MarcGrumpyOlejak commited on
Commit
ac8852a
1 Parent(s): bf4cf9b

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - MarcGrumpyOlejak/VerwaltungsAnthologie_clear_7B
4
+ - DiscoResearch/DiscoLM_German_7b_v1
5
+ library_name: transformers
6
+ tags:
7
+ - mergekit
8
+ - merge
9
+
10
+ ---
11
+ # VerwaltungsAnthologie_Disco_7B
12
+
13
+ This is a first usable experiment of a german based text summarizer after the [talky](https://huggingface.co/MarcGrumpyOlejak/VerwaltungsAnthologie_talky_7B) and the intermediate [clear](https://huggingface.co/MarcGrumpyOlejak/VerwaltungsAnthologie_clear_7B)-versions.
14
+
15
+ In a short direct comparison to [DiscoResearch/DiscoLM_German_7b_v1](https://huggingface.co/DiscoResearch/DiscoLM_German_7b_v1) using ROUGE1, 2 and L, VA_Disco in combination with [hiig-piai/simba-v01c](https://huggingface.co/hiig-piai/simba-v01c) is capable of writing 'better' (more fluently) summaries.
16
+
17
+ |Model|Rouge-1 F|Rouge-2 F|Rouge-L F|
18
+ |-|-|-|-|
19
+ |DiscoLM|18,88|5,70|17,18|
20
+ |VA_disco_results_#6b|23,15|8,67|21,16|
21
+
22
+ "#6b" is the "prompt"-version to "provoke" nicer sentences.
23
+
24
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
25
+
26
+ ## Merge Details
27
+ ### Merge Method
28
+
29
+ This model was merged using the SLERP merge method.
30
+
31
+ ### Models Merged
32
+
33
+ The following models were included in the merge:
34
+ * [MarcGrumpyOlejak/VerwaltungsAnthologie_clear_7B](https://huggingface.co/MarcGrumpyOlejak/VerwaltungsAnthologie_clear_7B)
35
+ * [DiscoResearch/DiscoLM_German_7b_v1](https://huggingface.co/DiscoResearch/DiscoLM_German_7b_v1)
36
+
37
+ ### Configuration
38
+
39
+ The following YAML configuration was used to produce this model:
40
+
41
+ ```yaml
42
+ #
43
+ #
44
+ slices:
45
+ - sources:
46
+ - model: DiscoResearch/DiscoLM_German_7b_v1
47
+ layer_range: [0, 32]
48
+ - model: MarcGrumpyOlejak/VerwaltungsAnthologie_clear_7B
49
+ layer_range: [0, 32]
50
+ merge_method: slerp
51
+ base_model: MarcGrumpyOlejak/VerwaltungsAnthologie_clear_7B
52
+ embed_slerp: true
53
+ parameters:
54
+ t:
55
+ - filter: self_attn
56
+ value: [0, 0.5, 0.3, 0.7, 1]
57
+ - filter: mlp
58
+ value: [1, 0.5, 0.7, 0.3, 0]
59
+ - value: 0.5
60
+ dtype: bfloat16
61
+ name: VerwaltungsAnthologie_Disco_7B
62
+
63
+
64
+ ```
VerwaltungsAnthologie_Disco_7B.yaml ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #
2
+ #
3
+ slices:
4
+ - sources:
5
+ - model: DiscoResearch/DiscoLM_German_7b_v1
6
+ layer_range: [0, 32]
7
+ - model: MarcGrumpyOlejak/VerwaltungsAnthologie_clear_7B
8
+ layer_range: [0, 32]
9
+ merge_method: slerp
10
+ base_model: MarcGrumpyOlejak/VerwaltungsAnthologie_clear_7B
11
+ embed_slerp: true
12
+ parameters:
13
+ t:
14
+ - filter: self_attn
15
+ value: [0, 0.5, 0.3, 0.7, 1]
16
+ - filter: mlp
17
+ value: [1, 0.5, 0.7, 0.3, 0]
18
+ - value: 0.5
19
+ dtype: bfloat16
20
+ name: VerwaltungsAnthologie_Disco_7B
21
+
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "MarcGrumpyOlejak/VerwaltungsAnthologie_clear_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
+ #
3
+ slices:
4
+ - sources:
5
+ - model: DiscoResearch/DiscoLM_German_7b_v1
6
+ layer_range: [0, 32]
7
+ - model: MarcGrumpyOlejak/VerwaltungsAnthologie_clear_7B
8
+ layer_range: [0, 32]
9
+ merge_method: slerp
10
+ base_model: MarcGrumpyOlejak/VerwaltungsAnthologie_clear_7B
11
+ embed_slerp: true
12
+ parameters:
13
+ t:
14
+ - filter: self_attn
15
+ value: [0, 0.5, 0.3, 0.7, 1]
16
+ - filter: mlp
17
+ value: [1, 0.5, 0.7, 0.3, 0]
18
+ - value: 0.5
19
+ dtype: bfloat16
20
+ name: VerwaltungsAnthologie_Disco_7B
21
+
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deca313ff814b3b7cc8596fe3c01d2154f9474313a163beb29099881a6ffb5f6
3
+ size 3926008768
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5f989b773f79778ad070f0dc43a630d183d88ef5abfc883d3468ddf4ac4c5ff
3
+ size 3953271680
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f52d82c3f4d2fbb3810bf31c98966ac9cff743c1c3780e05a34203b18e8afe26
3
+ size 3986858976
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bdae752d1ad2d07c6fa8c2a75b77160024730c5a10f77f744721fe5a0a3d71d
3
+ size 2617358600
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-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.embed_tokens.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "lm_head.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00004.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": null,
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }