aipib commited on
Commit
38dedf1
1 Parent(s): 186ddeb

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - line-corporation/japanese-large-lm-1.7b-instruction-sft
4
+ - line-corporation/japanese-large-lm-1.7b
5
+ tags:
6
+ - merge
7
+ - mergekit
8
+ - lazymergekit
9
+ - line-corporation/japanese-large-lm-1.7b-instruction-sft
10
+ - line-corporation/japanese-large-lm-1.7b
11
+ ---
12
+
13
+ # line-slerp2
14
+
15
+ line-slerp2 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
16
+ * [line-corporation/japanese-large-lm-1.7b-instruction-sft](https://huggingface.co/line-corporation/japanese-large-lm-1.7b-instruction-sft)
17
+ * [line-corporation/japanese-large-lm-1.7b](https://huggingface.co/line-corporation/japanese-large-lm-1.7b)
18
+
19
+ ## 🧩 Configuration
20
+
21
+ ```yaml
22
+ slices:
23
+ - sources:
24
+ - model: line-corporation/japanese-large-lm-1.7b-instruction-sft
25
+ layer_range: [0, 24]
26
+ - model: line-corporation/japanese-large-lm-1.7b
27
+ layer_range: [0, 24]
28
+ merge_method: slerp
29
+ base_model: line-corporation/japanese-large-lm-1.7b
30
+ parameters:
31
+ t:
32
+ - filter: self_attn
33
+ value: [0, 0.5, 0.3, 0.7, 1]
34
+ - filter: mlp
35
+ value: [1, 0.5, 0.7, 0.3, 0]
36
+ - value: 0.5
37
+ dtype: bfloat16
38
+ ```
39
+
40
+ ## 💻 Usage
41
+
42
+ ```python
43
+ !pip install -qU transformers accelerate
44
+
45
+ from transformers import AutoTokenizer
46
+ import transformers
47
+ import torch
48
+
49
+ model = "aipib/line-slerp2"
50
+ messages = [{"role": "user", "content": "What is a large language model?"}]
51
+
52
+ tokenizer = AutoTokenizer.from_pretrained(model)
53
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
54
+ pipeline = transformers.pipeline(
55
+ "text-generation",
56
+ model=model,
57
+ torch_dtype=torch.float16,
58
+ device_map="auto",
59
+ )
60
+
61
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
62
+ print(outputs[0]["generated_text"])
63
+ ```
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "line-corporation/japanese-large-lm-1.7b",
3
+ "activation_function": "gelu",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 1,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 2,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 2048,
16
+ "n_embd": 2304,
17
+ "n_head": 24,
18
+ "n_inner": 9216,
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": 51200
34
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - model: line-corporation/japanese-large-lm-1.7b-instruction-sft
5
+ layer_range: [0, 24]
6
+ - model: line-corporation/japanese-large-lm-1.7b
7
+ layer_range: [0, 24]
8
+ merge_method: slerp
9
+ base_model: line-corporation/japanese-large-lm-1.7b
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-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f37f1baabb06b1c074f4eb9b35c769dc37c4d8490f72797ae98495093e65044
3
+ size 977237696
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11ab9637a2dbf45bbbfcddacad0f3806f27d0f9282ed61d9dcf98af5f1684120
3
+ size 977233008
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be5a83a3e9931c5ecbec9844cc42919f0567d76dbf45aad33ad961ed7605b84f
3
+ size 977195480
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49e3cd642ddca1e4727a44b21849681dbb617ce7b759df77d69814c8e2a010d3
3
+ size 372825608
