jumtul commited on
Commit
ba91681
1 Parent(s): bfa4091

Initial commit

Browse files
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - hyeogi/SOLAR-10.7B-dpo-v1
4
+ - LDCC/LDCC-SOLAR-10.7B
5
+ tags:
6
+ - mergekit
7
+ - merge
8
+
9
+ ---
10
+ # merge
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 SLERP merge method.
18
+
19
+ ### Models Merged
20
+
21
+ The following models were included in the merge:
22
+ * [hyeogi/SOLAR-10.7B-dpo-v1](https://huggingface.co/hyeogi/SOLAR-10.7B-dpo-v1)
23
+ * [LDCC/LDCC-SOLAR-10.7B](https://huggingface.co/LDCC/LDCC-SOLAR-10.7B)
24
+
25
+ ### Configuration
26
+
27
+ The following YAML configuration was used to produce this model:
28
+
29
+ ```yaml
30
+
31
+
32
+ slices:
33
+
34
+ - sources:
35
+
36
+ - model: LDCC/LDCC-SOLAR-10.7B
37
+
38
+ layer_range: [0, 48]
39
+
40
+ - model: hyeogi/SOLAR-10.7B-dpo-v1
41
+
42
+ layer_range: [0, 48]
43
+
44
+ merge_method: slerp
45
+ tokenizer_source: base
46
+ base_model: LDCC/LDCC-SOLAR-10.7B
47
+
48
+ embed_slerp: true
49
+
50
+ parameters:
51
+
52
+ t:
53
+
54
+ - filter: self_attn
55
+
56
+ value: [0, 0.5, 0.3, 0.7, 1]
57
+
58
+ - filter: mlp
59
+
60
+ value: [1, 0.5, 0.7, 0.3, 0]
61
+
62
+ - value: 0.5
63
+
64
+ dtype: bfloat16
65
+
66
+
67
+ ```
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "LDCC/LDCC-SOLAR-10.7B",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 32000,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 48,
18
+ "num_key_value_heads": 8,
19
+ "pad_token_id": 2,
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": "bfloat16",
26
+ "transformers_version": "4.37.2",
27
+ "use_cache": true,
28
+ "vocab_size": 48000
29
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+
3
+ slices:
4
+
5
+ - sources:
6
+
7
+ - model: LDCC/LDCC-SOLAR-10.7B
8
+
9
+ layer_range: [0, 48]
10
+
11
+ - model: hyeogi/SOLAR-10.7B-dpo-v1
12
+
13
+ layer_range: [0, 48]
14
+
15
+ merge_method: slerp
16
+ tokenizer_source: base
17
+ base_model: LDCC/LDCC-SOLAR-10.7B
18
+
19
+ embed_slerp: true
20
+
21
+ parameters:
22
+
23
+ t:
24
+
25
+ - filter: self_attn
26
+
27
+ value: [0, 0.5, 0.3, 0.7, 1]
28
+
29
+ - filter: mlp
30
+
31
+ value: [1, 0.5, 0.7, 0.3, 0]
32
+
33
+ - value: 0.5
34
+
35
+ dtype: bfloat16
36
+
model-00001-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b38f5f7212a390f8883dd47706a324ecd2168b0f2978fe8f63d5ed5e3dcc60ef
3
+ size 1996559344
model-00002-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb73baf7cd8cc082226a3eb2eff044b4bef76bdbef9ba9af640358537e30f93f
3
+ size 1895903648
model-00003-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77ff19a396f5533b4e061e281e5a1aaf37343e28fda50d5097f6ee1942989dde
3
+ size 1903218432
model-00004-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42e7883dd99ae5ec321e8052ec622ad4e3e646965b5592ac296080cd3f414610
3
+ size 1979781456
model-00005-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a7b689d466024aacc683d04e712ac8edd5b9cbaf492e4fcfaffe182eb31426b
3
+ size 1979798064
model-00006-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1259e25946e82a4923e0d887d18a1af9e4eebaa1f6c820cbb8458a2830427818
3
+ size 1996567672
model-00007-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1792b8d9f75f68add2979b0ba4d5fa4bed0e2af6bdc1b734cdc128cc8b9d4aa
3
+ size 1895903688
model-00008-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d29ee646192282038682b93c103d6981dea62d53b42458e586346c490cfffcbd
3
+ size 1946243984
model-00009-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31464040abe34f451888596f7fc1575a8a0493c4e894a9a3d827db74c163b2bd
3
+ size 1979781456
model-00010-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38c67ed118b1d5751273cd55494d9003df4abf2f22a1812b1b5525ea42cf1292
3
+ size 1979798064
model-00011-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e276fc19fd247769eb73ba26635c2df1047e7693202ab164ba3ce986138e676
3
+ size 1936797416
model-00012-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba919136483815a2e3f0831fe03a2adb391a89a48cf6a2ec67c223d87374b2ab
3
+ size 234889576
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.embed_tokens.weight": "model-00003-of-00012.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.10.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.32.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.21.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.42.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.41.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.40.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.39.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.38.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.37.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.36.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.35.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.34.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.33.input_layernorm.weight": "model-00011-of-00012.safetensors", "lm_head.weight": "model-00011-of-00012.safetensors", "model.norm.weight": "model-00011-of-00012.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.47.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.46.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.45.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00012-of-00012.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00012-of-00012.safetensors", "model.layers.44.input_layernorm.weight": "model-00012-of-00012.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": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
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_config.json ADDED
The diff for this file is too large to render. See raw diff