Upload folder using huggingface_hub

README.md

@@ -0,0 +1,63 @@
+---
+base_model:
+- aipib/llmjp-slerp
+- aipib/llmjp-slerp3
+tags:
+- merge
+- mergekit
+- lazymergekit
+- aipib/llmjp-slerp
+- aipib/llmjp-slerp3
+---
+
+# llmjp-slerp5
+
+llmjp-slerp5 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [aipib/llmjp-slerp](https://huggingface.co/aipib/llmjp-slerp)
+* [aipib/llmjp-slerp3](https://huggingface.co/aipib/llmjp-slerp3)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: aipib/llmjp-slerp
+        layer_range: [0, 24]
+      - model: aipib/llmjp-slerp3
+        layer_range: [0, 24]
+merge_method: slerp
+base_model: aipib/llmjp-slerp3
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "aipib/llmjp-slerp5"
+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"])
+```

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "aipib/llmjp-slerp3",
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 7,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 7,
+  "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": 2048,
+  "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": 50688
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: aipib/llmjp-slerp
+        layer_range: [0, 24]
+      - model: aipib/llmjp-slerp3
+        layer_range: [0, 24]
+merge_method: slerp
+base_model: aipib/llmjp-slerp3
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48e921611dd938a0b7f1f13f2d6db7541c828dfe870f22d0ef11e7e02342078c
+size 973623440

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81781470214e0d8e67ad440be191d8f8df9cf9d95e46991c77f74ddef99e433e
+size 973619232

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:155331a32b051fad43f7fb962ddc1c2914c9d287b40fc577fbd70fa75e9676ce
+size 685999688

model.safetensors.index.json

@@ -0,0 +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

@@ -0,0 +1,54 @@
+{
+  "additional_special_tokens": [
+    "</s|LLM-jp>"
+  ],
+  "bos_token": {
+    "content": "<s|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<CLS|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<EOD|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<SEP|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,84 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<mask|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<pad|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<CLS|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<SEP|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOD|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "</s|LLM-jp>"
+  ],
+  "bos_token": "<s|LLM-jp>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<CLS|LLM-jp>",
+  "eod_token": "<EOD|LLM-jp>",
+  "eos_token": "<EOD|LLM-jp>",
+  "extra_ids": 0,
+  "mask_token": "<mask|LLM-jp>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad|LLM-jp>",
+  "sep_token": "<SEP|LLM-jp>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk|LLM-jp>"
+}