dozzke commited on
Commit
e774e8e
1 Parent(s): ba19e79

Upload 9 files

Browse files
README.md ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - NousResearch/Hermes-2-Pro-Mistral-7B
4
+ - Open-Orca/Mistral-7B-OpenOrca
5
+ library_name: transformers
6
+ tags:
7
+ - mergekit
8
+ - merge
9
+
10
+ ---
11
+ # model_hermorca
12
+
13
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
14
+
15
+ ## Merge Details
16
+ ### Merge Method
17
+
18
+ This model was merged using the SLERP merge method.
19
+
20
+ ### Models Merged
21
+
22
+ The following models were included in the merge:
23
+ * [NousResearch/Hermes-2-Pro-Mistral-7B](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B)
24
+ * [Open-Orca/Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca)
25
+
26
+ ### Configuration
27
+
28
+ The following YAML configuration was used to produce this model:
29
+
30
+ ```yaml
31
+
32
+ slices:
33
+ - sources:
34
+ - model: NousResearch/Hermes-2-Pro-Mistral-7B
35
+ layer_range: [0, 32]
36
+ - model: Open-Orca/Mistral-7B-OpenOrca
37
+ layer_range: [0, 32]
38
+ merge_method: slerp
39
+ base_model: NousResearch/Hermes-2-Pro-Mistral-7B
40
+ parameters:
41
+ t:
42
+ - filter: self_attn
43
+ value: [0, 0.5, 0.3, 0.7, 1]
44
+ - filter: mlp
45
+ value: [1, 0.5, 0.7, 0.3, 0]
46
+ - value: 0.5
47
+ dtype: bfloat16
48
+
49
+ ```
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 32000,
3
+ "<|im_start|>": 32001
4
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "NousResearch/Hermes-2-Pro-Mistral-7B",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 32000,
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": "4.39.0.dev0",
24
+ "use_cache": false,
25
+ "vocab_size": 32002
26
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - model: NousResearch/Hermes-2-Pro-Mistral-7B
5
+ layer_range: [0, 32]
6
+ - model: Open-Orca/Mistral-7B-OpenOrca
7
+ layer_range: [0, 32]
8
+ merge_method: slerp
9
+ base_model: NousResearch/Hermes-2-Pro-Mistral-7B
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
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.8.mlp.gate_proj.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.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-00001-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-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-00002-of-00008.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.embed_tokens.weight": "model-00003-of-00008.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.input_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-00003-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-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.mlp.up_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.11.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00007-of-00008.safetensors", "lm_head.weight": "model-00007-of-00008.safetensors", "model.norm.weight": "model-00007-of-00008.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00008.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": "<|im_end|>",
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 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "32000": {
31
+ "content": "<|im_end|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|im_start|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ }
46
+ },
47
+ "additional_special_tokens": [],
48
+ "bos_token": "<s>",
49
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
50
+ "clean_up_tokenization_spaces": false,
51
+ "eos_token": "<|im_end|>",
52
+ "legacy": true,
53
+ "model_max_length": 1000000000000000019884624838656,
54
+ "pad_token": "</s>",
55
+ "sp_model_kwargs": {},
56
+ "spaces_between_special_tokens": false,
57
+ "tokenizer_class": "LlamaTokenizer",
58
+ "unk_token": "<unk>",
59
+ "use_default_system_prompt": false,
60
+ "use_fast": true
61
+ }