CorticalStack commited on
Commit
3bf41a3
1 Parent(s): 662b96d

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - merge
5
+ - mergekit
6
+ - mlabonne/AlphaMonarch-7B
7
+ - bardsai/jaskier-7b-dpo-v5.6
8
+ - macadeliccc/MBX-7B-v3-DPO
9
+ ---
10
+
11
+ # pastiche-crown-clown-7B-dare
12
+
13
+ pastiche-crown-clown-7B-dare is a DARE merge of the following models using [mergekit](https://github.com/cg123/mergekit):
14
+ * [mlabonne/AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B)
15
+ * [bardsai/jaskier-7b-dpo-v5.6](https://huggingface.co/bardsai/jaskier-7b-dpo-v5.6)
16
+ * [macadeliccc/MBX-7B-v3-DPO](https://huggingface.co/macadeliccc/MBX-7B-v3-DPO)
17
+
18
+ See the paper [Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch](https://arxiv.org/abs/2311.03099) for more on the method.
19
+
20
+ ## 🧩 Configuration
21
+
22
+ ```yaml
23
+ models:
24
+ - model: mlabonne/NeuralMonarch-7B
25
+ # No parameters necessary for base model
26
+ - model: mlabonne/AlphaMonarch-7B
27
+ parameters:
28
+ density: 0.53
29
+ weight: 0.4
30
+ - model: bardsai/jaskier-7b-dpo-v5.6
31
+ parameters:
32
+ density: 0.53
33
+ weight: 0.3
34
+ - model: macadeliccc/MBX-7B-v3-DPO
35
+ parameters:
36
+ density: 0.53
37
+ weight: 0.3
38
+ merge_method: dare_ties
39
+ base_model: mlabonne/NeuralMonarch-7B
40
+ parameters:
41
+ int8_mask: true
42
+ dtype: bfloat16
43
+ ```
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mlabonne/NeuralMonarch-7B",
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": "4.37.2",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ models:
3
+ - model: mlabonne/NeuralMonarch-7B
4
+ # No parameters necessary for base model
5
+ - model: mlabonne/AlphaMonarch-7B
6
+ parameters:
7
+ density: 0.53
8
+ weight: 0.4
9
+ - model: bardsai/jaskier-7b-dpo-v5.6
10
+ parameters:
11
+ density: 0.53
12
+ weight: 0.3
13
+ - model: macadeliccc/MBX-7B-v3-DPO
14
+ parameters:
15
+ density: 0.53
16
+ weight: 0.3
17
+ merge_method: dare_ties
18
+ base_model: mlabonne/NeuralMonarch-7B
19
+ parameters:
20
+ int8_mask: true
21
+ dtype: bfloat16
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1c4e94d59a1b3b2042256762a84e0fb346919d229447c3f6e1ca261a2f7983f
3
+ size 1979773128
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ec9b61762ce02e3979f5fb1b8bb6dde49b21f173bc28b9af9b4c1506a5727fa
3
+ size 1946235640
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1671a773f94d8cfe20254b3b29b2f43615a31ae4767b84198f4ccdf1b9a3d090
3
+ size 1973490216
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fe6210dc00fe6d9a51f09001916629435fa8c32905fc97062eade4bdb42797f
3
+ size 1979781464
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7676ddc7e0c4cb453ae5a4dbe44ea9d447146314a90190e9b7c71f57052bd12a
3
+ size 1946243984
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d91264faa1d17b06508dce9d6a1d2b0dbb6887e7cdc56170f5d7d92d30cd5ab
3
+ size 1923166040
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:037711c0f067a079adc4540dc9d92cedc0a35ce051bbd08632638ebcd1f2dd4a
3
+ size 1946243984
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb9f924ccd00a17a2e070fa78273834997dc66f9fa650e31076657abe1d72028
3
+ size 788563544
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-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.8.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.embed_tokens.weight": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-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", "lm_head.weight": "model-00006-of-00008.safetensors", "model.norm.weight": "model-00006-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.28.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-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.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-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 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "additional_special_tokens": [
31
+ "<unk>",
32
+ "<s>",
33
+ "</s>"
34
+ ],
35
+ "bos_token": "<s>",
36
+ "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 %}",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "</s>",
39
+ "legacy": true,
40
+ "model_max_length": 8192,
41
+ "pad_token": "</s>",
42
+ "padding_side": "left",
43
+ "sp_model_kwargs": {},
44
+ "spaces_between_special_tokens": false,
45
+ "split_special_tokens": false,
46
+ "tokenizer_class": "LlamaTokenizer",
47
+ "unk_token": "<unk>",
48
+ "use_default_system_prompt": true
49
+ }