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 3304461312}, "weight_map": {"transformer.h.0.attn.c_attn.bias": "model-00001-of-00004.safetensors", "transformer.h.0.attn.c_attn.weight": "model-00001-of-00004.safetensors", "transformer.h.0.attn.c_proj.bias": "model-00001-of-00004.safetensors", "transformer.h.0.attn.c_proj.weight": "model-00001-of-00004.safetensors", "transformer.h.0.ln_1.bias": "model-00001-of-00004.safetensors", "transformer.h.0.ln_1.weight": "model-00001-of-00004.safetensors", "transformer.h.0.ln_2.bias": "model-00001-of-00004.safetensors", "transformer.h.0.ln_2.weight": "model-00001-of-00004.safetensors", "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00004.safetensors", "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00004.safetensors", "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00004.safetensors", "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00004.safetensors", "transformer.h.1.attn.c_attn.bias": "model-00001-of-00004.safetensors", "transformer.h.1.attn.c_attn.weight": "model-00001-of-00004.safetensors", "transformer.h.1.attn.c_proj.bias": "model-00001-of-00004.safetensors", "transformer.h.1.attn.c_proj.weight": "model-00001-of-00004.safetensors", "transformer.h.1.ln_1.bias": "model-00001-of-00004.safetensors", "transformer.h.1.ln_1.weight": "model-00001-of-00004.safetensors", "transformer.h.1.ln_2.bias": "model-00001-of-00004.safetensors", "transformer.h.1.ln_2.weight": "model-00001-of-00004.safetensors", "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00004.safetensors", "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00004.safetensors", "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00004.safetensors", "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00004.safetensors", "transformer.h.10.attn.c_attn.bias": "model-00001-of-00004.safetensors", "transformer.h.10.attn.c_attn.weight": "model-00001-of-00004.safetensors", "transformer.h.10.attn.c_proj.bias": "model-00001-of-00004.safetensors", "transformer.h.10.attn.c_proj.weight": "model-00001-of-00004.safetensors", "transformer.h.10.ln_1.bias": "model-00001-of-00004.safetensors", "transformer.h.10.ln_1.weight": "model-00001-of-00004.safetensors", "transformer.h.10.ln_2.bias": "model-00001-of-00004.safetensors", "transformer.h.10.ln_2.weight": "model-00001-of-00004.safetensors", "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00004.safetensors", "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00004.safetensors", "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00004.safetensors", "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00004.safetensors", "transformer.h.11.attn.c_attn.bias": "model-00001-of-00004.safetensors", "transformer.h.11.attn.c_attn.weight": "model-00001-of-00004.safetensors", "transformer.h.11.attn.c_proj.bias": "model-00001-of-00004.safetensors", "transformer.h.11.attn.c_proj.weight": "model-00001-of-00004.safetensors", "transformer.h.11.ln_1.bias": "model-00001-of-00004.safetensors", "transformer.h.11.ln_1.weight": "model-00001-of-00004.safetensors", "transformer.h.11.ln_2.bias": "model-00001-of-00004.safetensors", "transformer.h.11.ln_2.weight": "model-00001-of-00004.safetensors", "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00004.safetensors", "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00004.safetensors", "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00004.safetensors", "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00004.safetensors", "transformer.h.12.attn.c_attn.bias": "model-00001-of-00004.safetensors", "transformer.h.12.attn.c_attn.weight": "model-00001-of-00004.safetensors", "transformer.h.12.attn.c_proj.bias": "model-00001-of-00004.safetensors", "transformer.h.12.attn.c_proj.weight": "model-00001-of-00004.safetensors", "transformer.h.12.ln_1.bias": "model-00001-of-00004.safetensors", "transformer.h.12.ln_1.weight": "model-00001-of-00004.safetensors", "transformer.h.12.ln_2