Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,58 @@
+---
+base_model:
+- newsbang/Homer-v1.0-Qwen2.5-7B
+- AIDC-AI/Marco-o1
+tags:
+- merge
+- mergekit
+- lazymergekit
+- newsbang/Homer-v1.0-Qwen2.5-7B
+- AIDC-AI/Marco-o1
+---
+
+# Llama3.2NextGen
+
+Llama3.2NextGen is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [newsbang/Homer-v1.0-Qwen2.5-7B](https://huggingface.co/newsbang/Homer-v1.0-Qwen2.5-7B)
+* [AIDC-AI/Marco-o1](https://huggingface.co/AIDC-AI/Marco-o1)
+
+## 🧩 Configuration
+
+```yaml
+
+slices:
+  - sources:
+    - model: newsbang/Homer-v1.0-Qwen2.5-7B
+      layer_range: [0, 12]
+  - sources:
+    - model: AIDC-AI/Marco-o1
+      layer_range: [8, 28]
+merge_method: passthrough
+tokenizer_source: union
+dtype: float16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "powermove72/Llama3.2NextGen"
+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 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "AIDC-AI/Marco-o1",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151665
+}

mergekit_config.yml

@@ -0,0 +1,12 @@
+
+
+slices:
+  - sources:
+    - model: newsbang/Homer-v1.0-Qwen2.5-7B
+      layer_range: [0, 12]
+  - sources:
+    - model: AIDC-AI/Marco-o1
+      layer_range: [8, 28]
+merge_method: passthrough
+tokenizer_source: union
+dtype: float16

model-00001-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89b4ccb9e15f39ffb88fc58b7ee9d29bae7735515ac96c52318b809ad6f7c382
+size 1087134848

model-00002-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75b4ef909ccb4d9a0e54599bf81c0378a4a87b34a825b5f4d64f4451c079e419
+size 1087134856

model-00003-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2044f8bcb14d8d395b96872c5c339921a8e8845cfceff779d05a0dc3a17df587
+size 932248408

model-00004-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cab7c89e33cd3fc1acd20d24ea7ca01e299d748b24d6b76042dabd7f484c3fc7
+size 932233888

model-00005-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0777d92db70ad905b34a31cb8293ec09587e5cd5f4bc9a01559a3fc33ed07ea7
+size 932226616

model-00006-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3be091f04b71cfec34da302fdcbd8cf16ea551863138841f11e7f70eb9013e33
+size 932233888

model-00007-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6acdcae2b754e3477ec4e00586a45f6e70ce5c7711e4da48d0a5f5af12f12a7d
+size 932233888

model-00008-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1d447885b0a5ced5c2c7cbc0203d81f33f12ca97d5d76b67f07b90fefd8b9a9
+size 932233888

model-00009-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90a124379be5fde196af664a7c3a62c57bfbd39c366d3f0f5d4d90df4ee0d26e
+size 932233880

model-00010-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46b2aea6893314e6f9861a88254453ed5648c600aad868a7f252d84f54da6734
+size 932233880

model-00011-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b95e2f9db55ca58190451a5ff0e3f073687e1ab542625551bf33551d362dd4e
+size 932233888

model-00012-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa9c0df63be4dd29152c6e9dba8e8724e390f85f1249fee0590f4aa67aad6ab4
+size 932233888

model-00013-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb136ea9400787392683a30d729d966a9fb223fe9595ff1cb47d58d1f4371d0c
+size 932233888

model-00014-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2158fea9bce3680ae67be7ea3a7d00412cfba30aeaaab78a9a81a1f72fa913e
+size 932233872

model-00015-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:287727d563e629acf168616a4848b5f4a5469af31d39346b44cdfe7037a58d3c
+size 932233864

model-00016-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26864c33724f1ddd31578d0d765c0e85fc1c532b305aa4fd2f5f13584d3a1cc3
+size 932241136

model-00017-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69c4e0d49a2aaaa38ed232cb52b6c73b7cfd91ada40d07838fa4939022d80599
+size 932233880

model-00018-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d035d12cc6ef8e98bc857919d487f3f47774160418284b60edad99999e3e0183
+size 932226584

