Hugging Face's logo

allknowingroger
/
Llama-3.1-Nemotron-70B-Instruct-HF-F32

Text Generation
Transformers
Safetensors
llama
mergekit
Merge
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
allknowingroger commited on
Commit
a74c9d2
·
verified ·
1 Parent(s): 26e4013

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. README.md +38 -0
  3. config.json +40 -0
  4. mergekit_config.yml +8 -0
  5. model-00001-of-00062.safetensors +3 -0
  6. model-00002-of-00062.safetensors +3 -0
  7. model-00003-of-00062.safetensors +3 -0
  8. model-00004-of-00062.safetensors +3 -0
  9. model-00005-of-00062.safetensors +3 -0
  10. model-00006-of-00062.safetensors +3 -0
  11. model-00007-of-00062.safetensors +3 -0
  12. model-00008-of-00062.safetensors +3 -0
  13. model-00009-of-00062.safetensors +3 -0
  14. model-00010-of-00062.safetensors +3 -0
  15. model-00011-of-00062.safetensors +3 -0
  16. model-00012-of-00062.safetensors +3 -0
  17. model-00013-of-00062.safetensors +3 -0
  18. model-00014-of-00062.safetensors +3 -0
  19. model-00015-of-00062.safetensors +3 -0
  20. model-00016-of-00062.safetensors +3 -0
  21. model-00017-of-00062.safetensors +3 -0
  22. model-00018-of-00062.safetensors +3 -0
  23. model-00019-of-00062.safetensors +3 -0
  24. model-00020-of-00062.safetensors +3 -0
  25. model-00021-of-00062.safetensors +3 -0
  26. model-00022-of-00062.safetensors +3 -0
  27. model-00023-of-00062.safetensors +3 -0
  28. model-00024-of-00062.safetensors +3 -0
  29. model-00025-of-00062.safetensors +3 -0
  30. model-00026-of-00062.safetensors +3 -0
  31. model-00027-of-00062.safetensors +3 -0
  32. model-00028-of-00062.safetensors +3 -0
  33. model-00029-of-00062.safetensors +3 -0
  34. model-00030-of-00062.safetensors +3 -0
  35. model-00031-of-00062.safetensors +3 -0
  36. model-00032-of-00062.safetensors +3 -0
  37. model-00033-of-00062.safetensors +3 -0
  38. model-00034-of-00062.safetensors +3 -0
  39. model-00035-of-00062.safetensors +3 -0
  40. model-00036-of-00062.safetensors +3 -0
  41. model-00037-of-00062.safetensors +3 -0
  42. model-00038-of-00062.safetensors +3 -0
  43. model-00039-of-00062.safetensors +3 -0
  44. model-00040-of-00062.safetensors +3 -0
  45. model-00041-of-00062.safetensors +3 -0
  46. model-00042-of-00062.safetensors +3 -0
  47. model-00043-of-00062.safetensors +3 -0
  48. model-00044-of-00062.safetensors +3 -0
  49. model-00045-of-00062.safetensors +3 -0
  50. model-00046-of-00062.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
README.md ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
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 SLERP merge method.
18
+
19
+ ### Models Merged
20
+
21
+ The following models were included in the merge:
22
+ * [nvidia/Llama-3.1-Nemotron-70B-Instruct-HF](https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF)
23
+
24
+ ### Configuration
25
+
26
+ The following YAML configuration was used to produce this model:
27
+
28
+ ```yaml
29
+ models:
30
+ - model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
31
+ - model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
32
+ merge_method: slerp
33
+ base_model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
34
+ dtype: float32
35
+ parameters:
36
+ t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers
37
+
38
+ ```
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
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
+ "head_dim": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 8192,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 28672,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 64,
23
+ "num_hidden_layers": 80,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 8.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.45.1",
38
+ "use_cache": true,
39
+ "vocab_size": 128256
40
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ models:
2
+ - model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
3
+ - model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
4
+ merge_method: slerp
5
+ base_model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
6
+ dtype: float32
7
+ parameters:
8
+ t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers
model-00001-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c586551e617c8ae63f7e4a5703b7c87525ea0d768e2728f0d52840285f5b255f
3
+ size 4202692736
model-00002-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea3697e671e4580084a0ef8a5f42a6c0521619bdeda135d9312f2c9d806a7913
3
+ size 4202725624
model-00003-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f993698a6481e0fa28a5ef519667b623155eebceb064c754b95003986ed00203
3
+ size 4362142872
model-00004-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8419fffa1b566080e107e8262ea405324b3872e16815734a38a11e15857a638
3
+ size 4362142880
model-00005-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a7b1f1978b249a8a83b7ad5ed3dcae96e554faed02b8d40844038be9e4ac137
3
+ size 4966188888
model-00006-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3951cae83b7f23aa7083930e002a965cde0f73e667b23b5f6de186001e51e852
3
+ size 4362142888
model-00007-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e338466927e5685b8681a69e042495efce8b516bc60deeb3dfa948f5ad00ae3d
3
+ size 4362142888
model-00008-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:114349879d5d3c144846000dc9d8d2d409fc5bd9f71c11e7078873966eb938d2
3
+ size 4966188888
model-00009-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e09c0d14648b95eaa4170c4b424c4d604bda0cd4070dd7c374a19f40560f163
3
+ size 4362142888
