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 +1,63 @@
+---
+base_model:
+- Qwen/Qwen2.5-Math-7B
+- Qwen/Qwen2.5-7B
+tags:
+- merge
+- mergekit
+- lazymergekit
+- Qwen/Qwen2.5-Math-7B
+- Qwen/Qwen2.5-7B
+---
+
+# Double-Down-Qwen-Math-7B
+
+Double-Down-Qwen-Math-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [Qwen/Qwen2.5-Math-7B](https://huggingface.co/Qwen/Qwen2.5-Math-7B)
+* [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: Qwen/Qwen2.5-Math-7B
+        layer_range: [0, 28]
+      - model: Qwen/Qwen2.5-7B
+        layer_range: [0, 28]
+merge_method: slerp
+base_model: Qwen/Qwen2.5-Math-7B
+parameters:
+  t:
+    - filter: self_attn
+      value: [1, 0.5, 0.7, 0.7, 1]
+    - filter: mlp
+      value: [0, 0.5, 0.3, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "HeraiHench/Double-Down-Qwen-Math-7B"
+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 +1,30 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-Math-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 4096,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.0",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: Qwen/Qwen2.5-Math-7B
+        layer_range: [0, 28]
+      - model: Qwen/Qwen2.5-7B
+        layer_range: [0, 28]
+merge_method: slerp
+base_model: Qwen/Qwen2.5-Math-7B
+parameters:
+  t:
+    - filter: self_attn
+      value: [1, 0.5, 0.7, 0.7, 1]
+    - filter: mlp
+      value: [0, 0.5, 0.3, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16

model-00001-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4b102e03327fcd46b625a66d67e3cbdf66a232285e17254cd9541d5c4231c3
+size 1089994880

model-00002-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:942b4528c9e1c4fec950a4eb9baa7ed20977bc10ac5c1bdc52010c88c0699132
+size 1089994896

model-00003-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:376cf6becf6fbf0cc5bf05729acfb1dcd26cbd87dccb49b635bf9af83a4638a1
+size 932241160

model-00004-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3db155cf90823ded458c8363cb4bdf11d1d6ce5ac9d4ce749510fec42e9ca85f
+size 932233912

model-00005-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0a6d590d53701de70c56f397f58a676ff5d682a5c2a979c3a9498fe55edfa85
+size 932233912

model-00006-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7129ed08680670d9f84029e9a5ed049a077519856a83e1d10f034384f3e2c76
+size 932233912

model-00007-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c272db3156ed8e11037ce71c3f296dcd1bb5e3ecb58ce26bb0c4800444014e97
+size 932233912

model-00008-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ce651073cf53ca1f02fad5946d6603c76660490034762fff7e49d09b5cca431
+size 932233912

model-00009-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:915aba8987d2c679a826b5a3aabcef4f03ec9593d95fcc43d0754f7199ee6b95
+size 932233904

model-00010-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63ce1d362c554af0100a57415749a6b30f5c765ee1b5b18094ab4cca0408a1c3
+size 932233912

model-00011-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c02486b9222b1e021bd6b1905b289f9794360e98127a6c0172cf55b87deff6f8
+size 932233912

model-00012-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f55026e0d6bade7bcae498f0af5b317842bf6adfc5f2db9af1c9d196b5f2f773
+size 932233912

model-00013-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4b946cf46e83f785f323d5bcfcc3eec88b6317811a06ea5eb9465ae62663203
+size 932233904

model-00014-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dc49232e01f238322a4a6258a0b25a58b7758f095dcc19c64b2317b2370ee9b
+size 932233888

model-00015-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aa6cc5b39f6826b497a3445e49ce0b2ffd0957d68a33bc36c9d2b0851e26484
+size 932233888

model-00016-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b925b47ac8e6f0684ebf94ea05d9f0fa34639f42543dab6a7e72a4ec5517981
+size 932233872

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.6", "total_size": 15231233024}, "weight_map": {"lm_head.weight": "model-00001-of-00016.safetensors", "model.embed_tokens.weight": "model-00002-of-00016.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00003-of-00016.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00003-of-00016.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00003-of-00016.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00003-of-00016.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00003-of-00016.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00003-of-00016.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00004-of-00016.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00004-of-00016.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00004-of-00016.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00016.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00016.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00016.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00005-of-00016.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00005-of-00016.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00005-of-00016.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00005-of-00016.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00005-of-00016.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00005-of-00016.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00006-of-00016.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00006-of-00016.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00006-of-00016.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00006-of-00016.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00006-of-00016.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00006-of-00016.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00007-of-00016.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00007-of-00016.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00007-of-00016.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.17.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00007-of-00016.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00007-of-00016.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00007-of-00016.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.19.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00008-of-00016.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00008-of-00016.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00008-of-00016.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.2.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00009-of-00016.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00009-of-00016.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00009-of-00016.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.20.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00009-of-00016.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00009-of-00016.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00009-of-00016.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.21.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00010-of-00016.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00010-of-00016.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00010-of-00016.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.22.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00010-of-00016.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00010-of-00016.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00010-of-00016.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.23.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00011-of-00016.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00011-of-00016.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00011-of-00016.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.24.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00011-of-00016.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00011-of-00016.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00011-of-00016.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.25.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00012-of-00016.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00012-of-00016.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00012-of-00016.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.26.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00012-of-00016.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00012-of-00016.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00012-of-00016.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.27.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00013-of-00016.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00013-of-00016.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00013-of-00016.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.3.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00013-of-00016.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00013-of-00016.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00013-of-00016.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00014-of-00016.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00014-of-00016.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00014-of-00016.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.5.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00014-of-00016.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00014-of-00016.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00014-of-00016.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.6.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.8.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.input_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.norm.weight": "model-00016-of-00016.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "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|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}