Upload folder using huggingface_hub (#2)

- 27aa4b577b0aec4cb8f628c2ad2f38843650aa369e2cd83d977a3a45ddd81405 (83729b6fc9276e299843ef5bfeca26dd2a79089d)
- 8a04f4a41f525df9e0c6aae347eb33a05036fd8f6986f2be4130fc059160ff2b (7ba3032a2581840e92d38e848b9d11457bdd3f79)
- 3f317971efd18a32bc4e83e545d4378124e3076369c03ddc9ebaf0e0fc88a1bc (3b21b3d552df218046466b024656cd337ae096f8)
- 393a3e87c69af8270cecd7b6dfff7569d7aad36a85675c54d4aaf1ca8af4c408 (dca812ede75005ff03c25c4103c9d867c627cd4b)
- 13dc5a80f87db6937e283b483e1f426a26d723d7ec3fc42a8afbd71f0279fd8e (29c91249761b27ea6011b8e7212b629e3c89eb00)
- 6a615a65b6efac57797a93c6a33e6df415435b1aa17bea39cefe412ed5cafd40 (47b59eef9ccb75b2a1b9a83ee8fc91c3db5e965a)

README.md

@@ -0,0 +1,52 @@
+---
+license: apache-2.0
+language:
+- en
+- ja
+programming_language:
+- C
+- C++
+- C#
+- Go
+- Java
+- JavaScript
+- Lua
+- PHP
+- Python
+- Ruby
+- Rust
+- Scala
+- TypeScript
+pipeline_tag: text-generation
+library_name: transformers
+inference: false
+tags:
+- mlx
+base_model: llm-jp/llm-jp-3-13b
+---
+
+# niryuu/llm-jp-3-13b-instruct-test
+
+The Model [niryuu/llm-jp-3-13b-instruct-test](https://huggingface.co/niryuu/llm-jp-3-13b-instruct-test) was converted to MLX format from [llm-jp/llm-jp-3-13b](https://huggingface.co/llm-jp/llm-jp-3-13b) using mlx-lm version **0.19.3**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("niryuu/llm-jp-3-13b-instruct-test")
+
+prompt="hello"
+
+if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, tokenize=False, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

config.json

@@ -0,0 +1,28 @@
+{
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 13824,
+    "max_position_embeddings": 4096,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 40,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 40,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 10000,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.43.3",
+    "use_cache": true,
+    "vocab_size": 99584
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12ca415f296c29ea9677cde29dbcadf972a03283103b36f27e896ce54a4a8910
+size 5319031636

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:545cab67bb16e86190b92609bb0ecc1d1d204bd4dcbe3a1840ce87fb6cea3b45
+size 5321716410

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ea0b8f3a1b5503463c3373a5b4d4ca85ef0f5b5bc11d71cb20150d07994859e
+size 5321695725

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fa5c98c4d520095524eabe6dd9ce0f07c18ede923b619050fe3ca3239c1d32b
+size 5358416471

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa3006212409b1df2e69e3e5b239f49bcd1b04d0d85d22ff7a492d3182703759
+size 5075290340

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e36ce2988e7a0530d3d972ac35b5f8f1809546ee5844b3c9abd8d14ca0a11f33
+size 1019740285

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+    "metadata": {
+        "total_size": 27415848960
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00006-of-00006.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+        "model.norm.weight": "model-00005-of-00006.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "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": "</s>",
+    "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>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,84 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "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": "<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
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<CLS|LLM-jp>",
+  "eod_token": "</s>",
+  "eos_token": "</s>",
+  "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>"
+}