Hugging Face's logo

typeof
/
Hermes-2-Pro-Llama-3-8B-exploded

Text Generation
Transformers
Safetensors
English
llama
Llama-3
instruct
finetune
chatml
DPO
RLHF
gpt4
synthetic data
distillation
function calling
json mode
axolotl
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
typeof commited on
Commit
7158c1c
•
1 Parent(s): a581136

init

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. config.json +28 -0
  2. dpo-adapter/adapter_config.json +37 -0
  3. generation_config.json +7 -0
  4. model-00002-of-00291.safetensors +3 -0
  5. model-00003-of-00291.safetensors +3 -0
  6. model-00004-of-00291.safetensors +3 -0
  7. model-00005-of-00291.safetensors +3 -0
  8. model-00006-of-00291.safetensors +3 -0
  9. model-00007-of-00291.safetensors +3 -0
  10. model-00008-of-00291.safetensors +3 -0
  11. model-00009-of-00291.safetensors +3 -0
  12. model-00010-of-00291.safetensors +3 -0
  13. model-00011-of-00291.safetensors +3 -0
  14. model-00012-of-00291.safetensors +3 -0
  15. model-00013-of-00291.safetensors +3 -0
  16. model-00014-of-00291.safetensors +3 -0
  17. model-00015-of-00291.safetensors +3 -0
  18. model-00016-of-00291.safetensors +3 -0
  19. model-00017-of-00291.safetensors +3 -0
  20. model-00018-of-00291.safetensors +3 -0
  21. model-00019-of-00291.safetensors +3 -0
  22. model-00020-of-00291.safetensors +3 -0
  23. model-00021-of-00291.safetensors +3 -0
  24. model-00022-of-00291.safetensors +3 -0
  25. model-00023-of-00291.safetensors +3 -0
  26. model-00024-of-00291.safetensors +3 -0
  27. model-00025-of-00291.safetensors +3 -0
  28. model-00026-of-00291.safetensors +3 -0
  29. model-00027-of-00291.safetensors +3 -0
  30. model-00028-of-00291.safetensors +3 -0
  31. model-00029-of-00291.safetensors +3 -0
  32. model-00030-of-00291.safetensors +3 -0
  33. model-00031-of-00291.safetensors +3 -0
  34. model-00032-of-00291.safetensors +3 -0
  35. model-00033-of-00291.safetensors +3 -0
  36. model-00034-of-00291.safetensors +3 -0
  37. model-00035-of-00291.safetensors +3 -0
  38. model-00036-of-00291.safetensors +3 -0
  39. model-00037-of-00291.safetensors +3 -0
  40. model-00038-of-00291.safetensors +3 -0
  41. model-00039-of-00291.safetensors +3 -0
  42. model-00040-of-00291.safetensors +3 -0
  43. model-00041-of-00291.safetensors +3 -0
  44. model-00042-of-00291.safetensors +3 -0
  45. model-00043-of-00291.safetensors +3 -0
  46. model-00044-of-00291.safetensors +3 -0
  47. model-00045-of-00291.safetensors +3 -0
  48. model-00046-of-00291.safetensors +3 -0
  49. model-00047-of-00291.safetensors +3 -0
  50. model-00048-of-00291.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./hermes-2-pro-llama-3-8b-DPO",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128003,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 500000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float16",
25
+ "transformers_version": "4.40.1",
26
+ "use_cache": true,
27
+ "vocab_size": 128288
28
+ }
dpo-adapter/adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/workspace/axolotl/hermes-2-pro-llama-3-8b-dpo-split-2",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": [
18
+ "embed_tokens",
19
+ "lm_head"
20
+ ],
21
+ "peft_type": "LORA",
22
+ "r": 32,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "v_proj",
27
+ "up_proj",
28
+ "o_proj",
29
+ "k_proj",
30
+ "gate_proj",
31
+ "q_proj",
32
+ "down_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128003,
6
+ "transformers_version": "4.40.1"
7
+ }
model-00002-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24552d1e6d6052ead2c070190507fb9d48ec508d0dedc3823a4364f7b78bbac0
3
+ size 1050935440
model-00003-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:846ca1ce27d38aff82568ace21f4fe9896b8ce0280ed184f116c4b7fb02615d6
3
+ size 8328
model-00004-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78af5e278ece63631e0fd51e842e873c2e67ecc0760d5f1c29145c17424b0b4f
3
+ size 117440664
model-00005-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:467aad1f458b395e4a80e3906c7ac9f4c92021228210f2e3fd3976c19365b300
3
+ size 117440664
model-00006-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bf7cae68e59b6b4e50a924c0080fb7e9cc64a33274c2aebb9dfe2adc4601ef8
3
+ size 117440656
model-00007-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c962f39377822f59e0dd13e386fe8c1ebf677d0b8c9232ed16345670582a3847
3
+ size 8344
model-00008-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a6d8645191188f21a6ca664d20dac70884642ab5f91ced665d4140a2a01dd73
3
+ size 8388760
model-00009-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20f2d8bfc782b9e171c64d62b464c407b5ec8e195a7298865cc54ee882abc713
3
+ size 33554584
model-00010-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a97689d83877b08f7de787f800779db799377bfd9b4ddf5bc506435c3605879
3
+ size 33554584
model-00011-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07c922a158c2ef774a6be06b38db5282f4400e5865c84451a34b2edb5cbcee93
3
+ size 8388760
model-00012-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8983028bc1ad6c1dab49535d874e24cc320cba2460110e30fb531b09e2fc0f08
3
+ size 8328
model-00013-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04e46088235994852e13caf9158c8517c7c553090c14ed696caffac044dc769b