model-00010-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b326d74ced39db5698da962cfa494015d4d005f14c17d7fd8299c34e8c44d41
3
+ size 4362142888
model-00011-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af78c2bcda60f0398145e72e2cee2cf3a385b7f9d0c2f20c7c81ecec34d65e91
3
+ size 4966188888
model-00012-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8b888556ab9ec0753cf34fcbcd9ca3b84bf5dc6973e5dbdaa46854c97ea21c2
3
+ size 4362142880
model-00013-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d5d59df942d0093172491831c195e14d0c9bf90b58bcdae1fc8a7af59e3f1b7
3
+ size 4362142888
model-00014-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:010699335db697affc6b1e82b18b765fc2db17bc219e020af1e11212655667d2
3
+ size 4966188888
model-00015-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbe399dd52de591c39a559d6225f4b3dc57325fc352deb7559d28fd207a56bdd
3
+ size 4362142888
model-00016-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fee2f7823a4b2d6b3184cddc3cd5a4ae00325661c8e4f95b7dc665d6ea6a665
3
+ size 4362142888
model-00017-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b75ae983b3a22f09ee7eed7953886d2631db3b20e4bb7baa21bd6906428b6e3
3
+ size 4966188888
model-00018-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ea1fc6e8fbfaae8fc8f82b530d7baf6b1ccac77991790859d0acfaea327c4bb
3
+ size 4362142888
model-00019-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01ae280ac51dba1ceec848e75d4cb1236d9d006536ea3c3296f408b80119a841
3
+ size 4362142888
model-00020-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8856745f666f77a378e9cd2bc38fad02871dd2fa2cd2247e7b937cd9f81b778
3
+ size 4966188880
model-00021-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bab843c21d5b63f30264356bb7745ec4e74324096e5739291c3c7b8c0e2c9c94
3
+ size 4362142888
model-00022-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcabf19ed395aeb0508a8726cedad0e51375d0d7bb07b6dc0ae9bb699f4f33c2
3
+ size 4362142888
model-00023-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96757a399d181ee7892fd6132bae7995c822d791f3833af1b5686fd5c1383e98
3
+ size 4966188888
model-00024-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e53f80d7a206542b8a95a75a0fad12dae802339bc2439eb01465b2c88a304d8d
3
+ size 4362142888
model-00025-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c007f51758dc9f9bf34c02e1f0e0b3297f9af4d5bad4af3ff5e4770e08ba1f1
3
+ size 4362142888
model-00026-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90b41c6ec17e03a44259b2c5fdb0fa73fe921ce6fe18b29d320a8d16dfa47960
3
+ size 4966188888
model-00027-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be91f27da9a9a00033592afd98c842e1029f77220ef9e976b41207526ec8ebdc
3
+ size 4362142888
model-00028-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:141ae9d8d2c97fdcf62251439619bbdefa1aef403f25faef756e979d42ed8077
3
+ size 4362142880
model-00029-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e983f7885c1621c48c9af6b5a8273e983c2027fd43151a2cd51d5edfdd3d8e0
3
+ size 4966188888
model-00030-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73860114fee2f3cf4ea1285f05975516b118139b94cba0b573994b06b5c3c975
3
+ size 4362142888
model-00031-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c92c0b72e34df12eb64d5914e5e2d61812975935973a1e9ead258fff4010dd27
3
+ size 4362142888
model-00032-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aafeaed4da6bb82883b2c81b3ac84753adca9dce7fbbeac99316e2ee7815014
3
+ size 4966188888
model-00033-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5d132390a5446a97737014366b637e36bd5a1f84fb4bce795de4d52c6009f61
3
+ size 4362142888
model-00034-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa2612d2bd871a1e854dafcb9c4d4afd62c402e81e2d022dd01beafaec8364f9
3
+ size 4362142888
model-00035-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0f8743f1eaa3a8ec43bc531c51939a0952458a4a69ca62892e9907feb8aa99c
3
+ size 4966188888
model-00036-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46a1b9e5ecc8194ab1c464bdc600a9b354db952794c057b29eb29a9408553241
3
+ size 4362142880
model-00037-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fee59d0a4e0da7c93363af17f4fab6a1282ae51719734405d0abdd6a76690e16
3
+ size 4362142880
model-00038-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ceb1cf95f946e4876734b6d948714450425a1e2df54bfc16bea8a51f9e349ce
3
+ size 4966188888
model-00039-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b06808d882d3976b4d9c1e647209fe4cd6d311a45f42bf67936260cecd153257
3
+ size 4362142888
model-00040-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f6465e41c94cf6cbd449ee7fa1e9b0b5ec3587e5a2bdf0fafc1d6fccf6906cc
3
+ size 4362142888
model-00041-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8040bb720aaedd64596ad4296fef2d35de3c92acbdee99be6f165a6f00e677fd
3
+ size 4966188888
model-00042-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48c381605535c584416c45adb808163fa51bcd993008fe7a4e325dfa2989f81f
3
+ size 4362142888
model-00043-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f81d97f526d5626f8038a9dc5e4dc0db16b7667d1ff72e77c08d5eb71429c592
3
+ size 4362142888
model-00044-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b87e849fc35b91ca37b2f165c20bc288b54549c45b7bfe02e73fe651c64a8979
3
+ size 4966188888
model-00045-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:746390a51cb67e6d991cb2f89a16a262772fd7e4a290d6227a52b468b4860988
3
+ size 4362142880
model-00046-of-00062.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4fb64bf5f2bd3322d3add391fd30e964e47fc52378e675d8ead105f35c6cc19
3
+ size 4362142888