djuna commited on
Commit
7188601
1 Parent(s): 8064dc9

Upload folder using huggingface_hub

Browse files
Files changed (42) hide show
  1. README.md +41 -0
  2. config.json +27 -0
  3. mergekit_config.yml +9 -0
  4. model-00001-of-00034.safetensors +3 -0
  5. model-00002-of-00034.safetensors +3 -0
  6. model-00003-of-00034.safetensors +3 -0
  7. model-00004-of-00034.safetensors +3 -0
  8. model-00005-of-00034.safetensors +3 -0
  9. model-00006-of-00034.safetensors +3 -0
  10. model-00007-of-00034.safetensors +3 -0
  11. model-00008-of-00034.safetensors +3 -0
  12. model-00009-of-00034.safetensors +3 -0
  13. model-00010-of-00034.safetensors +3 -0
  14. model-00011-of-00034.safetensors +3 -0
  15. model-00012-of-00034.safetensors +3 -0
  16. model-00013-of-00034.safetensors +3 -0
  17. model-00014-of-00034.safetensors +3 -0
  18. model-00015-of-00034.safetensors +3 -0
  19. model-00016-of-00034.safetensors +3 -0
  20. model-00017-of-00034.safetensors +3 -0
  21. model-00018-of-00034.safetensors +3 -0
  22. model-00019-of-00034.safetensors +3 -0
  23. model-00020-of-00034.safetensors +3 -0
  24. model-00021-of-00034.safetensors +3 -0
  25. model-00022-of-00034.safetensors +3 -0
  26. model-00023-of-00034.safetensors +3 -0
  27. model-00024-of-00034.safetensors +3 -0
  28. model-00025-of-00034.safetensors +3 -0
  29. model-00026-of-00034.safetensors +3 -0
  30. model-00027-of-00034.safetensors +3 -0
  31. model-00028-of-00034.safetensors +3 -0
  32. model-00029-of-00034.safetensors +3 -0
  33. model-00030-of-00034.safetensors +3 -0
  34. model-00031-of-00034.safetensors +3 -0
  35. model-00032-of-00034.safetensors +3 -0
  36. model-00033-of-00034.safetensors +3 -0
  37. model-00034-of-00034.safetensors +3 -0
  38. model.safetensors.index.json +1 -0
  39. special_tokens_map.json +23 -0
  40. tokenizer.json +0 -0
  41. tokenizer.model +3 -0
  42. tokenizer_config.json +44 -0
README.md ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - icefog72/IceDrunkenCherryRP-7b
4
+ - dreamgen/opus-v1.2-7b
5
+ library_name: transformers
6
+ tags:
7
+ - mergekit
8
+ - merge
9
+
10
+ ---
11
+ # merge
12
+
13
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
14
+
15
+ ## Merge Details
16
+ ### Merge Method
17
+
18
+ This model was merged using the SLERP merge method.
19
+
20
+ ### Models Merged
21
+
22
+ The following models were included in the merge:
23
+ * [icefog72/IceDrunkenCherryRP-7b](https://huggingface.co/icefog72/IceDrunkenCherryRP-7b)
24
+ * [dreamgen/opus-v1.2-7b](https://huggingface.co/dreamgen/opus-v1.2-7b)
25
+
26
+ ### Configuration
27
+
28
+ The following YAML configuration was used to produce this model:
29
+
30
+ ```yaml
31
+ models:
32
+ - model: dreamgen/opus-v1.2-7b
33
+ - model: icefog72/IceDrunkenCherryRP-7b
34
+ merge_method: slerp
35
+ base_model: icefog72/IceDrunkenCherryRP-7b
36
+ dtype: float32
37
+ out_dtype: bfloat16
38
+ parameters:
39
+ t: [0.05,0.19,0.31,0.19,0.31,0.19,0.05]
40
+
41
+ ```
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "icefog72/IceDrunkenCherryRP-7b",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 32768,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_theta": 40000.0,
21
+ "sliding_window": null,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.46.3",
25
+ "use_cache": true,
26
+ "vocab_size": 32000
27
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ models:
2
+ - model: dreamgen/opus-v1.2-7b
3
+ - model: icefog72/IceDrunkenCherryRP-7b
4
+ merge_method: slerp
5
+ base_model: icefog72/IceDrunkenCherryRP-7b
6
+ dtype: float32
7
+ out_dtype: bfloat16
8
+ parameters:
9
+ t: [0.05,0.19,0.31,0.19,0.31,0.19,0.05]
model-00001-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17458450a5d97b38736664a546dbcb82649eb0798690555c0675de7f2e9868c3
3
+ size 262144128
model-00002-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f87438c36fd3afb676e9ec6d928119f3c07f7aa119b14d8c8302244e0abe471
3
+ size 497033688
model-00003-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8460c99fea86e572d9471de028eca7f84cf0db902cd8bc67e395d22c2d6b1b00
3
+ size 436225056
model-00004-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dfc5de8e8f299ca9565fa056e3eff67333b82f205461bc471d4435dac8d9fa1
3
+ size 436225064
model-00005-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74e8537ced5405dbe234ee3efbe9f54640cd6a029211e7c1cbc9667cc7d215d6
3
+ size 436225072
model-00006-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:342dcfdd1a6da8fbbe718642b1c8933c7e37f14b30db1bc030dcf44a9728bd35
3
+ size 436225072
model-00007-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c566e68c72ffd8b8a1801ce5a65a6e10d2f8f07f68febf1e7673ae1d108be68
3
+ size 436225072
model-00008-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca3e069f3011c88883fc0e2e38f946429e1c008426f598347e1328108f75d780
3
+ size 436225072
model-00009-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4668cdde53237ae31463138d656a506b7b134abbf69aae65b310beaca8740bc6
3
+ size 436225072
model-00010-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:277e73023d47e97dcc85dce5521be843fee9ca6c473bb69596648a6c294d545e
3
+ size 436225072
model-00011-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fade0aa6ff935ddac5a43f11c5afd597572e8c405c3346e70b9c6449bd31dc8
3
+ size 436225072
model-00012-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9820ac2dee364fe0e3645f63a6a02f34a470e310ff0d8f742e01a9dddbea8e8
3
+ size 436225072
model-00013-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a49c473947b3d3d57a80f92a9dc2d265b4bde47844cff3026d470a38eecfe55a
3
+ size 436225072
model-00014-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f5b1ad64898c926264703d55decb34b345897561787403d3812613f6045eff2
3
+ size 436225064
model-00015-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c18bcad744fbc75e44995dc4beafec20e01bdf6b480221966f6993fbdaa26e2
3
+ size 436225064
model-00016-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b143dd82654891584743a4cdc08b69151e8d734cf28cf136309e761998525b7
3
+ size 436225072
model-00017-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb0cc39fc7e7156426ef2d9fafb676c8184b2902f33fd8a33ee31e2f333152e9
3
+ size 436225072
model-00018-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0cc83811482da5d64303e36d07c248fa5e66dc3f675f3707798691ff42f0da3
3
+ size 436225072
model-00019-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85ea644ef686d10d5dc9dba5698bb4c42154de9e05881cef5afe9f99a5935525
3
+ size 436225072
model-00020-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fe651e888883ae19ba6279c344d0cca9ca1acee51ef6b4051ec393761dfd028
3
+ size 436225072
model-00021-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b1abbf0ab42f82cb828938a2d865635006b97fcc016b393882325618a342c2f
3
+ size 436225072
model-00022-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f7170398f1479990a47078e24f86d01bc31f88cc88c3e2664cfa5906cf9d37e
3
+ size 436225072
model-00023-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:412affa4153117dbf87f3e53d1d6713326d5bea697176a22d28db5023207a2ea
3
+ size 436225072
model-00024-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c088e6bd12abc0e391401fe554c66d08e764d173b580e28ff543887f01ee01f4
3
+ size 436225072
model-00025-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:320749fc28fd08629d88fa300ee800b2754cc61e8fad06256f34cf6b0c3d1e98
3
+ size 436225064
model-00026-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a46c61e431de327357b9a3a9a9074e1af6361630857c86748dacd465a5336bc
3
+ size 436225064
model-00027-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cab22440759fb33698f368b940b104cabb39f7f6474acd340ef4b0614e958fb
3
+ size 436225072
model-00028-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0508b3abeb676f9ee1dd2bce77ab977fea0ca9dbf06d010428071673d95a0fc
3
+ size 436225064
model-00029-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aed66e8659760a6e045932dcc11df45ec11232ca74341460721ce1933f342f35
3
+ size 436225056
model-00030-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:587f2ec150080134094c601321c85d030f03066c113c9613de028e4d9452f7cf
3
+ size 436225056
model-00031-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86b44fe259fedaaa49fe2a4963406e4fb0cec21ccfd6074410c267a85be8f3fd
3
+ size 436225056
model-00032-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1d2f51f0a9b07ab98fb0f381ad9359fd00ba036d69702fca084be0a31e88ea6
3
+ size 436225056
model-00033-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fad4b23d10a6e6016792a79a022d2e06cd26aa60a8d2a6421bf4d47a68dbf578
3
+ size 436225056
model-00034-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6a91956d42dfa4a54ff228e53771554eccdccd66660c6a06193dcc2ebf85216
3
+ size 201343792
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.5.1", "total_size": 14483464192}, "weight_map": {"lm_head.weight": "model-00001-of-00034.safetensors", "model.embed_tokens.weight": "model-00002-of-00034.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00034.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00034.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00034.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00034.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00034.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00034.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00034.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00034.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00034.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00034.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00034.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00034.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00004-of-00034.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00034.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00004-of-00034.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00034.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00034.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00034.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00034.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00034.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00034.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00005-of-00034.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00034.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00034.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00034.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00034.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00034.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00034.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00005-of-00034.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00034.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00006-of-00034.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00034.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00034.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00034.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00034.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00034.safetensors", "model.layers.12.input_layernorm.weight": "model-00006-of-00034.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00006-of-00034.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00034.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00007-of-00034.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00034.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00034.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00034.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00034.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00034.safetensors", "model.layers.13.input_layernorm.weight": "model-00007-of-00034.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00007-of-00034.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00034.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00008-of-00034.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00008-of-00034.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00034.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00034.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00034.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00034.safetensors", "model.layers.14.input_layernorm.weight": "model-00008-of-00034.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00008-of-00034.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00008-of-00034.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00009-of-00034.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00034.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00009-of-00034.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00034.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00034.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00034.safetensors", "model.layers.15.input_layernorm.weight": "model-00009-of-00034.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00009-of-00034.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00009-of-00034.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00010-of-00034.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00034.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00034.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00010-of-00034.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00010-of-00034.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00010-of-00034.safetensors", "model.layers.16.input_layernorm.weight": "model-00010-of-00034.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00010-of-00034.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00010-of-00034.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00011-of-00034.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00034.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00011-of-00034.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00011-of-00034.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00011-of-00034.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00011-of-00034.safetensors", "model.layers.17.input_layernorm.weight": "model-00011-of-00034.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00011-of-00034.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00011-of-00034.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00012-of-00034.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00012-of-00034.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00012-of-00034.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00012-of-00034.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00012-of-00034.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00012-of-00034.safetensors", "model.layers.18.input_layernorm.weight": "model-00012-of-00034.