LeroyDyer commited on
Commit
1915bd9
1 Parent(s): 7cfb34e

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - LeroyDyer/Mixtral_AI_Cyber_3.m1
4
+ - LeroyDyer/Mixtral_AI_Cyber_3.1_SFT
5
+ - LeroyDyer/Mixtral_AI_Cyber_2.0
6
+ - LeroyDyer/Mixtral_AI_Cyber_1.0
7
+ - LeroyDyer/Mixtral_AI_Cyber_3.m2
8
+ - LeroyDyer/Mixtral_AI_Cyber_3.0
9
+ library_name: transformers
10
+ tags:
11
+ - mergekit
12
+ - merge
13
+
14
+ ---
15
+ # merge
16
+
17
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
18
+
19
+ ## Merge Details
20
+ ### Merge Method
21
+
22
+ This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [LeroyDyer/Mixtral_AI_Cyber_3.m2](https://huggingface.co/LeroyDyer/Mixtral_AI_Cyber_3.m2) as a base.
23
+
24
+ ### Models Merged
25
+
26
+ The following models were included in the merge:
27
+ * [LeroyDyer/Mixtral_AI_Cyber_3.m1](https://huggingface.co/LeroyDyer/Mixtral_AI_Cyber_3.m1)
28
+ * [LeroyDyer/Mixtral_AI_Cyber_3.1_SFT](https://huggingface.co/LeroyDyer/Mixtral_AI_Cyber_3.1_SFT)
29
+ * [LeroyDyer/Mixtral_AI_Cyber_2.0](https://huggingface.co/LeroyDyer/Mixtral_AI_Cyber_2.0)
30
+ * [LeroyDyer/Mixtral_AI_Cyber_1.0](https://huggingface.co/LeroyDyer/Mixtral_AI_Cyber_1.0)
31
+ * [LeroyDyer/Mixtral_AI_Cyber_3.0](https://huggingface.co/LeroyDyer/Mixtral_AI_Cyber_3.0)
32
+
33
+ ### Configuration
34
+
35
+ The following YAML configuration was used to produce this model:
36
+
37
+ ```yaml
38
+
39
+ models:
40
+ - model: LeroyDyer/Mixtral_AI_Cyber_3.m2
41
+ parameters:
42
+ density: [0.256, 0.512, 0.128] # density gradient
43
+ weight: 0.382
44
+ - model: LeroyDyer/Mixtral_AI_Cyber_2.0
45
+ parameters:
46
+ density: 0.382
47
+ weight: [0.256, 0.128, 0.256, 0.128] # weight gradient
48
+ - model: LeroyDyer/Mixtral_AI_Cyber_3.0
49
+ parameters:
50
+ density: 0.382
51
+ weight: [0.128, 0.512, 0.128, 0.128] # weight gradient
52
+ - model: LeroyDyer/Mixtral_AI_Cyber_3.m1
53
+ parameters:
54
+ density: 0.382
55
+ weight: [0.256, 0.256, 0.512, 0.128] # weight gradient
56
+ - model: LeroyDyer/Mixtral_AI_Cyber_1.0
57
+ parameters:
58
+ density: 0.382
59
+ weight: [0.128, 0.512, 0.128, 0.128] # weight gradient
60
+ - model: LeroyDyer/Mixtral_AI_Cyber_3.1_SFT
61
+ parameters:
62
+ density: 0.382
63
+ weight:
64
+ - filter: mlp
65
+ value: 0.5
66
+ - value: 0
67
+ merge_method: ties
68
+ base_model: LeroyDyer/Mixtral_AI_Cyber_3.m2
69
+ parameters:
70
+ normalize: true
71
+ int8_mask: true
72
+ dtype: float16
73
+
74
+ ```
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "LeroyDyer/Mixtral_AI_Cyber_3.m2",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "pad_token_id": 2,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_theta": 10000.0,
21
+ "sliding_window": 4096,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "float16",
24
+ "transformers_version": "4.38.2",
25
+ "unsloth_version": "2024.3",
26
+ "use_cache": true,
27
+ "vocab_size": 32000
28
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ models:
3
+ - model: LeroyDyer/Mixtral_AI_Cyber_3.m2
4
+ parameters:
5
+ density: [0.256, 0.512, 0.128] # density gradient
6
+ weight: 0.382
7
+ - model: LeroyDyer/Mixtral_AI_Cyber_2.0
8
+ parameters:
9
+ density: 0.382
10
+ weight: [0.256, 0.128, 0.256, 0.128] # weight gradient
11
+ - model: LeroyDyer/Mixtral_AI_Cyber_3.0
12
+ parameters:
13
+ density: 0.382
14
+ weight: [0.128, 0.512, 0.128, 0.128] # weight gradient
15
+ - model: LeroyDyer/Mixtral_AI_Cyber_3.m1
16
+ parameters:
17
+ density: 0.382
18
+ weight: [0.256, 0.256, 0.512, 0.128] # weight gradient
19
+ - model: LeroyDyer/Mixtral_AI_Cyber_1.0
20
+ parameters:
21
+ density: 0.382
22
+ weight: [0.128, 0.512, 0.128, 0.128] # weight gradient
23
+ - model: LeroyDyer/Mixtral_AI_Cyber_3.1_SFT
24
+ parameters:
25
+ density: 0.382
26
+ weight:
27
+ - filter: mlp
28
+ value: 0.5
29
+ - value: 0
30
+ merge_method: ties
31
+ base_model: LeroyDyer/Mixtral_AI_Cyber_3.m2
32
+ parameters:
33
+ normalize: true
34
+ int8_mask: true
35
+ dtype: float16
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c18a99280a4c1abce0209e0d1e4e5fc8d66b434039397198307dff2a7a748bf2
3
+ size 1912664448
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a66af77b2b597d77e22a65d82e10ae6c1f757f2b571289b81cd8545ca0bd01e
3
+ size 1895870400
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a3069bec3770d7da1862a39afdabb501156fdd3bf1c28571e4300cc921a6718
3
+ size 1946227288
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a441e53812eb2359e038246e1df69814a3fe3a557edadd7e16943685f11ccea8
3
+ size 1979781416
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52943d518cccf7af24e1244eaa50f600ad0b623d25e58b95de2fc38f280a3ce4
3
+ size 1889645184
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:732f00ed61c86ce5b340893a3f67184f87eaa871635e81e4656cee23dacb7222
3
+ size 1946210728
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6475e02c882c257cd6389a7ff032eb4fe5a340358c228aca53ecf6bbf3d9e50
3
+ size 1923182616
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a593dde4cdf03f2d3664af7f629ab1c16650a19b4a4fd5f15dab6f4e3f3208e
3
+ size 989915608
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 14483464192}, "weight_map": {"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.embed_tokens.weight": "model-00005-of-00008.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00007-of-00008.safetensors", "lm_head.weight": "model-00007-of-00008.safetensors", "model.norm.weight": "model-00007-of-00008.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00008.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
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
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 32768,
37
+ "pad_token": "<unk>",
38
+ "padding_side": "right",
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
+ }