KatyTheCutie commited on
Commit
8940576
1 Parent(s): 2fb03a4

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - KatyTheCutie/EstopianMaid-13B
4
+ - Undi95/X-MythoChronos-13B
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
+ * [KatyTheCutie/EstopianMaid-13B](https://huggingface.co/KatyTheCutie/EstopianMaid-13B)
24
+ * [Undi95/X-MythoChronos-13B](https://huggingface.co/Undi95/X-MythoChronos-13B)
25
+
26
+ ### Configuration
27
+
28
+ The following YAML configuration was used to produce this model:
29
+
30
+ ```yaml
31
+
32
+ models:
33
+ - model: Undi95/X-MythoChronos-13B
34
+ - model: KatyTheCutie/EstopianMaid-13B
35
+ merge_method: slerp
36
+ base_model: KatyTheCutie/EstopianMaid-13B
37
+ parameters:
38
+ t:
39
+ - filter: self_attn
40
+ value: [0, 0.5, 0.3, 0.7, 1]
41
+ - filter: mlp
42
+ value: [1, 0.5, 0.7, 0.3, 0]
43
+ - value: 0.5 # fallback for rest of tensors
44
+ dtype: float16
45
+
46
+ ```
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "MythoMaid-13B-SLERP",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 13824,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 40,
18
+ "num_key_value_heads": 40,
19
+ "pad_token_id": 0,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float16",
26
+ "transformers_version": "4.38.2",
27
+ "use_cache": true,
28
+ "vocab_size": 32000
29
+ }
model-00001-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8821b46c21e46966eb71b197c58a17f0c424c7eda9224e6efd43a3702a55e04
3
+ size 1903230008
model-00002-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c03e829de58d68f89e36cd50cb447570bca045e61937dcd3656ddb7f9563bce1
3
+ size 1903230000
model-00003-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e7da0479f0de79d06257c52f081f6fd241e8a49843eb85d04bd6db08bcafda3
3
+ size 1903229984
model-00004-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abd781f8061e74157b1e0c3eca644f94c92cadd28884713bf6998def4a87633c
3
+ size 1903229984
model-00005-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fe766d648e08be63296b147c3d994cd3c37447b655f2a6790faa6bb41d30e5e
3
+ size 1903229984
model-00006-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:578bb5407fb7076e7fa82a0b4cb3cfa19bff628accb72aee03e6790a7490df64
3
+ size 1984473704
model-00007-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84d455540b42604fda2c6eaa20615abe2d9fb88f5c48dd744f1c8416b98bc2b3
3
+ size 1955669280
model-00008-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:760e663d94b049c818b8056c15aef47716c824db928f2566b607d5cf99de58e7
3
+ size 1903230008
model-00009-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70e73db452a20820b92562175242db655174d440b32bcdc7e076a0944feb81c2
3
+ size 1903230008
model-00010-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c3ad6b2c3e1b9c3b3919c0f9d541010b55ed3c79afbaad9146dbb2e8667e0b8
3
+ size 1903230008
model-00011-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f924cedbab75e64b9fd729c3674ff880b379184b547b2308d9aba4b799c06e7
3
+ size 1879626192
model-00012-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca6cb75f3b30adf3b8efd1918f8d32b1bbf81548b544282f7565c0b94ba8a7d4
3
+ size 1903230016
model-00013-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:484ea25d5fe6ab3f1174cd362dda8556980f74af2980a0ded576dfb7bd7df1d3
3
+ size 1903230016
model-00014-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:147240a79f40f808d6be5fb2f5e46513d6780c20a95c100092ef671087bb56ce
3
+ size 1179701408
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.14.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.0.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.embed_tokens.weight": "model-00006-of-00014.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.21.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.20.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.19.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.18.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.17.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.16.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00011-of-00014.safetensors", "lm_head.weight": "model-00011-of-00014.safetensors", "model.norm.weight": "model-00011-of-00014.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.39.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.38.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.37.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.36.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.35.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.34.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.33.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.32.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.31.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00014-of-00014.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "model_max_length": 1000000000000000019884624838656,
34
+ "pad_token": null,
35
+ "sp_model_kwargs": {},
36
+ "tokenizer_class": "LlamaTokenizer",
37
+ "unk_token": "<unk>",
38
+ "use_default_system_prompt": false
39
+ }