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00012-of-00034.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00012-of-00034.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00013-of-00034.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00013-of-00034.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00013-of-00034.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00013-of-00034.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00013-of-00034.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00013-of-00034.safetensors", "model.layers.19.input_layernorm.weight": "model-00013-of-00034.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00013-of-00034.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00013-of-00034.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00014-of-00034.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00014-of-00034.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00014-of-00034.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00014-of-00034.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00014-of-00034.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00014-of-00034.safetensors", "model.layers.2.input_layernorm.weight": "model-00014-of-00034.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00014-of-00034.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00014-of-00034.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00015-of-00034.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00015-of-00034.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00015-of-00034.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00015-of-00034.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00015-of-00034.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00015-of-00034.safetensors", "model.layers.20.input_layernorm.weight": "model-00015-of-00034.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00015-of-00034.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00015-of-00034.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00016-of-00034.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00016-of-00034.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00016-of-00034.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00016-of-00034.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00016-of-00034.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00016-of-00034.safetensors", "model.layers.21.input_layernorm.weight": "model-00016-of-00034.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00016-of-00034.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00016-of-00034.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00017-of-00034.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00017-of-00034.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00017-of-00034.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00017-of-00034.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00017-of-00034.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00017-of-00034.safetensors", "model.layers.22.input_layernorm.weight": "model-00017-of-00034.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00017-of-00034.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00017-of-00034.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00018-of-00034.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00018-of-00034.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00018-of-00034.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00018-of-00034.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00018-of-00034.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00018-of-00034.safetensors", "model.layers.23.input_layernorm.weight": "model-00018-of-00034.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00018-of-00034.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00018-of-00034.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00019-of-00034.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00019-of-00034.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00019-of-00034.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00019-of-00034.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00019-of-00034.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00019-of-00034.safetensors", "model.layers.24.input_layernorm.weight": "model-00019-of-00034.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00019-of-00034.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00019-of-00034.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00020-of-00034.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00020-of-00034.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00020-of-00034.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00020-of-00034.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00020-of-00034.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00020-of-00034.safetensors", "model.layers.25.input_layernorm.weight": "model-00020-of-00034.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00020-of-00034.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00020-of-00034.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00021-of-00034.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00021-of-00034.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00021-of-00034.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00021-of-00034.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00021-of-00034.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00021-of-00034.safetensors", "model.layers.26.input_layernorm.weight": "model-00021-of-00034.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00021-of-00034.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00021-of-00034.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00022-of-00034.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00022-of-00034.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00022-of-00034.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00022-of-00034.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00022-of-00034.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00022-of-00034.safetensors", "model.layers.27.input_layernorm.weight": "model-00022-of-00034.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00022-of-00034.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00022-of-00034.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00023-of-00034.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00023-of-00034.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00023-of-00034.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00023-of-00034.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00023-of-00034.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00023-of-00034.safetensors", "model.layers.28.input_layernorm.weight": "model-00023-of-00034.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00023-of-00034.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00023-of-00034.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00024-of-00034.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00024-of-00034.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00024-of-00034.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00024-of-00034.