ND911 commited on
Commit
85ae9e1
1 Parent(s): 59683f0

Upload 20 files

Browse files
README.md CHANGED
@@ -1,33 +1,25 @@
1
  ---
2
  base_model:
3
  - ND911/Franken-Merlinite-Maid
4
- - l3utterfly/mistral-7b-v0.1-layla-v4-chatml
5
  library_name: transformers
6
  tags:
7
  - mergekit
8
  - merge
9
 
10
  ---
11
-
12
- ![](maid.jpeg)
13
-
14
- # Franken-Mistral-Merlinite-Maid 9B guff
15
 
16
  This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
17
 
18
  ## Merge Details
19
-
20
- see below
21
-
22
  ### Merge Method
23
 
24
- This model was merged using the SLERP merge method.
25
 
26
  ### Models Merged
27
 
28
  The following models were included in the merge:
29
  * [ND911/Franken-Merlinite-Maid](https://huggingface.co/ND911/Franken-Merlinite-Maid)
30
- * [l3utterfly/mistral-7b-v0.1-layla-v4-chatml](https://huggingface.co/l3utterfly/mistral-7b-v0.1-layla-v4-chatml)
31
 
32
  ### Configuration
33
 
@@ -36,20 +28,14 @@ The following YAML configuration was used to produce this model:
36
  ```yaml
37
  slices:
38
  - sources:
39
- - model: ND911/Franken-Merlinite-Maid
40
- layer_range: [0, 32]
41
- - model: l3utterfly/mistral-7b-v0.1-layla-v4-chatml
42
- layer_range: [0, 32]
43
- merge_method: slerp
44
- base_model: ND911/Franken-Merlinite-Maid
45
- parameters:
46
- t:
47
- - filter: self_attn
48
- value: [0, 0.5, 0.3, 0.7, 1]
49
- - filter: mlp
50
- value: [1, 0.5, 0.7, 0.3, 0]
51
- - value: 0.5
52
- dtype: bfloat16
53
-
54
-
55
  ```
 
1
  ---
2
  base_model:
3
  - ND911/Franken-Merlinite-Maid
 
4
  library_name: transformers
5
  tags:
6
  - mergekit
7
  - merge
8
 
9
  ---
10
+ # mergemaid
 
 
 
11
 
12
  This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
13
 
14
  ## Merge Details
 
 
 
15
  ### Merge Method
16
 
17
+ This model was merged using the passthrough merge method.
18
 
19
  ### Models Merged
20
 
21
  The following models were included in the merge:
22
  * [ND911/Franken-Merlinite-Maid](https://huggingface.co/ND911/Franken-Merlinite-Maid)
 
23
 
24
  ### Configuration
25
 
 
28
  ```yaml
29
  slices:
30
  - sources:
31
+ - model: "ND911/Franken-Merlinite-Maid"
32
+ layer_range: [0, 16]
33
+ - sources:
34
+ - model: "ND911/Franken-Merlinite-Maid"
35
+ layer_range: [8, 24]
36
+ - sources:
37
+ - model: "ND911/Franken-Merlinite-Maid"
38
+ layer_range: [17, 32]
39
+ merge_method: passthrough
40
+ dtype: float16
 
 
 
 
 
 
41
  ```
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ND911/Franken-Merlinite-Maid",
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": 8192,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 47,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.38.2",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
maid.jpeg ADDED
mergekit_config.yml ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ slices:
2
+ - sources:
3
+ - model: "ND911/Franken-Merlinite-Maid"
4
+ layer_range: [0, 16]
5
+ - sources:
6
+ - model: "ND911/Franken-Merlinite-Maid"
7
+ layer_range: [8, 24]
8
+ - sources:
9
+ - model: "ND911/Franken-Merlinite-Maid"
10
+ layer_range: [17, 32]
11
+ merge_method: passthrough
12
+ dtype: float16
model-00001-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17e3f42781e875f7ba6c87d8040d41a8f57d1dfedd2cbbf59c993ed38437a410
3
+ size 1979764816
model-00002-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b6359b17a571a0800c803663a0af3d773213db85d96578b957e7edfaf3e1f2f
3
+ size 1979800232
model-00003-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7328308a0c6d9055282466924b1a45773688659b6583e1110d1f1c0b981beaa8
3
+ size 1929449408
model-00004-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bdb6886a1cc113cfcbb5d1fa0440045d03ff198809e5d3eb75521fec9aa2d20
3
+ size 1979789688
model-00005-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc01bbefd20a948572e65f528ecc9f1615ad950da70952fb6d5a6476b9d0ce07
3
+ size 1979797968
model-00006-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28c4af01fdda11fe1f6e32beb54072a8a20505e9d537fbcb3ad3d9ef2830383a
3
+ size 1979781416
model-00007-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4841f58a16218f7727ddbc1a3b4cb8486af8442c30a7a897792cfd9eb63ddf13
3
+ size 1895911480
model-00008-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d55f8c61ee1d532420f188bdff1afb71b98443c11957bf42380ef7290072c98
3
+ size 1946243904
model-00009-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:801bd68ff9341b3d0ee11105e2223560dff2b193384e61130dfc5efbc79466ee
3
+ size 1950403968
model-00010-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36c1b790f1ea929f0295d364889cd3c6941d7678d25f996a2c273d9e9416e82d
3
+ size 1996558880
model-00011-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:999563b0c3c8f9bb7acb436fea669e85f81831794f9c14de392efddcf62ace57
3
+ size 1409371504
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.36.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.norm.weight": "model-00004-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.46.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.45.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.44.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.43.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.embed_tokens.weight": "model-00009-of-00011.safetensors", "lm_head.weight": "model-00009-of-00011.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.42.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.38.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.37.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.36.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00011-of-00011.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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": null,
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }