Upload folder using huggingface_hub

README.md

@@ -0,0 +1,68 @@
+---
+base_model:
+- oshizo/qa-refine-japanese-gpt-1b
+- rinna/japanese-gpt-1b
+tags:
+- merge
+- mergekit
+- lazymergekit
+- oshizo/qa-refine-japanese-gpt-1b
+- rinna/japanese-gpt-1b
+---
+
+# jp-gpt-ab-dareties2
+
+jp-gpt-ab-dareties2 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [oshizo/qa-refine-japanese-gpt-1b](https://huggingface.co/oshizo/qa-refine-japanese-gpt-1b)
+* [rinna/japanese-gpt-1b](https://huggingface.co/rinna/japanese-gpt-1b)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+- sources:
+  - layer_range: [0, 24]
+    model: oshizo/qa-refine-japanese-gpt-1b
+    parameters:
+      density: [1, 0.7, 0.1]
+      weight: 1.0
+  - layer_range: [0, 24]
+    model: rinna/japanese-gpt-1b
+    parameters:
+      density: 0.33
+      weight:
+        - filter: mlp
+          value: 0.5
+        - value: 0
+merge_method: dare_ties
+base_model: rinna/japanese-gpt-1b
+parameters:
+  normalize: true
+  int8_mask: true
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "aipib/jp-gpt-ab-dareties2"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>": 44876
+}

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "rinna/japanese-gpt-1b",
+  "activation_function": "gelu_fast",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 2,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 3,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 2048,
+  "n_head": 16,
+  "n_inner": 8192,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 44928
+}

mergekit_config.yml

@@ -0,0 +1,22 @@
+
+slices:
+- sources:
+  - layer_range: [0, 24]
+    model: oshizo/qa-refine-japanese-gpt-1b
+    parameters:
+      density: [1, 0.7, 0.1]
+      weight: 1.0
+  - layer_range: [0, 24]
+    model: rinna/japanese-gpt-1b
+    parameters:
+      density: 0.33
+      weight:
+        - filter: mlp
+          value: 0.5
+        - value: 0
+merge_method: dare_ties
+base_model: rinna/japanese-gpt-1b
+parameters:
+  normalize: true
+  int8_mask: true
+dtype: bfloat16

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e5490d76025b3b0fb461246515e98b530260d863d560c988bd7c1a41c32df8d
+size 973623440

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a5f661c1cf67ccf43fd76ecba1542eea3493f047f5badb11ccfba701f39d950
+size 973619232

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d6f6f7434d6c6af30ea71b693f4f38dadefde2894b7dff2c664b5b20855a5db
+size 658212424

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 2605424640}, "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

@@ -0,0 +1,27 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "[CLS]",
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": "[MASK]",
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dbbd4ddbe43941051ed35fd44ff0d9d1c00ed345f7fd4d1969df174110f0609
+size 1044749

tokenizer_config.json

@@ -0,0 +1,76 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "44876": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "legacy": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}