.bias": "model-00001-of-00004.safetensors", "transformer.h.12.ln_2.weight": "model-00001-of-00004.safetensors", "transformer.h.12.mlp.c_fc.bias": "model-00001-of-00004.safetensors", "transformer.h.12.mlp.c_fc.weight": "model-00001-of-00004.safetensors", "transformer.h.12.mlp.c_proj.bias": "model-00001-of-00004.safetensors", "transformer.h.12.mlp.c_proj.weight": "model-00001-of-00004.safetensors", "transformer.h.13.attn.c_attn.bias": "model-00001-of-00004.safetensors", "transformer.h.13.attn.c_attn.weight": "model-00001-of-00004.safetensors", "transformer.h.13.attn.c_proj.bias": "model-00001-of-00004.safetensors", "transformer.h.13.attn.c_proj.weight": "model-00001-of-00004.safetensors", "transformer.h.13.ln_1.bias": "model-00001-of-00004.safetensors", "transformer.h.13.ln_1.weight": "model-00001-of-00004.safetensors", "transformer.h.13.ln_2.bias": "model-00001-of-00004.safetensors", "transformer.h.13.ln_2.weight": "model-00001-of-00004.safetensors", "transformer.h.13.mlp.c_fc.bias": "model-00001-of-00004.safetensors", "transformer.h.13.mlp.c_fc.weight": "model-00001-of-00004.safetensors", "transformer.h.13.mlp.c_proj.bias": "model-00001-of-00004.safetensors", "transformer.h.13.mlp.c_proj.weight": "model-00001-of-00004.safetensors", "transformer.h.14.attn.c_attn.bias": "model-00001-of-00004.safetensors", "transformer.h.14.attn.c_attn.weight": "model-00001-of-00004.safetensors", "transformer.h.14.attn.c_proj.bias": "model-00001-of-00004.safetensors", "transformer.h.14.attn.c_proj.weight": "model-00001-of-00004.safetensors", "transformer.h.14.ln_1.bias": "model-00001-of-00004.safetensors", "transformer.h.14.ln_1.weight": "model-00001-of-00004.safetensors", "transformer.h.14.ln_2.bias": "model-00001-of-00004.safetensors", "transformer.h.14.ln_2.weight": "model-00001-of-00004.safetensors", "transformer.h.14.mlp.c_fc.bias": "model-00001-of-00004.safetensors", "transformer.h.14.mlp.c_fc.weight": "model-00001-of-00004.safetensors", "transformer.h.14.mlp.c_proj.bias": "model-00001-of-00004.safetensors", "transformer.h.14.mlp.c_proj.weight": "model-00001-of-00004.safetensors", "transformer.h.15.attn.c_attn.bias": "model-00001-of-00004.safetensors", "transformer.h.15.attn.c_attn.weight": "model-00001-of-00004.safetensors", "transformer.h.15.attn.c_proj.bias": "model-00001-of-00004.safetensors", "transformer.h.15.attn.c_proj.weight": "model-00001-of-00004.safetensors", "transformer.h.15.ln_1.bias": "model-00001-of-00004.safetensors", "transformer.h.15.ln_1.weight": "model-00001-of-00004.safetensors", "transformer.h.15.ln_2.bias": "model-00001-of-00004.safetensors", "transformer.h.15.ln_2.weight": "model-00001-of-00004.safetensors", "transformer.h.15.mlp.c_fc.bias": "model-00001-of-00004.safetensors", "transformer.h.15.mlp.c_fc.weight": "model-00001-of-00004.safetensors", "transformer.h.15.mlp.c_proj.bias": "model-00001-of-00004.safetensors", "transformer.h.15.mlp.c_proj.weight": "model-00002-of-00004.safetensors", "transformer.h.16.attn.c_attn.bias": "model-00002-of-00004.safetensors", "transformer.h.16.attn.c_attn.weight": "model-00002-of-00004.safetensors", "transformer.h.16.attn.c_proj.bias": "model-00002-of-00004.safetensors", "transformer.h.16.attn.c_proj.weight": "model-00002-of-00004.safetensors", "transformer.h.16.ln_1.bias": "model-00002-of-00004.safetensors", "transformer.h.16.ln_1.weight": "model-00002-of-00004.safetensors", "transformer.h.16.ln_2.bias": "model-00002-of-00004.safetensors", "transformer.h.16.ln_2.weight": "model-00002-of-00004.safetensors", "transformer.h.16.mlp.c_fc.bias": "model-00002-of-00004.safetensors", "transformer.h.16.mlp