jeiku commited on
Commit
db76240
1 Parent(s): 3935716

Upload 8 files

Browse files
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - jeiku/ToxicNoRobotsRosaHermesBoros_3B
4
+ - jeiku/Theory_of_Mind_StableLM
5
+ - jeiku/ToxicNoRobotsRosaHermesBoros_3B
6
+ - jeiku/ToxicNoRobotsRosaHermesBoros_3B
7
+ - jeiku/Everything_v3_StableLM
8
+ - jeiku/ToxicNoRobotsRosaHermesBoros_3B
9
+ - jeiku/Bluemoon_cleaned_StableLM
10
+ - jeiku/ToxicNoRobotsRosaHermesBoros_3B
11
+ - jeiku/Capybara_StableLM
12
+ - jeiku/ToxicNoRobotsRosaHermesBoros_3B
13
+ - jeiku/alpaca-cleaned_StableLM
14
+ tags:
15
+ - mergekit
16
+ - merge
17
+
18
+ ---
19
+ # lower
20
+
21
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
22
+
23
+ ## Merge Details
24
+ ### Merge Method
25
+
26
+ This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [jeiku/ToxicNoRobotsRosaHermesBoros_3B](https://huggingface.co/jeiku/ToxicNoRobotsRosaHermesBoros_3B) as a base.
27
+
28
+ ### Models Merged
29
+
30
+ The following models were included in the merge:
31
+ * [jeiku/ToxicNoRobotsRosaHermesBoros_3B](https://huggingface.co/jeiku/ToxicNoRobotsRosaHermesBoros_3B) + [jeiku/Theory_of_Mind_StableLM](https://huggingface.co/jeiku/Theory_of_Mind_StableLM)
32
+ * [jeiku/ToxicNoRobotsRosaHermesBoros_3B](https://huggingface.co/jeiku/ToxicNoRobotsRosaHermesBoros_3B) + [jeiku/Everything_v3_StableLM](https://huggingface.co/jeiku/Everything_v3_StableLM)
33
+ * [jeiku/ToxicNoRobotsRosaHermesBoros_3B](https://huggingface.co/jeiku/ToxicNoRobotsRosaHermesBoros_3B) + [jeiku/Bluemoon_cleaned_StableLM](https://huggingface.co/jeiku/Bluemoon_cleaned_StableLM)
34
+ * [jeiku/ToxicNoRobotsRosaHermesBoros_3B](https://huggingface.co/jeiku/ToxicNoRobotsRosaHermesBoros_3B) + [jeiku/Capybara_StableLM](https://huggingface.co/jeiku/Capybara_StableLM)
35
+ * [jeiku/ToxicNoRobotsRosaHermesBoros_3B](https://huggingface.co/jeiku/ToxicNoRobotsRosaHermesBoros_3B) + [jeiku/alpaca-cleaned_StableLM](https://huggingface.co/jeiku/alpaca-cleaned_StableLM)
36
+
37
+ ### Configuration
38
+
39
+ The following YAML configuration was used to produce this model:
40
+
41
+ ```yaml
42
+ models:
43
+ - model: jeiku/ToxicNoRobotsRosaHermesBoros_3B+jeiku/alpaca-cleaned_StableLM
44
+ parameters:
45
+ weight: 0.1
46
+ density: 1
47
+ - model: jeiku/ToxicNoRobotsRosaHermesBoros_3B+jeiku/Capybara_StableLM
48
+ parameters:
49
+ weight: 0.1
50
+ density: 1
51
+ - model: jeiku/ToxicNoRobotsRosaHermesBoros_3B+jeiku/Everything_v3_StableLM
52
+ parameters:
53
+ weight: 0.1
54
+ density: 1
55
+ - model: jeiku/ToxicNoRobotsRosaHermesBoros_3B+jeiku/Theory_of_Mind_StableLM
56
+ parameters:
57
+ weight: 0.15
58
+ density: 1
59
+ - model: jeiku/ToxicNoRobotsRosaHermesBoros_3B+jeiku/Bluemoon_cleaned_StableLM
60
+ parameters:
61
+ weight: 0.1
62
+ density: 1
63
+ merge_method: dare_ties
64
+ base_model: jeiku/ToxicNoRobotsRosaHermesBoros_3B
65
+ parameters:
66
+ dtype: bfloat16
67
+ ```
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "jeiku/ToxicNoRobotsRosaHermesBoros_3B",
3
+ "architectures": [
4
+ "StableLMEpochForCausalLM"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "jeiku/ToxicNoRobotsRosaHermesBoros_3B--configuration_stablelm_epoch.StableLMEpochConfig",
8
+ "AutoModelForCausalLM": "jeiku/ToxicNoRobotsRosaHermesBoros_3B--modeling_stablelm_epoch.StableLMEpochForCausalLM"
9
+ },
10
+ "bos_token_id": 0,
11
+ "eos_token_id": 0,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 2560,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 6912,
16
+ "max_position_embeddings": 4096,
17
+ "model_type": "stablelm_epoch",
18
+ "norm_eps": 1e-05,
19
+ "num_attention_heads": 32,
20
+ "num_heads": 32,
21
+ "num_hidden_layers": 32,
22
+ "num_key_value_heads": 32,
23
+ "rope_pct": 0.25,
24
+ "rope_theta": 10000,
25
+ "rotary_scaling_factor": 1.0,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.35.2",
29
+ "use_cache": true,
30
+ "vocab_size": 50304
31
