aipib commited on
Commit
4904b9f
1 Parent(s): 11e456d

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - kcoopermiller/llm-jp-1.3b-v1.0-aya
4
+ - llm-jp/llm-jp-1.3b-v1.0
5
+ tags:
6
+ - merge
7
+ - mergekit
8
+ - lazymergekit
9
+ - kcoopermiller/llm-jp-1.3b-v1.0-aya
10
+ - llm-jp/llm-jp-1.3b-v1.0
11
+ ---
12
+
13
+ # llmjp-dareties
14
+
15
+ llmjp-dareties is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
16
+ * [kcoopermiller/llm-jp-1.3b-v1.0-aya](https://huggingface.co/kcoopermiller/llm-jp-1.3b-v1.0-aya)
17
+ * [llm-jp/llm-jp-1.3b-v1.0](https://huggingface.co/llm-jp/llm-jp-1.3b-v1.0)
18
+
19
+ ## 🧩 Configuration
20
+
21
+ ```yaml
22
+ slices:
23
+ - sources:
24
+ - layer_range: [0, 24]
25
+ model: kcoopermiller/llm-jp-1.3b-v1.0-aya
26
+ parameters:
27
+ density: [1, 0.7, 0.1]
28
+ weight: 1.0
29
+ - layer_range: [0, 24]
30
+ model: llm-jp/llm-jp-1.3b-v1.0
31
+ parameters:
32
+ density: 0.33
33
+ weight:
34
+ - filter: mlp
35
+ value: 0.5
36
+ - value: 0
37
+ merge_method: dare_ties
38
+ base_model: llm-jp/llm-jp-1.3b-v1.0
39
+ parameters:
40
+ normalize: true
41
+ int8_mask: true
42
+ dtype: bfloat16
43
+ ```
44
+
45
+ ## 💻 Usage
46
+
47
+ ```python
48
+ !pip install -qU transformers accelerate
49
+
50
+ from transformers import AutoTokenizer
51
+ import transformers
52
+ import torch
53
+
54
+ model = "aipib/llmjp-dareties"
55
+ messages = [{"role": "user", "content": "What is a large language model?"}]
56
+
57
+ tokenizer = AutoTokenizer.from_pretrained(model)
58
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
59
+ pipeline = transformers.pipeline(
60
+ "text-generation",
61
+ model=model,
62
+ torch_dtype=torch.float16,
63
+ device_map="auto",
64
+ )
65
+
66
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
67
+ print(outputs[0]["generated_text"])
68
+ ```
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<unk>": 44876
3
+ }
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "llm-jp/llm-jp-1.3b-v1.0",
3
+ "activation_function": "gelu",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 7,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 7,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 2048,
17
+ "n_head": 16,
18
+ "n_inner": 8192,
19
+ "n_layer": 24,
20
+ "n_positions": 2048,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.41.2",
32
+ "use_cache": true,
33
+ "vocab_size": 50688
34
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - layer_range: [0, 24]
5
+ model: kcoopermiller/llm-jp-1.3b-v1.0-aya
6
+ parameters:
7
+ density: [1, 0.7, 0.1]
8
+ weight: 1.0
9
+ - layer_range: [0, 24]
10
+ model: llm-jp/llm-jp-1.3b-v1.0
11
+ parameters:
12
+ density: 0.33
13
+ weight:
14
+ - filter: mlp
15
+ value: 0.5
16
+ - value: 0
17
+ merge_method: dare_ties
18
+ base_model: llm-jp/llm-jp-1.3b-v1.0
19
+ parameters:
20
+ normalize: true
21
+ int8_mask: true
22
+ dtype: bfloat16
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b3b12841fe2e167e2fffc7ca7a5072cb0330b51e127be050e94d01e99225287
3
+ size 973623440
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7690964d51476a0318df2d1f1f92f0fe4e1b270a654f36d4377e92d6461c6be5
3
+ size 973619232
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8d8c5b534c770efd1d3fb96dcce5508356077d04d3a350905387ddc52f4a0cd
3
+ size 685999688
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 2633211904}, "weight_map": {"transformer.h.0.attn.c_attn.bias": "model-00001-of-00003.safetensors", "transformer.h.0.attn.c_attn.weight": "model-00001-of-00003.safetensors", "transformer.h.0.attn.c_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.0.attn.c_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.0.ln_1.bias": "model-00001-of-00003.safetensors", "transformer.h.0.ln_1.weight": "model-00001-of-00003.safetensors", "transformer.h.0.ln_2.bias": "model-00001-of-00003.safetensors", "transformer.h.0.ln_2.weight": "model-00001-of-00003.safetensors", "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00003.safetensors", "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00003.safetensors", "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.1.attn.c_attn.bias": "model-00001-of-00003.safetensors", "transformer.h.1.attn.c_attn.weight": "model-00001-of-00003.safetensors", "transformer.h.1.attn.c_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.1.attn.c_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.1.ln_1.bias": "model-00001-of-00003.safetensors", "transformer.h.1.ln_1.weight": "model-00001-of-00003.safetensors", "transformer.h.1.ln_2.bias": "model-00001-of-00003.safetensors", "transformer.h.1.ln_2.weight": "model-00001-of-00003.safetensors", "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00003.safetensors", "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00003.safetensors", "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.10.attn.c_attn.bias": "model-00001-of-00003.safetensors", "transformer.h.10.attn.c_attn.weight": "model-00001-of-00003.safetensors", "transformer.h.10.attn.c_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.10.attn.c_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.10.ln_1.bias": "model-00001-of-00003.safetensors", "transformer.h.10.ln_1.weight": "model-00001-of-00003.safetensors", "transformer.h.10.ln_2.bias": "model-00001-of-00003.safetensors", "transformer.h.10.ln_2.weight": "model-00001-of-00003.safetensors", "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00003.safetensors", "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00003.safetensors", "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.11.attn.c_attn.bias": "model-00001-of-00003.safetensors", "transformer.h.11.attn.c_attn.weight": "model-00001-of-00003.safetensors", "transformer.h.11.attn.c_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.11.attn.c_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.11.ln_1.bias": "model-00001-of-00003.safetensors", "transformer.h.11.ln_1.weight": "model-00001-of-00003.safetensors", "transformer.h.11.ln_2.bias": "model-00001-of-00003.safetensors", "transformer.h.11.ln_2.weight": "model-00001-of-00003.safetensors", "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00003.safetensors", "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00003.safetensors", "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.12.attn.c_attn.bias": "model-00001-of-00003.safetensors", "transformer.h.12.attn.c_attn.weight": "model-00001-of-00003.safetensors", "transformer.h.12.attn.c_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.12.attn.c_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.12.ln_1.bias": "model-00001-of-00003.safetensors", "transformer.h.12.ln_1.weight": "model-00001-of-00003.safetensors", "transformer.h.12.ln_2.bias": "model-00001-of-00003.safetensors", "transformer.h.12.ln_2.weight": "model-00001-of-00003.safetensors", "transformer.h.12.mlp.c_fc.bias": "model-00001-of-00003.safetensors", "transformer.h.12.mlp.c_fc.weight": "model-00001-of-00003.safetensors", "transformer.h.12.mlp.c_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.12.mlp.c_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.13.attn.c_attn.bias": "model-00001-of-00003.safetensors", "transformer.h.13.attn.c_attn.weight": "model-00001-of-00003.safetensors", "transformer.h.13.attn.c_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.13.attn.c_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.13.ln_1.bias": "model-00001-of-00003.safetensors", "transformer.h.13.ln_1.weight": "model-00001-of-00003.safetensors", "transformer.h.13.ln_2.bias": "model-00001-of-00003.safetensors", "transformer.h.13.ln_2.weight": "model-00001-of-00003.safetensors", "transformer.h.13.mlp.c_fc.bias": "model-00001-of-00003.safetensors", "transformer.h.13.mlp.c_fc.weight": "model-00001-of-00003.safetensors", "transformer.h.13.mlp.c_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.13.mlp.c_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.14.attn.c_attn.bias": "model-00001-of-00003.safetensors", "transformer.h.14.attn.c_attn.weight": "model-00001-of-00003.safetensors", "transformer.h.14.attn.c_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.14.attn.c_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.14.ln_1.bias": "model-00001-of-00003.safetensors", "transformer.h.14.ln_1.weight": "model-00001-of-00003.safetensors", "transformer.h.14.ln_2.bias": "model-00001-of-00003.safetensors", "transformer.h.14.ln_2.weight": "model-00001-of-00003.safetensors", "transformer.h.14.mlp.c_fc.bias": "model-00001-of-00003.safetensors", "transformer.h.14.mlp.c_fc.weight": "model-00001-of-00003.safetensors", "transformer.h.14.mlp.c_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.14.mlp.c_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.15.attn.c_attn.bias": "model-00001-of-00003.safetensors", "transformer.h.15.attn.c_attn.weight": "model-00001-of-00003.safetensors", "transformer.h.15.attn.c_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.15.attn.c_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.15.ln_1.bias": "model-00001-of-00003.safetensors", "transformer.h.15.ln_1.weight": "model-00001-of-00003.safetensors", "transformer.h.15.ln_2.bias": "model-00001-of-00003.safetensors", "transformer.h.15.ln_2.weight": "model-00001-of-00003.safetensors", "transformer.h.15.mlp.c_fc.bias": "model-00001-of-00003.safetensors", "transformer.h.15.mlp.c_fc.weight": "model-00001-of-00003.safetensors", "transformer.h.15.mlp.c_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.15.mlp.c_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.16.attn.c_attn.bias": "model-00001-of-00003.safetensors", "transformer.h.16.attn.c_attn.weight": "model-00001-of-00003.safetensors", "transformer.h.16.attn.c_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.16.attn.c_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.16.ln_1.bias": "model-00001-of-00003.safetensors", "transformer.h.16.ln_1.weight": "model-00001-of-00003.safetensors", "transformer.h.16.ln_2.bias": "model-00001-of-00003.safetensors", "transformer.h.16.ln_2.weight": "model-00001-of-00003.safetensors", "transformer.h.16.mlp.c_fc.bias": "model-00001-of-00003.safetensors", "transformer.h.16.mlp.c_fc.weight": "model-00001-of-00003.safetensors", "transformer.h.16.mlp.c_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.16.mlp.c_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.17.attn.c_attn.bias": "model-00001-of-00003.safetensors", "transformer.h.17.attn.c_attn.weight": "model-00001-of-00003.safetensors", "transformer.h.17.attn.c_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.17.attn.c_proj.weight": "model-00001-of-00003.safetensors", "transformer.h.17.ln_1.bias": "model-00001-of-00003.safetensors", "transformer.h.17.ln_1.weight": "model-00001-of-00003.safetensors", "transformer.h.17.ln_2.bias": "model-00001-of-00003.safetensors", "transformer.h.17.ln_2.weight": "model-00001-of-00003.safetensors", "transformer.h.17.mlp.c_fc.bias": "model-00001-of-00003.safetensors", "transformer.h.17.mlp.c_fc.weight": "model-00001-of-00003.safetensors", "transformer.h.17.mlp.c_proj.bias": "model-00001-of-00003.safetensors", "transformer.h.17.mlp.c_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.18.attn.c_attn.bias": "model-00002-of-00003.safetensors", "transformer.h.18.attn.c_attn.weight": "model-00002-of-00003.safetensors", "transformer.h.18.attn.c_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.18.attn.c_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.18.ln_1.bias": "model-00002-of-00003.safetensors", "transformer.h.18.ln_1.weight": "model-00002-of-00003.safetensors", "transformer.h.18.ln_2.bias": "model-00002-of-00003.safetensors", "transformer.h.18.ln_2.weight": "model-00002-of-00003.safetensors", "transformer.h.18.mlp.c_fc.bias": "model-00002-of-00003.safetensors", "transformer.h.18.mlp.c_fc.weight": "model-00002-of-00003.safetensors", "transformer.h.18.mlp.c_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.18.mlp.c_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.19.attn.c_attn.bias": "model-00002-of-00003.safetensors", "transformer.h.19.attn.c_attn.weight": "model-00002-of-00003.safetensors", "transformer.h.19.attn.c_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.19.attn.c_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.19.ln_1.bias": "model-00002-of-00003.safetensors", "transformer.h.19.ln_1.weight": "model-00002-of-00003.safetensors", "transformer.h.19.ln_2.bias": "model-00002-of-00003.safetensors", "transformer.h.19.ln_2.weight": "model-00002-of-00003.safetensors", "transformer.h.19.mlp.c_fc.bias": "model-00002-of-00003.safetensors", "transformer.h.19.mlp.c_fc.weight": "model-00002-of-00003.safetensors", "transformer.h.19.mlp.c_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.19.mlp.c_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.2.attn.c_attn.bias": "model-00002-of-00003.safetensors", "transformer.h.2.attn.c_attn.weight": "model-00002-of-00003.safetensors", "transformer.h.2.attn.c_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.2.attn.c_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.2.ln_1.bias": "model-00002-of-00003.safetensors", "transformer.h.2.ln_1.weight": "model-00002-of-00003.safetensors", "transformer.h.2.ln_2.bias": "model-00002-of-00003.safetensors", "transformer.h.2.ln_2.weight": "model-00002-of-00003.safetensors", "transformer.h.2.mlp.c_fc.bias": "model-00002-of-00003.safetensors", "transformer.h.2.mlp.c_fc.weight": "model-00002-of-00003.safetensors", "transformer.h.2.mlp.c_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.2.mlp.c_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.20.attn.c_attn.bias": "model-00002-of-00003.safetensors", "transformer.h.20.attn.c_attn.weight": "model-00002-of-00003.safetensors", "transformer.h.20.attn.c_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.20.attn.c_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.20.ln_1.bias": "model-00002-of-00003.safetensors", "transformer.h.20.ln_1.weight": "model-00002-of-00003.safetensors", "transformer.h.20.ln_2.bias": "model-00002-of-00003.safetensors", "transformer.h.20.ln_2.weight": "model-00002-of-00003.safetensors", "transformer.h.20.mlp.c_fc.bias": "model-00002-of-00003.safetensors", "transformer.h.20.mlp.c_fc.weight": "model-00002-of-00003.safetensors", "transformer.h.20.mlp.c_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.20.mlp.c_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.21.attn.c_attn.bias": "model-00002-of-00003.safetensors", "transformer.h.21.attn.c_attn.weight": "model-00002-of-00003.safetensors", "transformer.h.21.attn.c_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.21.attn.c_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.21.ln_1.bias": "model-00002-of-00003.safetensors", "transformer.h.21.ln_1.weight": "model-00002-of-00003.safetensors", "transformer.h.21.ln_2.bias": "model-00002-of-00003.safetensors", "transformer.h.21.ln_2.weight": "model-00002-of-00003.safetensors", "transformer.h.21.mlp.c_fc.bias": "model-00002-of-00003.safetensors", "transformer.h.21.mlp.c_fc.weight": "model-00002-of-00003.safetensors", "transformer.h.21.mlp.c_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.21.mlp.c_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.22.attn.c_attn.bias": "model-00002-of-00003.safetensors", "transformer.h.22.attn.c_attn.weight": "model-00002-of-00003.safetensors", "transformer.h.22.attn.c_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.22.attn.c_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.22.ln_1.bias": "model-00002-of-00003.safetensors", "transformer.h.22.ln_1.weight": "model-00002-of-00003.safetensors", "transformer.h.22.ln_2.bias": "model-00002-of-00003.safetensors", "transformer.h.22.ln_2.weight": "model-00002-of-00003.safetensors", "transformer.h.22.mlp.c_fc.bias": "model-00002-of-00003.safetensors", "transformer.h.22.mlp.c_fc.weight": "model-00002-of-00003.safetensors", "transformer.h.22.mlp.c_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.22.mlp.c_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.23.attn.c_attn.bias": "model-00002-of-00003.safetensors", "transformer.h.23.attn.c_attn.weight": "model-00002-of-00003.safetensors", "transformer.h.23.attn.c_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.23.attn.c_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.23.ln_1.bias": "model-00002-of-00003.safetensors", "transformer.h.23.ln_1.weight": "model-00002-of-00003.safetensors", "transformer.h.23.ln_2.bias": "model-00002-of-00003.safetensors", "transformer.h.23.ln_2.weight": "model-00002-of-00003.safetensors", "transformer.h.23.mlp.c_fc.bias": "model-00002-of-00003.safetensors", "transformer.h.23.mlp.c_fc.weight": "model-00002-of-00003.safetensors", "transformer.h.23.mlp.c_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.23.mlp.c_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.3.attn.c_attn.bias": "model-00002-of-00003.safetensors", "transformer.h.3.attn.c_attn.weight": "model-00002-of-00003.safetensors", "transformer.h.3.attn.c_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.3.attn.c_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.3.ln_1.bias": "model-00002-of-00003.safetensors", "transformer.h.3.ln_1.weight": "model-00002-of-00003.safetensors", "transformer.h.3.ln_2.bias": "model-00002-of-00003.safetensors", "transformer.h.3.ln_2.weight": "model-00002-of-00003.safetensors", "transformer.h.3.mlp.c_fc.bias": "model-00002-of-00003.safetensors", "transformer.h.3.mlp.c_fc.weight": "model-00002-of-00003.safetensors", "transformer.h.3.mlp.c_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.3.mlp.c_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.4.attn.c_attn.bias": "model-00002-of-00003.safetensors", "transformer.h.4.attn.c_attn.weight": "model-00002-of-00003.safetensors", "transformer.h.4.attn.c_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.4.attn.c_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.4.ln_1.bias": "model-00002-of-00003.safetensors", "transformer.h.4.ln_1.weight": "model-00002-of-00003.safetensors", "transformer.h.4.ln_2.bias": "model-00002-of-00003.safetensors", "transformer.h.4.ln_2.weight": "model-00002-of-00003.safetensors", "transformer.h.4.mlp.c_fc.bias": "model-00002-of-00003.safetensors", "transformer.h.4.mlp.c_fc.weight": "model-00002-of-00003.safetensors", "transformer.h.4.mlp.c_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.4.mlp.c_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.5.attn.c_attn.bias": "model-00002-of-00003.safetensors", "transformer.h.5.attn.c_attn.weight": "model-00002-of-00003.safetensors", "transformer.h.5.attn.c_proj.bias": "model-00002-of-00003.safetensors", "transformer.h.5.attn.c_proj.weight": "model-00002-of-00003.safetensors", "transformer.h.5.ln_1.bias": "model-00002-of-00003.safetensors", "transformer.h.5.ln_1.weight": "model-00002-of-00003.safetensors", "transformer.h.5.ln_2.bias": "model-00002-of-00003.safetensors", "transformer.h.5.ln_2.weight": "model-00002-of-00003.safetensors", "transformer.h.5.mlp.c_fc.bias": "model-00002-of-00003.safetensors", "transformer.h.5.mlp.c_fc.weight": "model-00003-of-00003.safetensors", "transformer.h.5.mlp.c_proj.bias": "model-00003-of-00003.safetensors", "transformer.h.5.mlp.c_proj.weight": "model-00003-of-00003.safetensors", "transformer.h.6.attn.c_attn.bias": "model-00003-of-00003.safetensors", "transformer.h.6.attn.c_attn.weight": "model-00003-of-00003.safetensors", "transformer.h.6.attn.c_proj.bias": "model-00003-of-00003.safetensors", "transformer.h.6.attn.c_proj.weight": "model-00003-of-00003.safetensors", "transformer.h.6.ln_1.bias": "model-00003-of-00003.safetensors", "transformer.h.6.ln_1.weight": "model-00003-of-00003.safetensors", "transformer.h.6.ln_2.bias": "model-00003-of-00003.safetensors", "transformer.h.6.ln_2.weight": "model-00003-of-00003.safetensors", "transformer.h.6.mlp.c_fc.bias": "model-00003-of-00003.safetensors", "transformer.h.6.mlp.c_fc.weight": "model-00003-of-00003.safetensors", "transformer.h.6.mlp.c_proj.bias": "model-00003-of-00003.safetensors", "transformer.h.6.mlp.c_proj.weight": "model-00003-of-00003.safetensors", "transformer.h.7.attn.c_attn.bias": "model-00003-of-00003.safetensors", "transformer.h.7.attn.c_attn.weight": "model-00003-of-00003.safetensors", "transformer.h.7.attn.c_proj.bias": "model-00003-of-00003.safetensors", "transformer.h.7.attn.c_proj.weight": "model-00003-of-00003.safetensors", "transformer.h.7.ln_1.bias": "model-00003-of-00003.safetensors", "transformer.h.7.ln_1.weight": "model-00003-of-00003.safetensors", "transformer.h.7.ln_2.bias": "model-00003-of-00003.safetensors", "transformer.h.7.ln_2.weight": "model-00003-of-00003.safetensors", "transformer.h.7.mlp.c_fc.bias": "model-00003-of-00003.safetensors", "transformer.h.7.mlp.c_fc.weight": "model-00003-of-00003.safetensors", "transformer.h.7.mlp.c_proj.bias": "model-00003-of-00003.safetensors", "transformer.h.7.mlp.c_proj.weight": "model-00003-of-00003.safetensors", "transformer.h.8.attn.c_attn.bias": "model-00003-of-00003.safetensors", "transformer.h.8.attn.c_attn.weight": "model-00003-of-00003.safetensors", "transformer.h.8.attn.c_proj.bias": "model-00003-of-00003.safetensors", "transformer.h.8.attn.c_proj.weight": "model-00003-of-00003.safetensors", "transformer.h.8.ln_1.bias": "model-00003-of-00003.safetensors", "transformer.h.8.ln_1.weight": "model-00003-of-00003.safetensors", "transformer.h.8.ln_2.bias": "model-00003-of-00003.safetensors", "transformer.h.8.ln_2.weight": "model-00003-of-00003.safetensors", "transformer.h.8.mlp.c_fc.bias": "model-00003-of-00003.safetensors", "transformer.h.8.mlp.c_fc.weight": "model-00003-of-00003.safetensors", "transformer.h.8.mlp.c_proj.bias": "model-00003-of-00003.safetensors", "transformer.h.8.mlp.c_proj.weight": "model-00003-of-00003.safetensors", "transformer.h.9.attn.c_attn.bias": "model-00003-of-00003.safetensors", "transformer.h.9.attn.c_attn.weight": "model-00003-of-00003.safetensors", "transformer.h.9.attn.c_proj.bias": "model-00003-of-00003.safetensors", "transformer.h.9.attn.c_proj.weight": "model-00003-of-00003.safetensors", "transformer.h.9.ln_1.bias": "model-00003-of-00003.safetensors", "transformer.h.9.ln_1.weight": "model-00003-of-00003.safetensors", "transformer.h.9.ln_2.bias": "model-00003-of-00003.safetensors", "transformer.h.9.ln_2.weight": "model-00003-of-00003.safetensors", "transformer.h.9.mlp.c_fc.bias": "model-00003-of-00003.safetensors", "transformer.h.9.mlp.c_fc.weight": "model-00003-of-00003.safetensors", "transformer.h.9.mlp.c_proj.bias": "model-00003-of-00003.safetensors", "transformer.h.9.mlp.c_proj.weight": "model-00003-of-00003.safetensors", "transformer.ln_f.bias": "model-00003-of-00003.safetensors", "transformer.ln_f.weight": "model-00003-of-00003.safetensors", "transformer.wpe.weight": "model-00003-of-00003.safetensors", "transformer.wte.weight": "model-00003-of-00003.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "</s|LLM-jp>"
4
+ ],
5
+ "bos_token": {
6
+ "content": "<s|LLM-jp>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "cls_token": {
13
+ "content": "<CLS|LLM-jp>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "content": "<EOD|LLM-jp>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "mask_token": {
27
+ "content": "<mask|LLM-jp>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "pad_token": {
34
+ "content": "<pad|LLM-jp>",
35
+ "lstrip": false,
36
+ "normalized": false,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ },
40
+ "sep_token": {
41
+ "content": "<SEP|LLM-jp>",
42
+ "lstrip": false,
43
+ "normalized": false,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ },
47
+ "unk_token": {
48
+ "content": "<unk|LLM-jp>",
49
+ "lstrip": false,
50
+ "normalized": false,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ }
54
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dbbd4ddbe43941051ed35fd44ff0d9d1c00ed345f7fd4d1969df174110f0609
3
+ size 1044749
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk|LLM-jp>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s|LLM-jp>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s|LLM-jp>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<mask|LLM-jp>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<pad|LLM-jp>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<CLS|LLM-jp>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<SEP|LLM-jp>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<EOD|LLM-jp>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ }
67
+ },
68
+ "additional_special_tokens": [
69
+ "</s|LLM-jp>"
70
+ ],
71
+ "bos_token": "<s|LLM-jp>",
72
+ "clean_up_tokenization_spaces": false,
73
+ "cls_token": "<CLS|LLM-jp>",
74
+ "eod_token": "<EOD|LLM-jp>",
75
+ "eos_token": "<EOD|LLM-jp>",
76
+ "extra_ids": 0,
77
+ "mask_token": "<mask|LLM-jp>",
78
+ "model_max_length": 1000000000000000019884624838656,
79
+ "pad_token": "<pad|LLM-jp>",
80
+ "sep_token": "<SEP|LLM-jp>",
81
+ "sp_model_kwargs": {},
82
+ "tokenizer_class": "PreTrainedTokenizerFast",
83
+ "unk_token": "<unk|LLM-jp>"
84
+ }