PotatoB commited on
Commit
5a0e006
·
verified ·
1 Parent(s): 9737870

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - merge
5
+ - mergekit
6
+ - potatoB/task_3-1
7
+ - potatoB/task_2-1
8
+ ---
9
+
10
+ # task_4-1
11
+
12
+ task_4-1 is a merged model generated for Model Kinship experiments, originating from
13
+ * [potatoB/task_3-1](https://huggingface.co/potatoB/task_3-1)
14
+ * [potatoB/task_2-1](https://huggingface.co/potatoB/task_2-1)
15
+
16
+ ## 🧩 Configuration
17
+
18
+ ```yaml
19
+ slices:
20
+ - sources:
21
+ - model: potatoB/task_3-1
22
+ layer_range: [0, 32]
23
+ - model: potatoB/task_2-1
24
+ layer_range: [0, 32]
25
+ merge_method: slerp
26
+ base_model: potatoB/task_3-1
27
+ parameters:
28
+ t:
29
+ - filter: self_attn
30
+ value: [0, 0.5, 0.3, 0.7, 1]
31
+ - filter: mlp
32
+ value: [1, 0.5, 0.7, 0.3, 0]
33
+ - value: 0.5
34
+ dtype: float16
35
+ ```
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "potatoB/task_3-1",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 32768,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": null,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "float16",
24
+ "transformers_version": "4.46.3",
25
+ "use_cache": false,
26
+ "vocab_size": 32000
27
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - model: potatoB/task_3-1
5
+ layer_range: [0, 32]
6
+ - model: potatoB/task_2-1
7
+ layer_range: [0, 32]
8
+ merge_method: slerp
9
+ base_model: potatoB/task_3-1
10
+ parameters:
11
+ t:
12
+ - filter: self_attn
13
+ value: [0, 0.5, 0.3, 0.7, 1]
14
+ - filter: mlp
15
+ value: [1, 0.5, 0.7, 0.3, 0]
16
+ - value: 0.5
17
+ dtype: float16
model-00001-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4200d2976c2dc4d1860cbd462521611476af27773fbcc8965a407eff624eeafb
3
+ size 960521544
model-00002-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e2d02c5aca2411b4d1f26e3d193c63664e732c6bff2e26150f4706f655e0711
3
+ size 989890704
model-00003-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b42e6e8e9dc23b4ecfc334beeb462048dc9ddca7284b4357b785c57340079d4
3
+ size 989890712
model-00004-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98f25fb14d023161ddc93384ef4b7b087a1926ab06810e30c398faf7097174a2
3
+ size 998287736
model-00005-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3098e3fbf3a5d76450dbb6966c377aeee1611fd82fa8bd848d8c62033b150c93
3
+ size 947956192
model-00006-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4fdae0bfb8537a965e78caa8fb826e12a96074a8e6c514a147d65434607dff8
3
+ size 989890704
model-00007-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70e372082dfcdbf16e4ac3a2f782eee6c64cb75b8a5aca1c92558f96355f88a4
3
+ size 989890704
model-00008-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1539c693b15a83dc295acc4278358c7af4c90c67e83756d8cc67902c07eb6cbe
3
+ size 998287736
model-00009-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a390a9179a31b62302520255d05601ee53a103744ecc09bc233c94962af18cd
3
+ size 947956192
model-00010-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e09f16588351cdcd67e83041e5e6fdad7db823008ffa13c64b435ad4093a18c
3
+ size 989890712
model-00011-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cde24437755993191219f7463c48d1887330be02482cfb33ccb7ce6a360cbcb8
3
+ size 989890704
model-00012-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:352285dab92efe4072b38f1e9b1b03a9827afa2bd43bc5bcd6897c2953f7bc8e
3
+ size 998287736
model-00013-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e08de9b6e6b4801dbfaa44b1ad0dbb14b9ccd3a4adbb50072dbbaab97d0be2a5
3
+ size 947956176
model-00014-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf7fbd8fca31bbf9d411dda60bf280cb6931b59c1da277e9f5dc94cc40bc5781
3
+ size 989890688
model-00015-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33d8b2c50a43f1be1cd352ece90ac03e519e2c9632c210d2977ef5d3d9f2af8e
3
+ size 755009424
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.5.1", "total_size": 14483464192}, "weight_map": {"lm_head.weight": "model-00001-of-00015.safetensors", "model.embed_tokens.weight": "model-00001-of-00015.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.26.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.28.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.29.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.3.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.30.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.31.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.4.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.6.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00015-of-00015.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00015-of-00015.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00015-of-00015.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00015-of-00015.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00015-of-00015.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.input_layernorm.weight": "model-00015-of-00015.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00015-of-00015.safetensors", "model.norm.weight": "model-00015-of-00015.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 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
34
+ "clean_up_tokenization_spaces": false,
35
+ "eos_token": "</s>",
36
+ "legacy": true,
37
+ "model_max_length": 1000000000000000019884624838656,
38
+ "pad_token": "</s>",
39
+ "sp_model_kwargs": {},
40
+ "spaces_between_special_tokens": false,
41
+ "tokenizer_class": "LlamaTokenizer",
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": false,
44
+ "use_fast": true
45
+ }