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ models:
2
+ - model: jeiku/ToxicNoRobotsRosaHermesBoros_3B+jeiku/alpaca-cleaned_StableLM
3
+ parameters:
4
+ weight: 0.1
5
+ density: 1
6
+ - model: jeiku/ToxicNoRobotsRosaHermesBoros_3B+jeiku/Capybara_StableLM
7
+ parameters:
8
+ weight: 0.1
9
+ density: 1
10
+ - model: jeiku/ToxicNoRobotsRosaHermesBoros_3B+jeiku/Everything_v3_StableLM
11
+ parameters:
12
+ weight: 0.1
13
+ density: 1
14
+ - model: jeiku/ToxicNoRobotsRosaHermesBoros_3B+jeiku/Theory_of_Mind_StableLM
15
+ parameters:
16
+ weight: 0.15
17
+ density: 1
18
+ - model: jeiku/ToxicNoRobotsRosaHermesBoros_3B+jeiku/Bluemoon_cleaned_StableLM
19
+ parameters:
20
+ weight: 0.1
21
+ density: 1
22
+ merge_method: dare_ties
23
+ base_model: jeiku/ToxicNoRobotsRosaHermesBoros_3B
24
+ parameters:
25
+ dtype: bfloat16
model-00001-of-00001.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a486965aa6ea68f857c7c734500ec1c64e0c134a88e511e89cc40e7785bae3fb
3
+ size 5590927496
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00001.safetensors", "model.layers.0.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.27.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.27.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.28.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.28.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "lm_head.weight": "model-00001-of-00001.safetensors", "model.layers.29.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.29.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.30.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.30.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.31.input_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.31.post_attention_layernorm.bias": "model-00001-of-00001.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.norm.bias": "model-00001-of-00001.safetensors", "model.norm.weight": "model-00001-of-00001.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
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_config.json ADDED
@@ -0,0 +1,213 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|padding|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50254": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50255": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50256": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50257": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50258": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50259": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50260": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50261": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50262": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50263": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50264": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50265": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50266": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50267": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50268": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50269": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50270": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50271": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50272": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50273": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50274": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50275": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50276": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ }
204
+ },
205
+ "bos_token": "<|endoftext|>",
206
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
207
+ "clean_up_tokenization_spaces": true,
208
+ "eos_token": "<|endoftext|>",
209
+ "model_max_length": 1000000000000000019884624838656,
210
+ "pad_token": "<|endoftext|>",
211
+ "tokenizer_class": "GPTNeoXTokenizer",
212
+ "unk_token": "<|endoftext|>"
213
+ }