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00024-of-00034.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00024-of-00034.safetensors", "model.layers.29.input_layernorm.weight": "model-00024-of-00034.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00024-of-00034.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00024-of-00034.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00025-of-00034.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00025-of-00034.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00025-of-00034.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00025-of-00034.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00025-of-00034.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00025-of-00034.safetensors", "model.layers.3.input_layernorm.weight": "model-00025-of-00034.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00025-of-00034.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00025-of-00034.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00026-of-00034.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00026-of-00034.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00026-of-00034.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00026-of-00034.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00026-of-00034.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00026-of-00034.safetensors", "model.layers.30.input_layernorm.weight": "model-00026-of-00034.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00026-of-00034.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00026-of-00034.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00027-of-00034.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00027-of-00034.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00027-of-00034.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00027-of-00034.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00027-of-00034.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00027-of-00034.safetensors", "model.layers.31.input_layernorm.weight": "model-00027-of-00034.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00027-of-00034.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00027-of-00034.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00028-of-00034.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00028-of-00034.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00028-of-00034.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00028-of-00034.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00028-of-00034.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00028-of-00034.safetensors", "model.layers.4.input_layernorm.weight": "model-00028-of-00034.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00028-of-00034.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00028-of-00034.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00029-of-00034.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00029-of-00034.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00029-of-00034.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00029-of-00034.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00029-of-00034.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00029-of-00034.safetensors", "model.layers.5.input_layernorm.weight": "model-00029-of-00034.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00029-of-00034.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00029-of-00034.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00030-of-00034.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00030-of-00034.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00030-of-00034.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00030-of-00034.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00030-of-00034.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00030-of-00034.safetensors", "model.layers.6.input_layernorm.weight": "model-00030-of-00034.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00030-of-00034.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00030-of-00034.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00031-of-00034.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00031-of-00034.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00031-of-00034.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00031-of-00034.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00031-of-00034.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00031-of-00034.safetensors", "model.layers.7.input_layernorm.weight": "model-00031-of-00034.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00031-of-00034.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00031-of-00034.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00032-of-00034.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00032-of-00034.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00032-of-00034.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00032-of-00034.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00032-of-00034.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00032-of-00034.safetensors", "model.layers.8.input_layernorm.weight": "model-00032-of-00034.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00032-of-00034.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00032-of-00034.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00033-of-00034.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00033-of-00034.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00033-of-00034.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00033-of-00034.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00033-of-00034.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00033-of-00034.safetensors", "model.layers.9.input_layernorm.weight": "model-00033-of-00034.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00033-of-00034.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00033-of-00034.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00034-of-00034.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00034-of-00034.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00034-of-00034.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00034-of-00034.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00034-of-00034.safetensors", "model.norm.weight": "model-00034-of-00034.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "chat_template": "{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content'] %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n {%- endif %}\n {%- if message['role'] == 'user' %}\n {%- if loop.first and system_message is defined %}\n {{- ' [INST] ' + system_message + '\\n\\n' + message['content'] + ' [/INST]' }}\n {%- else %}\n {{- ' [INST] ' + message['content'] + ' [/INST]' }}\n {%- endif %}\n {%- elif message['role'] == 'assistant' %}\n {{- ' ' + message['content'] + eos_token}}\n {%- else %}\n {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}\n {%- endif %}\n{%- endfor %}\n",
34
+ "clean_up_tokenization_spaces": false,
35
+ "eos_token": "</s>",
36
+ "legacy": false,
37
+ "model_max_length": 1000000000000000019884624838656,
38
+ "pad_token": null,
39
+ "sp_model_kwargs": {},
40
+ "spaces_between_special_tokens": false,
41
+ "tokenizer_class": "LlamaTokenizer",
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": false
44
+ }