saishf commited on
Commit
d1fe44b
1 Parent(s): 0f7c978

Upload 19 files

Browse files
README.md CHANGED
@@ -1,3 +1,48 @@
1
  ---
2
- license: cc-by-nc-4.0
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ base_model:
3
+ - Sao10K/Fimbulvetr-10.7B-v1
4
+ - saishf/Kuro-Lotus-10.7B
5
+ library_name: transformers
6
+ tags:
7
+ - mergekit
8
+ - merge
9
+
10
  ---
11
+ # merge
12
+
13
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
14
+
15
+ ## Merge Details
16
+ ### Merge Method
17
+
18
+ This model was merged using the SLERP merge method.
19
+
20
+ ### Models Merged
21
+
22
+ The following models were included in the merge:
23
+ * [Sao10K/Fimbulvetr-10.7B-v1](https://huggingface.co/Sao10K/Fimbulvetr-10.7B-v1)
24
+ * [saishf/Kuro-Lotus-10.7B](https://huggingface.co/saishf/Kuro-Lotus-10.7B)
25
+
26
+ ### Configuration
27
+
28
+ The following YAML configuration was used to produce this model:
29
+
30
+ ```yaml
31
+ slices:
32
+ - sources:
33
+ - model: saishf/Kuro-Lotus-10.7B
34
+ layer_range: [0, 48]
35
+ - model: Sao10K/Fimbulvetr-10.7B-v1
36
+ layer_range: [0, 48]
37
+ merge_method: slerp
38
+ base_model: saishf/Kuro-Lotus-10.7B
39
+ parameters:
40
+ t:
41
+ - filter: self_attn
42
+ value: [0.6, 0.7, 0.8, 0.9, 1]
43
+ - filter: mlp
44
+ value: [0.4, 0.3, 0.2, 0.1, 0]
45
+ - value: 0.5
46
+ dtype: bfloat16
47
+
48
+ ```
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "saishf/Kuro-Lotus-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": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
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": false,
28
+ "vocab_size": 32000
29
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ slices:
2
+ - sources:
3
+ - model: saishf/Kuro-Lotus-10.7B
4
+ layer_range: [0, 48]
5
+ - model: Sao10K/Fimbulvetr-10.7B-v1
6
+ layer_range: [0, 48]
7
+ merge_method: slerp
8
+ base_model: saishf/Kuro-Lotus-10.7B
9
+ parameters:
10
+ t:
11
+ - filter: self_attn
12
+ value: [0.6, 0.7, 0.8, 0.9, 1]
13
+ - filter: mlp
14
+ value: [0.4, 0.3, 0.2, 0.1, 0]
15
+ - value: 0.5
16
+ dtype: bfloat16
model-00001-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45e47324d9dfe779d2b2181ecf82a3ab71cc552cbd195631a42817dfb438036b
3
+ size 1898000688
model-00002-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69cd37dd82cb754e4e821a2082f0f28ef1a6c5c72fbee17d7660a59fc978bd9e
3
+ size 1979781416
model-00003-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaeefda4c8a1f84932022a33a6aa806fd82e24958817807ef5b76c7368350bc8
3
+ size 1988186784
model-00004-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8281f6b12f3fe52e5a11895d57d28233f4ffd1dcc763d328a584fec3078745b2
3
+ size 1937846944
model-00005-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b21143b75718314a7b5a31db82a24fe7599df58695656dff4315f7db13eb0d6
3
+ size 1988178496
model-00006-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06ae3aa334d6cc19ec22552c6c21ad4a9aafb363eb4a34002fb28218316a3ebd
3
+ size 1937846944
model-00007-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d65a1d88b421a04dbbb8b816f486c5958a8f6dbe31e845c07199d41e729f6a86
3
+ size 1988178496
model-00008-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4584db0da41b4585fdcd6a13e20bc8beadf9f0cb828498922ca7e40d7dfe00bf
3
+ size 1937846944
model-00009-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8ac7218780e6d166bca8dbaa559fd7dafff2d51580db06f86f8436dba03c3b1
3
+ size 1979781456
model-00010-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77b6f56e25fc9a260e030b436eebb9ca1e2a320cfcb03731ce682a8e8c4aaa91
3
+ size 1937838640
model-00011-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cccccf8404ef90a8144e77e098ebda91ffb76edb70bb521b5fb9d5af05db61b3
3
+ size 1889611952
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.embed_tokens.weight": "model-00001-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.21.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.21.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.35.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00010-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.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.q_proj.weight": "model-00010-of-00011.safetensors", "lm_head.weight": "model-00011-of-00011.safetensors", "model.norm.weight": "model-00011-of-00011.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.44.input_layernorm.weight": "model-00011-of-00011.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</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.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 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": true,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "</s>",
36
+ "sp_model_kwargs": {},
37
+ "spaces_between_special_tokens": false,
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "trust_remote_code": false,
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false,
42
+ "use_fast": true
43
+ }