors +3 -0
  8. model-00003-of-00052.safetensors +3 -0
  9. model-00004-of-00052.safetensors +3 -0
  10. model-00005-of-00052.safetensors +3 -0
  11. model-00006-of-00052.safetensors +3 -0
  12. model-00007-of-00052.safetensors +3 -0
  13. model-00008-of-00052.safetensors +3 -0
  14. model-00009-of-00052.safetensors +3 -0
  15. model-00010-of-00052.safetensors +3 -0
  16. model-00011-of-00052.safetensors +3 -0
  17. model-00012-of-00052.safetensors +3 -0
  18. model-00013-of-00052.safetensors +3 -0
  19. model-00014-of-00052.safetensors +3 -0
  20. model-00015-of-00052.safetensors +3 -0
  21. model-00016-of-00052.safetensors +3 -0
  22. model-00017-of-00052.safetensors +3 -0
  23. model-00018-of-00052.safetensors +3 -0
  24. model-00019-of-00052.safetensors +3 -0
  25. model-00020-of-00052.safetensors +3 -0
  26. model-00021-of-00052.safetensors +3 -0
  27. model-00022-of-00052.safetensors +3 -0
  28. model-00023-of-00052.safetensors +3 -0
  29. model-00024-of-00052.safetensors +3 -0
  30. model-00025-of-00052.safetensors +3 -0
  31. model-00026-of-00052.safetensors +3 -0
  32. model-00027-of-00052.safetensors +3 -0
  33. model-00028-of-00052.safetensors +3 -0
  34. model-00029-of-00052.safetensors +3 -0
  35. model-00030-of-00052.safetensors +3 -0
  36. model-00031-of-00052.safetensors +3 -0
  37. model-00032-of-00052.safetensors +3 -0
  38. model-00033-of-00052.safetensors +3 -0
  39. model-00034-of-00052.safetensors +3 -0
  40. model-00035-of-00052.safetensors +3 -0
  41. model-00036-of-00052.safetensors +3 -0
  42. model-00037-of-00052.safetensors +3 -0
  43. model-00038-of-00052.safetensors +3 -0
  44. model-00039-of-00052.safetensors +3 -0
  45. model-00040-of-00052.safetensors +3 -0
  46. model-00041-of-00052.safetensors +3 -0
  47. model-00042-of-00052.safetensors +3 -0
  48. model-00043-of-00052.safetensors +3 -0
  49. model-00044-of-00052.safetensors +3 -0
  50. model-00045-of-00052.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - Qwen/Qwen2.5-72B-Instruct
4
+ library_name: transformers
5
+ tags:
6
+ - mergekit
7
+ - merge
8
+
9
+ ---
10
+ # merge
11
+
12
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
13
+
14
+ ## Merge Details
15
+ ### Merge Method
16
+
17
+ This model was merged using the passthrough merge method.
18
+
19
+ ### Models Merged
20
+
21
+ The following models were included in the merge:
22
+ * [Qwen/Qwen2.5-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct)
23
+
24
+ ### Configuration
25
+
26
+ The following YAML configuration was used to produce this model:
27
+
28
+ ```yaml
29
+ slices:
30
+ - sources:
31
+ - layer_range: [0, 20]
32
+ model: Qwen/Qwen2.5-72B-Instruct
33
+ - sources:
34
+ - layer_range: [10, 30]
35
+ model: Qwen/Qwen2.5-72B-Instruct
36
+ - sources:
37
+ - layer_range: [20, 40]
38
+ model: Qwen/Qwen2.5-72B-Instruct
39
+ - sources:
40
+ - layer_range: [30, 50]
41
+ model: Qwen/Qwen2.5-72B-Instruct
42
+ - sources:
43
+ - layer_range: [40, 60]
44
+ model: Qwen/Qwen2.5-72B-Instruct
45
+ - sources:
46
+ - layer_range: [50, 70]
47
+ model: Qwen/Qwen2.5-72B-Instruct
48
+ - sources:
49
+ - layer_range: [60, 80]
50
+ model: Qwen/Qwen2.5-72B-Instruct
51
+ merge_method: passthrough
52
+ dtype: bfloat16
53
+
54
+ ```
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen2.5-72B-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": 70,
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": null,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.44.2",
25
+ "use_cache": true,
26
+ "use_sliding_window": false,
27
+ "vocab_size": 152064
28
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ slices:
2
+ - sources:
3
+ - layer_range: [0, 20]
4
+ model: Qwen/Qwen2.5-72B-Instruct
5
+ - sources:
6
+ - layer_range: [10, 30]
7
+ model: Qwen/Qwen2.5-72B-Instruct
8
+ - sources:
9
+ - layer_range: [20, 40]
10
+ model: Qwen/Qwen2.5-72B-Instruct
11
+ - sources:
12
+ - layer_range: [30, 50]
13
+ model: Qwen/Qwen2.5-72B-Instruct
14
+ - sources:
15
+ - layer_range: [40, 60]
16
+ model: Qwen/Qwen2.5-72B-Instruct
17
+ - sources:
18
+ - layer_range: [50, 70]
19
+ model: Qwen/Qwen2.5-72B-Instruct
20
+ - sources:
21
+ - layer_range: [60, 80]
22
+ model: Qwen/Qwen2.5-72B-Instruct
23
+ merge_method: passthrough
24
+ dtype: bfloat16
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc1ed63ebe657c49642539e13528c031be9100da852238c80882c32fcef676b5
3
+ size 4982849880
model-00002-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64bc1a93221503b7fe23d67d1de69dbe4160b96ed7482f33ed0442d1c9273a35
3
+ size 4964084896
model-00003-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:824641ee5049d686fdbcb16acb9989151f509d3198900aa618eee1b95fedd02c
3
+ size 4997660416
model-00004-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cffeffa8614e0df25096fdf66682320d379c996f5d8fa23caf5404493104130
3
+ size 4565680312
model-00005-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef3355c1d34af993ea5b0a2daa0d0286e7d266d3f1ef15aaebfe0fd1470bcf9a
3
+ size 4964068424
model-00006-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a4606c7271224a825ea7cd32b136eabf09c441599514c74821aa83c03d9cdb6
3
+ size 4915904704
model-00007-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2dfafbac39c91e40970c83989d5849e21ee4a834bbcbda2702da3e6d18386b9
3
+ size 4647436016
model-00008-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:809a81f5af3ea6c4700f0cf205c679608fad76cc191586214d8b5582f615814e
3
+ size 4964068416
model-00009-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9d54d8ac5d530dddf4a2dfed95ff7ba6334db58dea4e218fffed19f88bee097
3
+ size 4599255800
model-00010-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c048e959d12be23ca5e66364033464a5128bc9323bd9ea6e8a66611b1a09ab75
3
+ size 4964101416
model-00011-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31c42973e9613f9827b0c06ec49b406313db91e28caf776a42e40baaf1bbaf49
3
+ size 4781653864
model-00012-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc33babef837a4b8095e8650eb5ddb958129d49a614e24d9d5c2275b7ce3c703
3
+ size 4964068416
model-00013-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d4d6aa91ff84cfa53a3f0a5ce6f0f6d5eba5c445324d6cc70142ee01bac59c9
3
+ size 4599272304
model-00014-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a587d69890a124416d2cf2820b31e049e7a6f30005b109b7e108abea78317751
3
+ size 4964068424
model-00015-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:882d0d3a1df48e1f71b3b79b63909ab934e6c0e33d80bddcde38d631b9cd0769
3
+ size 4997660416
model-00016-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6138b6bdc21e09a78be6e4adab3e6c9392ccddad72bce2bfa88f59fe3b1435f5
3
+ size 4565680312