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.2", "total_size": 17089975296}, "weight_map": {"lm_head.weight": "model-00001-of-00018.safetensors", "model.embed_tokens.weight": "model-00002-of-00018.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00018.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00018.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00018.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00003-of-00018.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00018.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00018.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00003-of-00018.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00018.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00003-of-00018.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00018.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00018.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00018.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00018.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00003-of-00018.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00018.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00018.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00003-of-00018.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00018.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00003-of-00018.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00018.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00018.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00018.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00018.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00018.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00018.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00018.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00018.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00004-of-00018.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00018.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00018.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00018.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00018.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00018.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00004-of-00018.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00018.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00018.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00018.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00004-of-00018.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00018.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00018.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00005-of-00018.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00005-of-00018.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00018.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00018.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00005-of-00018.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00005-of-00018.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00005-of-00018.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00005-of-00018.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00018.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00018.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00018.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00018.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00005-of-00018.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00005-of-00018.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00018.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00018.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00005-of-00018.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00005-of-00018.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00018.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00018.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00018.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00018.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00006-of-00018.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00006-of-00018.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00018.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00018.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00006-of-00018.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00018.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00006-of-00018.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00018.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00006-of-00018.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00018.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00006-of-00018.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00006-of-00018.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00018.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00018.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00006-of-00018.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00018.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00006-of-00018.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00018.safetensors", "model.layers.18.input_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00018.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00018.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00007-of-00018.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00007-of-00018.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00018.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00018.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00007-of-00018.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00018.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00007-of-00018.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00018.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00018.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00018.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00007-of-00018.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00007-of-00018.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00018.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00018.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00007-of-00018.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00018.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00007-of-00018.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00018.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00008-of-00018.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00018.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00008-of-00018.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00008-of-00018.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00018.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00018.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00008-of-00018.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00018.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00008-of-00018.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00018.safetensors", "model.layers.21.input_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00008-of-00018.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00018.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00008-of-00018.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00008-of-00018.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00018.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00018.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00008-of-00018.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00018.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00008-of-00018.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00018.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00009-of-00018.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00018.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00009-of-00018.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00009-of-00018.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00018.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00018.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00009-of-00018.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00018.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00009-of-00018.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00018.safetensors", "model.layers.23.input_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00009-of-00018.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00018.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00009-of-00018.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00009-of-00018.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00018.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00018.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00009-of-00018.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00018.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00009-of-00018.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00018.safetensors", "model.layers.2.input_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00010-of-00018.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00010-of-00018.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00010-of-00018.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00010-of-00018.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00010-of-00018.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00010-of-00018.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00010-of-00018.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00010-of-00018.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00010-of-00018.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00010-of-00018.safetensors", "model.layers.24.input_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00010-of-00018.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00018.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00010-of-00018.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00010-of-00018.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00018.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00018.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00010-of-00018.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00018.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00010-of-00018.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00018.safetensors", "model.layers.25.input_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00011-of-00018.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00011-of-00018.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00011-of-00018.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00011-of-00018.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00011-of-00018.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00011-of-00018.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00011-of-00018.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00011-of-00018.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00011-of-00018.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00011-of-00018.safetensors", "model.layers.26.input_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00011-of-00018.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00011-of-00018.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00011-of-00018.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00011-of-00018.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00018.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00018.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00011-of-00018.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00018.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00011-of-00018.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00018.safetensors", "model.layers.27.input_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00012-of-00018.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00012-of-00018.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00012-of-00018.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00012-of-00018.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00018.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00018.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00012-of-00018.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00018.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00012-of-00018.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00018.safetensors", "model.layers.28.input_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00012-of-00018.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00012-of-00018.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00012-of-00018.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00012-of-00018.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00012-of-00018.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00012-of-00018.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00012-of-00018.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00018.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00012-of-00018.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00012-of-00018.safetensors", "model.layers.29.input_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00013-of-00018.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00013-of-00018.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00013-of-00018.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00013-of-00018.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00013-of-00018.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00018.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00013-of-00018.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00013-of-00018.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00013-of-00018.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00013-of-00018.safetensors", "model.layers.30.input_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00013-of-00018.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00013-of-00018.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00013-of-00018.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00013-of-00018.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00018.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00013-of-00018.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00013-of-00018.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00013-of-00018.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00013-of-00018.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00013-of-00018.safetensors", "model.layers.31.input_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00014-of-00018.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00014-of-00018.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00014-of-00018.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00014-of-00018.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00014-of-00018.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00014-of-00018.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00014-of-00018.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00018.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00014-of-00018.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00014-of-00018.safetensors", "model.layers.3.input_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00014-of-00018.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00014-of-00018.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00014-of-00018.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00014-of-00018.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00014-of-00018.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00014-of-00018.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00014-of-00018.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00014-of-00018.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00014-of-00018.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00014-of-00018.safetensors", "model.layers.4.input_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00015-of-00018.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00015-of-00018.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00015-of-00018.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00015-of-00018.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00015-of-00018.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00015-of-00018.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00015-of-00018.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00015-of-00018.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00015-of-00018.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00015-of-00018.safetensors", "model.layers.5.input_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00015-of-00018.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00015-of-00018.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00015-of-00018.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00015-of-00018.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00015-of-00018.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00015-of-00018.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00015-of-00018.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00015-of-00018.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00015-of-00018.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00015-of-00018.safetensors", "model.layers.6.input_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00016-of-00018.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00016-of-00018.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00016-of-00018.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00016-of-00018.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00016-of-00018.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00016-of-00018.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00016-of-00018.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00016-of-00018.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00016-of-00018.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00016-of-00018.safetensors", "model.layers.7.input_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00016-of-00018.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00016-of-00018.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00016-of-00018.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00016-of-00018.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00016-of-00018.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00016-of-00018.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00016-of-00018.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00016-of-00018.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00016-of-00018.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00016-of-00018.safetensors", "model.layers.12.input_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.8.input_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00017-of-00018.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00017-of-00018.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00017-of-00018.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00017-of-00018.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00017-of-00018.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00017-of-00018.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00017-of-00018.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00017-of-00018.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00017-of-00018.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00017-of-00018.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00017-of-00018.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00017-of-00018.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00017-of-00018.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00017-of-00018.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.13.input_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.9.input_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00018-of-00018.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00018-of-00018.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00018-of-00018.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00018-of-00018.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00018-of-00018.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00018-of-00018.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00018-of-00018.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00018-of-00018.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00018-of-00018.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00018-of-00018.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00018-of-00018.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00018-of-00018.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00018-of-00018.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00018-of-00018.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00018-of-00018.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00018-of-00018.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00018-of-00018.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00018-of-00018.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.norm.weight": "model-00018-of-00018.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83396048d512ec1f3178af0d7c1f79a226bba041822614b0e26a4fd2d4b55bf7
+size 11421995

tokenizer_config.json

@@ -0,0 +1,199 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\n\n你是一个经过良好训练的AI助手，你的名字是Marco-o1.由阿里国际数字商业集团的AI Business创造.\n        \n## 重要！！！！！\n当你回答问题时，你的思考应该在<Thought>内完成，<Output>内输出你的结果。\n<Thought>应该尽可能是英文，但是有2个特例，一个是对原文中的引用，另一个是是数学应该使用markdown格式，<Output>内的输出需要遵循用户输入的语言。\n        <|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "max_length": 4096,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": null
+}