Eric111 commited on
Commit
782a406
1 Parent(s): dab3e26

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - merge
5
+ - mergekit
6
+ - lazymergekit
7
+ - Eric111/Mayo
8
+ - Eric111/Roya
9
+ ---
10
+
11
+ # Mayoroya
12
+
13
+ Mayoroya is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
14
+ * [Eric111/Mayo](https://huggingface.co/Eric111/Mayo)
15
+ * [Eric111/Roya](https://huggingface.co/Eric111/Roya)
16
+
17
+ ## 🧩 Configuration
18
+
19
+ ```yaml
20
+ slices:
21
+ - sources:
22
+ - model: Eric111/Mayo
23
+ layer_range: [0, 32]
24
+ - model: Eric111/Roya
25
+ layer_range: [0, 32]
26
+ merge_method: slerp
27
+ base_model: Eric111/Mayo
28
+ parameters:
29
+ t:
30
+ - filter: self_attn
31
+ value: [0, 0.5, 0.3, 0.7, 1]
32
+ - filter: mlp
33
+ value: [1, 0.5, 0.7, 0.3, 0]
34
+ - value: 0.5
35
+ dtype: bfloat16
36
+
37
+ ```
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Eric111/Mayo",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.35.2",
24
+ "use_cache": false,
25
+ "vocab_size": 32000
26
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - model: Eric111/Mayo
5
+ layer_range: [0, 32]
6
+ - model: Eric111/Roya
7
+ layer_range: [0, 32]
8
+ merge_method: slerp
9
+ base_model: Eric111/Mayo
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: bfloat16
18
+
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df89c32ab177b23e872ae6ad5b5007019bab1d302bf29f99671cb960cd9a100b
3
+ size 1946210752
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00b011208a78ef281b581dc8f7949de55816a63a0dc0369f1e5a53709e51a193
3
+ size 1996575968
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e88b1df0a48d147448151fd29d7e4fa4fe7da194b58700496bf3e16346593ab9
3
+ size 1929449432
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5e809bc76788fb2ae74c99d36d00f64a2d1ba0572207bc65da6a6c827e4e690
3
+ size 1946235680
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78d0d82adadedc0205593025b1b557b64786494808141431124096ab75c6fb0e
3
+ size 1889611928
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b131f1175c9327b7cc290caeb7d76da5fc7271696181beced38d3381314ecd8f
3
+ size 1923166072
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b24297b752a5ce3fafc09bc78fd993ff09b23ace435ea93295d6ed8a44ddec5
3
+ size 1979789776
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:847f7f8aa37d82bef61c2a1e95c05df36cc67b1a1c73e4e152e0648435d8d0e3
3
+ size 872458392
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00005-of-00008.safetensors", "lm_head.weight": "model-00005-of-00008.safetensors", "model.norm.weight": "model-00005-of-00008.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.embed_tokens.weight": "model-00006-of-00008.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00008.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
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 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [
29
+ "<unk>",
30
+ "<s>",
31
+ "</s>"
32
+ ],
33
+ "bos_token": "<s>",
34
+ "chat_template": "{% for message in messages %}{{bos_token + message['role'] + '\n' + message['content'] + eos_token + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ bos_token + 'assistant\n' }}{% endif %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "</s>",
37
+ "legacy": true,
38
+ "model_max_length": 8192,
39
+ "pad_token": "</s>",
40
+ "padding_side": "left",
41
+ "sp_model_kwargs": {},
42
+ "spaces_between_special_tokens": false,
43
+ "split_special_tokens": false,
44
+ "tokenizer_class": "LlamaTokenizer",
45
+ "unk_token": "<unk>",
46
+ "use_default_system_prompt": true
47
+ }