model-00017-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:befb341cdfbbbbaf765bf5ed58bfb14ea0cab076259a7930f910c5cc5d78dfef
3
+ size 4781670352
model-00018-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be0877ee93d72a0a683e4b142d0fdcfb83b1f9f0bf1863ba8c9751a3a147ef4c
3
+ size 4964068424
model-00019-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97de4b995476bab76859e0d0581c4c8d0857971b6f977f59588f83e92e6926ec
3
+ size 4997660416
model-00020-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ff34a1d83abd39cba7e26823230500a775932a497dd3d3774c562a2266eb4a7
3
+ size 4565680312
model-00021-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f100c8e23139a09ea1df85d74834a6a5a3400c4f15eca552e5c22e4a45f8cd29
3
+ size 4964068424
model-00022-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4ff6ee710b3c0fcc0063b35f76336e7d92bc1476cd3622be89ed5f5fced8bcb
3
+ size 4915904704
model-00023-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5149690ff245672efed459708c955d5d277403558829d86e43ca490f62b23150
3
+ size 4647436016
model-00024-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87afdc3aee7198b21f511d22f6e737b32f2a8eaf1bbad1465eadc3f84f403d57
3
+ size 4964068416
model-00025-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7452d75ff98d904c659b5291ccaa87866ffef995105cfb212a40cc1e30486fb
3
+ size 4781670352
model-00026-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3399900982ccca94a39bbaba3ced5e18c34ac39ff95dff45cecd5ee0248e5652
3
+ size 4915904704
model-00027-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a90c5288e38c2fb7c42a1fa188a401d72786e9696a6850c19e620f8fb9bd220
3
+ size 4647436016
model-00028-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a06df65cc8c1c30778c854fc4578104b59a023c7cc33ee7a3d4ea1169718807
3
+ size 4964068416
model-00029-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17df73a09b2c1b45ff2b321626033806d351c7425ca6db0c1ea2b37151a6245b
3
+ size 4599272304
model-00030-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29eda1db9e58a76ca277a02c40450e5441087715239c0bbb15c1e1b5ee07c5a3
3
+ size 4964068424
model-00031-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ee46fe8c4eeae108f6bb1e5833e68307b9714faa145bbd693fd5c2daebe9744
3
+ size 4997660416
model-00032-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2272de4b813e4dc9a4b0fe1dbc18ce43879a313dc6704a9dfeefcaa90ab3ac27
3
+ size 4565663808
model-00033-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38b26ad69323a21bf0480bd6a113865c83f0ca962abf1094195d729e1dfaf756
3
+ size 4781686856
model-00034-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77e8e46c0a8f320f34a0a6cb6fedaa10c3d20e1666aad662593f1a4cab4b8081
3
+ size 4964068440
model-00035-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2b034e7df201ad83ff0cfb57536a6718a8e06048601219d361a67919551622e
3
+ size 4997660416
model-00036-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:646a4efba2901add13934f555d0674bfa9d2da439d0ec381c4d94d2cfdf73728
3
+ size 4565680328
model-00037-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ba34a36e43714d979f12ddb179f173e77cadd2e4c385f4146f97b098b282f3d
3
+ size 4964068432
model-00038-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38fc6e4e2a84862eae66e7c5fa3d50b9d8920a67bc1dbd347e8f0161f65dc303
3
+ size 4915904720
model-00039-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4e96bd281c262d510da2a74823a5039b6729d09d1c85e4781c82c75799dfd0f
3
+ size 4647436016
model-00040-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d90c2f997da224c9c3590319df5aba14533c5f25e36b8f6852691b506cd09ed2
3
+ size 4781670368
model-00041-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:460a7babeb0f1a0368204a37241393b5d33931739c735b86ee8210fd7597e4f6
3
+ size 4964068456
model-00042-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ee13bbece4977cb49c2fbde2e6e30349b8b4975f5949c2950ec46d1e5de0b2f
3
+ size 4915904736
model-00043-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b59bfb904a1746ac0136dd1a9592e5536a83c1ba210dd85f21719cdccf4ab8c5
3
+ size 4647436048
model-00044-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df45eefa10cf545ec5bd750cd318d7fd8cc4f1e576da3cf342f231239203ee70
3
+ size 4964068448
model-00045-of-00052.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20dbd9cb338667432cb8f01505007730a7e2ff033da62dff5fc6276a154cad91
3
+ size 4599272344