.c_fc.weight": "model-00002-of-00004.safetensors", "transformer.h.16.mlp.c_proj.bias": "model-00002-of-00004.safetensors", "transformer.h.16.mlp.c_proj.weight": "model-00002-of-00004.safetensors", "transformer.h.17.attn.c_attn.bias": "model-00002-of-00004.safetensors", "transformer.h.17.attn.c_attn.weight": "model-00002-of-00004.safetensors", "transformer.h.17.attn.c_proj.bias": "model-00002-of-00004.safetensors", "transformer.h.17.attn.c_proj.weight": "model-00002-of-00004.safetensors", "transformer.h.17.ln_1.bias": "model-00002-of-00004.safetensors", "transformer.h.17.ln_1.weight": "model-00002-of-00004.safetensors", "transformer.h.17.ln_2.bias": "model-00002-of-00004.safetensors", "transformer.h.17.ln_2.weight": "model-00002-of-00004.safetensors", "transformer.h.17.mlp.c_fc.bias": "model-00002-of-00004.safetensors", "transformer.h.17.mlp.c_fc.weight": "model-00002-of-00004.safetensors", "transformer.h.17.mlp.c_proj.bias": "model-00002-of-00004.safetensors", "transformer.h.17.mlp.c_proj.weight": "model-00002-of-00004.safetensors", "transformer.h.18.attn.c_attn.bias": "model-00002-of-00004.safetensors", "transformer.h.18.attn.c_attn.weight": "model-00002-of-00004.safetensors", "transformer.h.18.attn.c_proj.bias": "model-00002-of-00004.safetensors", "transformer.h.18.attn.c_proj.weight": "model-00002-of-00004.safetensors", "transformer.h.18.ln_1.bias": "model-00002-of-00004.safetensors", "transformer.h.18.ln_1.weight": "model-00002-of-00004.safetensors", "transformer.h.18.ln_2.bias": "model-00002-of-00004.safetensors", "transformer.h.18.ln_2.weight": "model-00002-of-00004.safetensors", "transformer.h.18.mlp.c_fc.bias": "model-00002-of-00004.safetensors", "transformer.h.18.mlp.c_fc.weight": "model-00002-of-00004.safetensors", "transformer.h.18.mlp.c_proj.bias": "model-00002-of-00004.safetensors", "transformer.h.18.mlp.c_proj.weight": "model-00002-of-00004.safetensors", "transformer.h.19.attn.c_attn.bias": "model-00002-of-00004.safetensors", "transformer.h.19.attn.c_attn.weight": "model-00002-of-00004.safetensors", "transformer.h.19.attn.c_proj.bias": "model-00002-of-00004.safetensors", "transformer.h.19.attn.c_proj.weight": "model-00002-of-00004.safetensors", "transformer.h.19.ln_1.bias": "model-00002-of-00004.safetensors", "transformer.h.19.ln_1.weight": "model-00002-of-00004.safetensors", "transformer.h.19.ln_2.bias": "model-00002-of-00004.safetensors", "transformer.h.19.ln_2.weight": "model-00002-of-00004.safetensors", "transformer.h.19.mlp.c_fc.bias": "model-00002-of-00004.safetensors", "transformer.h.19.mlp.c_fc.weight": "model-00002-of-00004.safetensors", "transformer.h.19.mlp.c_proj.bias": "model-00002-of-00004.safetensors", "transformer.h.19.mlp.c_proj.weight": "model-00002-of-00004.safetensors", "transformer.h.2.attn.c_attn.bias": "model-00002-of-00004.safetensors", "transformer.h.2.attn.c_attn.weight": "model-00002-of-00004.safetensors", "transformer.h.2.attn.c_proj.bias": "model-00002-of-00004.safetensors", "transformer.h.2.attn.c_proj.weight": "model-00002-of-00004.safetensors", "transformer.h.2.ln_1.bias": "model-00002-of-00004.safetensors", "transformer.h.2.ln_1.weight": "model-00002-of-00004.safetensors", "transformer.h.2.ln_2.bias": "model-00002-of-00004.safetensors", "transformer.h.2.ln_2.weight": "model-00002-of-00004.safetensors", "transformer.h.2.mlp.c_fc.bias": "model-00002-of-00004.safetensors", "transformer.h.2.mlp.c_fc.weight": "model-00002-of-00004.safetensors", "transformer.h.2.mlp.c_proj.bias": "model-00002-of-00004.safetensors", "transformer.h.2.mlp.c_proj.weight": "model-00002-of-00004.safetensors", "transformer.h.20.attn.c_attn.bias": "model-00002-of-00004.safetensors", "transformer.h.20.attn.c_attn.weight": "model-00002-of-00004.safetensors", "transformer.h.20.attn.c_proj.bias": "model-00002-of-00004.safetensors", "transformer.h.20.attn.c_proj.weight": "model-00002-of-00004.safetensors", "transformer.h.20.ln_1.bias": "model-00002-of-00004.safetensors", "transformer.h.20.ln_1.weight": "model-00002-of-00004.safetensors", "transformer.h.20.ln_2.bias": "model-00002-of-00004.safetensors", "transformer.h.20.ln_2.weight": "model-00002-of-00004.safetensors", "transformer.h.20.mlp.c_fc.bias": "model-00002-of-00004.safetensors", "transformer.h.20.mlp.c_fc.weight": "model-00002-of-00004.safetensors", "transformer.h.20.mlp.c_proj.bias": "model-00002-of-00004.safetensors", "transformer.h.20.mlp.c_proj.weight": "model-00002-of-00004.safetensors", "transformer.h.21.attn.c_attn.bias": "model-00002-of-00004.safetensors", "transformer.h.21.attn.c_attn.weight": "model-00002-of-00004.safetensors", "transformer.h.21.attn.c_proj.bias": "model-00002-of-00004.safetensors", "transformer.h.21.attn.c_proj.weight": "model-00002-of-00004.safetensors", "transformer.h.21.ln_1.bias": "model-00002-of-00004.safetensors", "transformer.h.21.ln_1.weight": "model-00002-of-00004.safetensors", "transformer.h.21.ln_2.bias": "model-00002-of-00004.safetensors", "transformer.h.21.ln_2.weight": "model-00002-of-00004.safetensors", "transformer.h.21.mlp.c_fc.bias": "model-00002-of-00004.safetensors", "transformer.h.21.mlp.c_fc.weight": "model-00002-of-00004.safetensors", "transformer.h.21.mlp.c_proj.bias": "model-00002-of-00004.safetensors", "transformer.h.21.mlp.c_proj.weight": "model-00002-of-00004.safetensors", "transformer.h.22.attn.c_attn.bias": "model-00002-of-00004.safetensors", "transformer.h.22.attn.c_attn.weight": "model-00002-of-00004.safetensors", "transformer.h.22.attn.c_proj.bias": "model-00002-of-00004.safetensors", "transformer.h.22.attn.c_proj.weight": "model-00002-of-00004.safetensors", "transformer.h.22.ln_1.bias": "model-00002-of-00004.safetensors", "transformer.h.22.ln_1.weight": "model-00002-of-00004.safetensors", "transformer.h.22.ln_2.bias": "model-00002-of-00004.safetensors", "transformer.h.22.ln_2.weight": "model-00002-of-00004.safetensors", "transformer.h.22.mlp.c_fc.bias": "model-00002-of-00004.safetensors", "transformer.h.22.mlp.c_fc.weight": "model-00003-of-00004.safetensors", "transformer.h.22.mlp.c_proj.bias": "model-00003-of-00004.safetensors", "transformer.h.22.mlp.c_proj.weight": "model-00003-of-00004.safetensors", "transformer.h.23.attn.c_attn.bias": "model-00003-of-00004.safetensors", "transformer.h.23.attn.c_attn.weight": "model-00003-of-00004.safetensors", "transformer.h.23.attn.c_proj.bias": "model-00003-of-00004.safetensors", "transformer.h.23.attn.c_proj.weight": "model-00003-of-00004.safetensors", "transformer.h.23.ln_1.bias": "model-00003-of-00004.safetensors", "transformer.h.23.ln_1.weight": "model-00003-of-00004.safetensors", "transformer.h.23.ln_2.bias": "model-00003-of-00004.safetensors", "transformer.h.23.ln_2.weight": "model-00003-of-00004.safetensors", "transformer.h.23.mlp.c_fc.bias": "model-00003-of-00004.safetensors", "transformer.h.23.mlp.c_fc.weight": "model-00003-of-00004.safetensors", "transformer.h.23.mlp.c_proj.bias": "model-00003-of-00004.safetensors", "transformer.h.23.mlp.c_proj.weight": "model-00003-of-00004.safetensors", "transformer.h.3.attn.c_attn.bias": "model-00003-of-00004.safetensors", "transformer.h.3.attn.c_attn.weight": "model-00003-of-00004.safetensors", "transformer.h.3.attn.c_proj.bias": "model-00003-of-00004.safetensors", "transformer.h.3.attn.c_proj.weight": "model-00003-of-00004.safetensors", "transformer.h.3.ln_1.bias": "model-00003-of-00004.safetensors", "transformer.h.3.ln_1.weight": "model-00003-of-00004.safetensors", "transformer.h.3.ln_2.bias": "model-00003-of-00004.safetensors", "transformer.h.3.ln_2.weight": "model-00003-of-00004.safetensors", "transformer.h.3.mlp.c_fc.bias": "model-00003-of-00004.safetensors", "transformer.h.3.mlp.c_fc.weight": "model-00003-of-00004.safetensors", "transformer.h.3.mlp.c_proj.bias": "model-00003-of-00004.safetensors", "transformer.h.3.mlp.c_proj.weight": "model-00003-of-00004.safetensors", "transformer.h.4.attn.c_attn.bias": "model-00003-of-00004.safetensors", "transformer.h.4.attn.c_attn.weight": "model-00003-of-00004.safetensors", "transformer.h.4.attn.c_proj.bias": "model-00003-of-00004.safetensors", "transformer.h.4.attn.c_proj.weight": "model-00003-of-00004.safetensors", "transformer.h.4.ln_1.bias": "model-00003-of-00004.safetensors", "transformer.h.4.ln_1.weight": "model-00003-of-00004.safetensors", "transformer.h.4.ln_2.bias": "model-00003-of-00004.safetensors", "transformer.h.4.ln_2.weight": "model-00003-of-00004.safetensors", "transformer.h.4.mlp.c_fc.bias": "model-00003-of-00004.safetensors", "transformer.h.4.mlp.c_fc.weight": "model-00003-of-00004.safetensors", "transformer.h.4.mlp.c_proj.bias": "model-00003-of-00004.safetensors", "transformer.h.4.mlp.c_proj.weight": "model-00003-of-00004.safetensors", "transformer.h.5.attn.c_attn.bias": "model-00003-of-00004.safetensors", "transformer.h.5.attn.c_attn.weight": "model-00003-of-00004.safetensors", "transformer.h.5.attn.c_proj.bias": "model-00003-of-00004.safetensors", "transformer.h.5.attn.c_proj.weight": "model-00003-of-00004.safetensors", "transformer.h.5.ln_1.bias": "model-00003-of-00004.safetensors", "transformer.h.5.ln_1.weight": "model-00003-of-00004.safetensors", "transformer.h.5.ln_2.bias": "model-00003-of-00004.safetensors", "transformer.h.5.ln_2.weight": "model-00003-of-00004.safetensors", "transformer.h.5.mlp.c_fc.bias": "model-00003-of-00004.safetensors", "transformer.h.5.mlp.c_fc.weight": "model-00003-of-00004.safetensors", "transformer.h.5.mlp.c_proj.bias": "model-00003-of-00004.safetensors", "transformer.h.5.mlp.c_proj.weight": "model-00003-of-00004.safetensors", "transformer.h.6.attn.c_attn.bias": "model-00003-of-00004.safetensors", "transformer.h.6.attn.c_attn.weight": "model-00003-of-00004.safetensors", "transformer.h.6.attn.c_proj.bias": "model-00003-of-00004.safetensors", "transformer.h.6.attn.c_proj.weight": "model-00003-of-00004.safetensors", "transformer.h.6.ln_1.bias": "model-00003-of-00004.safetensors", "transformer.h.6.ln_1.weight": "model-00003-of-00004.safetensors", "transformer.h.6.ln_2.bias": "model-00003-of-00004.safetensors", "transformer.h.6.ln_2.weight": "model-00003-of-00004.safetensors", "transformer.h.6.mlp.c_fc.bias": "model-00003-of-00004.safetensors", "transformer.h.6.mlp.c_fc.weight": "model-00003-of-00004.safetensors", "transformer.h.6.mlp.c_proj.bias": "model-00003-of-00004.safetensors", "transformer.h.6.mlp.c_proj.weight": "model-00003-of-00004.safetensors", "transformer.h.7.attn.c_attn.bias": "model-00003-of-00004.safetensors", "transformer.h.7.attn.c_attn.weight": "model-00003-of-00004.safetensors", "transformer.h.7.attn.c_proj.bias": "model-00003-of-00004.safetensors", "transformer.h.7.attn.c_proj.weight": "model-00003-of-00004.safetensors", "transformer.h.7.ln_1.bias": "model-00003-of-00004.safetensors", "transformer.h.7.ln_1.weight": "model-00003-of-00004.safetensors", "transformer.h.7.ln_2.bias": "model-00003-of-00004