3
+ size 117440664
model-00014-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa8130ab75fb8a04cc80aaa4c028e516b2be024b5176539b384a4860d13d94ab
3
+ size 117440664
model-00015-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0475145714ae8c747d76ddc349a416811e4ed1f93ecb1152f568e3ecd270c704
3
+ size 117440656
model-00016-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e39832d18c9e16c0ad04798f38100874628d3589c3aadd179ea66240ed3466aa
3
+ size 8344
model-00017-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fbb0fd3816122198136749aba5b4e133a4549ffe48f836bda11be5096552646
3
+ size 8388760
model-00018-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41061ea464cbe84ecc20effc1ac388cee57888fb4fd4af297f693325bd3e1c37
3
+ size 33554584
model-00019-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ae025687ca74c331cc5c67006c0fcba6ca858f3180cf439422b8c8b74a2e48d
3
+ size 33554584
model-00020-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79753bc658d351b69c11ac657d0feb29edd59b942414a896f4b8befcb3d2ea41
3
+ size 8388760
model-00021-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:145266d5b6af1a5cbb502bfd7ff7c167960a088dcf05787eddfe89af3ca2fd32
3
+ size 8328
model-00022-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79817449923dfede8afef28211abe854f6c5de18a3f7388a82431941b686ee87
3
+ size 117440664
model-00023-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7838fa5112156244eba5f5d44f8bf2c76396857c4f23fc213c31cb31495d5e6
3
+ size 117440664
model-00024-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7a47c30373f159fa6c745f5641a1be5921697b3fb10c4809ddfb99f61b02b35
3
+ size 117440656
model-00025-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b219f83795a10ed825ab18a607ee442b2ffc1b42bbec0def50b1487550ead037
3
+ size 8344
model-00026-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4373ae351de6eb043da589457ca52a0e0facd3d3221d2624bbfe11335d616856
3
+ size 8388760
model-00027-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a65e567f2634ad308e6f6f520e7c7101ad98ed03f095acecba7ac44f10b04c0
3
+ size 33554584
model-00028-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f411737043de5ce3052797e900e86047a13a4f804701abf74e1898b36dac1bdd
3
+ size 33554584
model-00029-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28e5f14788cb93b81a5a01377895f9ff21d10cb9bdb022338643e18d6ec3d3e1
3
+ size 8388760
model-00030-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c59eebe6bbdf99ad5cd1ac7f5a3e7fb50007d81be9d98b691ba9f370705117c7
3
+ size 8328
model-00031-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:778a511c311f11d35c263a0fb20ce8e797a202257290d737b1e92105b483e7df
3
+ size 117440664
model-00032-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b5c14a6ea6d7ca004b0e3ccafb389367869671dce4cde5c431ca899fc6fd32b
3
+ size 117440664
model-00033-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bdfb259143e05797d22e2e2d9639d897b1204661303e93a3657ebbda71b7ab5
3
+ size 117440656
model-00034-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edf13cd86249045a162ef2159372ec8ac54dca9ca5e3607001781f687d4bd971
3
+ size 8344
model-00035-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8344f93f075e94fdae7d4c0b06333336d0ee940599aae80ac85a67b2e42fa29
3
+ size 8388760
model-00036-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8f6b2911c3c3029ee2403fc7b223fe6bc8cb3d587bdb96f21d08c24c771ea43
3
+ size 33554584
model-00037-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45292fade1cb7acc51ac5feb0271db645104b5dacb6cdd9624c26534974afd79
3
+ size 33554584
model-00038-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9cb0ff7e383d75cd1575131f4712535bdcf4d0e12cb51664db27c2fe1948113
3
+ size 8388760
model-00039-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dda2944f210c72003ffa5eb5e88c5feef641182c94601434d357afbf2a12e5f
3
+ size 8328
model-00040-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3957c5f871f3b3c02e0430bcd4a81a0485fd1120544d61b93223da272d5ace69
3
+ size 117440664
model-00041-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5113b79de71d90e87c4972dee99ea1a556370729673825db0000d2f5b25c187
3
+ size 117440664
model-00042-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:403273c3a08447f55a2e10cc185671c8283906d3f48e2b6c1f3323e7f12cc6cd
3
+ size 117440656
model-00043-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d55d56b67fcda633bfc97a68eb1a0f29b25058c678961354e090a7d255e3615
3
+ size 8344
model-00044-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ba0d6f335d206262c3789ef7aa4bd260d56d0100c39d2fbb57929d51d374b4c
3
+ size 8388760
model-00045-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9ccb4a00554f6870ee20cba233110ee1d2f2fec9a5abc94f8f09db320e9c67d
3
+ size 33554584
model-00046-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8eba400eb104aca976807b7743476e0d7e1df7fad024cee6b12043e4cb939901
3
+ size 33554584
model-00047-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1671d3d380b7c0ef3eed36bf565800c3158fda9462df93691cd1eca6f90f2ff7
3
+ size 8388760
model-00048-of-00291.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddbdb3cc7247dc10eb70ab278310e583855aeec5833da0e15a0f741622a3c53f
3
+ size 8328