.safetensors", "transformer.h.7.ln_2.weight": "model-00003-of-00004.safetensors", "transformer.h.7.mlp.c_fc.bias": "model-00003-of-00004.safetensors", "transformer.h.7.mlp.c_fc.weight": "model-00003-of-00004.safetensors", "transformer.h.7.mlp.c_proj.bias": "model-00003-of-00004.safetensors", "transformer.h.7.mlp.c_proj.weight": "model-00003-of-00004.safetensors", "transformer.h.8.attn.c_attn.bias": "model-00003-of-00004.safetensors", "transformer.h.8.attn.c_attn.weight": "model-00003-of-00004.safetensors", "transformer.h.8.attn.c_proj.bias": "model-00003-of-00004.safetensors", "transformer.h.8.attn.c_proj.weight": "model-00003-of-00004.safetensors", "transformer.h.8.ln_1.bias": "model-00003-of-00004.safetensors", "transformer.h.8.ln_1.weight": "model-00003-of-00004.safetensors", "transformer.h.8.ln_2.bias": "model-00003-of-00004.safetensors", "transformer.h.8.ln_2.weight": "model-00003-of-00004.safetensors", "transformer.h.8.mlp.c_fc.bias": "model-00003-of-00004.safetensors", "transformer.h.8.mlp.c_fc.weight": "model-00003-of-00004.safetensors", "transformer.h.8.mlp.c_proj.bias": "model-00003-of-00004.safetensors", "transformer.h.8.mlp.c_proj.weight": "model-00003-of-00004.safetensors", "transformer.h.9.attn.c_attn.bias": "model-00003-of-00004.safetensors", "transformer.h.9.attn.c_attn.weight": "model-00004-of-00004.safetensors", "transformer.h.9.attn.c_proj.bias": "model-00004-of-00004.safetensors", "transformer.h.9.attn.c_proj.weight": "model-00004-of-00004.safetensors", "transformer.h.9.ln_1.bias": "model-00004-of-00004.safetensors", "transformer.h.9.ln_1.weight": "model-00004-of-00004.safetensors", "transformer.h.9.ln_2.bias": "model-00004-of-00004.safetensors", "transformer.h.9.ln_2.weight": "model-00004-of-00004.safetensors", "transformer.h.9.mlp.c_fc.bias": "model-00004-of-00004.safetensors", "transformer.h.9.mlp.c_fc.weight": "model-00004-of-00004.safetensors", "transformer.h.9.mlp.c_proj.bias": "model-00004-of-00004.safetensors", "transformer.h.9.mlp.c_proj.weight": "model-00004-of-00004.safetensors", "transformer.ln_f.bias": "model-00004-of-00004.safetensors", "transformer.ln_f.weight": "model-00004-of-00004.safetensors", "transformer.wpe.weight": "model-00004-of-00004.safetensors", "transformer.wte.weight": "model-00004-of-00004.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<cls>",
4
+ "eos_token": {
5
+ "content": "</s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "mask_token": "<mask>",
12
+ "pad_token": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "sep_token": "<sep>",
20
+ "unk_token": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ }
27
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c5c56a739832923347681ed8a03a9cbf5afb6d1fe60089a5b01dd2dd063ab71
3
+ size 1208648
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<unk>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<pad>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<sep>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<mask>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<cls>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ }
60
+ },
61
+ "additional_special_tokens": [],
62
+ "bos_token": "<s>",
63
+ "clean_up_tokenization_spaces": true,
64
+ "cls_token": "<cls>",
65
+ "do_lower_case": false,
66
+ "eos_token": "</s>",
67
+ "extra_ids": 0,
68
+ "keep_accents": true,
69
+ "legacy": true,
70
+ "mask_token": "<mask>",
71
+ "model_max_length": 1000000000000000019884624838656,
72
+ "pad_token": "<pad>",
73
+ "sep_token": "<sep>",
74
+ "sp_model_kwargs": {},
75
+ "tokenizer_class": "T5Tokenizer",
76
+ "unk_token": "<unk>"
77
+ }