Upload folder using huggingface_hub

README.md

@@ -0,0 +1,71 @@
+---
+base_model:
+- Qwen/Qwen2.5-7B-Instruct
+- Qwen/Qwen2.5-Math-7B-Instruct
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the NuSLERP merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)
+* [Qwen/Qwen2.5-Math-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+      - model: Qwen/Qwen2.5-7B-Instruct
+        layer_range: [0, 7]
+      - model: Qwen/Qwen2.5-Math-7B-Instruct
+        layer_range: [0, 7]
+    parameters:
+      weight: [0.85, 0.15]
+      nuslerp_flatten: false
+
+  - sources:
+      - model: Qwen/Qwen2.5-7B-Instruct
+        layer_range: [7, 14]
+      - model: Qwen/Qwen2.5-Math-7B-Instruct
+        layer_range: [7, 14]
+    parameters:
+      weight: [0.6, 0.4]
+      nuslerp_flatten: false
+
+  - sources:
+      - model: Qwen/Qwen2.5-7B-Instruct
+        layer_range: [14, 21]
+      - model: Qwen/Qwen2.5-Math-7B-Instruct
+        layer_range: [14, 21]
+    parameters:
+      weight: [0.4, 0.6]
+      nuslerp_flatten: false
+
+  - sources:
+      - model: Qwen/Qwen2.5-7B-Instruct
+        layer_range: [21, 28]
+      - model: Qwen/Qwen2.5-Math-7B-Instruct
+        layer_range: [21, 28]
+    parameters:
+      weight: [0.3, 0.7]
+      nuslerp_flatten: false
+
+merge_method: nuslerp
+dtype: float16
+
+```

config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "float16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "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": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

mergekit_config.yml

@@ -0,0 +1,39 @@
+slices:
+  - sources:
+      - model: Qwen/Qwen2.5-7B-Instruct
+        layer_range: [0, 7]
+      - model: Qwen/Qwen2.5-Math-7B-Instruct
+        layer_range: [0, 7]
+    parameters:
+      weight: [0.85, 0.15]
+      nuslerp_flatten: false
+
+  - sources:
+      - model: Qwen/Qwen2.5-7B-Instruct
+        layer_range: [7, 14]
+      - model: Qwen/Qwen2.5-Math-7B-Instruct
+        layer_range: [7, 14]
+    parameters:
+      weight: [0.6, 0.4]
+      nuslerp_flatten: false
+
+  - sources:
+      - model: Qwen/Qwen2.5-7B-Instruct
+        layer_range: [14, 21]
+      - model: Qwen/Qwen2.5-Math-7B-Instruct
+        layer_range: [14, 21]
+    parameters:
+      weight: [0.4, 0.6]
+      nuslerp_flatten: false
+
+  - sources:
+      - model: Qwen/Qwen2.5-7B-Instruct
+        layer_range: [21, 28]
+      - model: Qwen/Qwen2.5-Math-7B-Instruct
+        layer_range: [21, 28]
+    parameters:
+      weight: [0.3, 0.7]
+      nuslerp_flatten: false
+
+merge_method: nuslerp
+dtype: float16

model-00001-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ec96fdaaf35f201d95693f66f81e094a3f124f37f75aa7d62bd9a5893c6b601
+size 1089994880

model-00002-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31f22570a2a77b83f4ec58d404e33fd90c6fbaeb66ae2cbf3543cbc78248ecf1
+size 1089994888

model-00003-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40b370039ffc0fc07c0675264e7759dd013b0755024ae45deb443ee0b3e65ce4
+size 932241136

model-00004-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96e0660ee8d93d2691af3563a73e572f740bc279bc75d69889361a37aebb4569
+size 932233888

model-00005-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7755e03c0a79b4e3ee29af3ac0f2122e2ad045601e4b1925fe9ffcdf1607af79
+size 932233888

model-00006-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76d38d2005dc5ae568eceeebbee0acac79847b4caaa938a777b1091971039986
+size 932233888

model-00007-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3a282359cf65711987039fbcb870541cbecee5cdd95e75054ff2596014106c2
+size 932233888

model-00008-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:862749633d106101362efeaa0a1dcb853b789b182f37c81a83c0441d416677bc
+size 932233888

model-00009-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e74b3e07aaf566b9b701e1e4d611fb4e00228d844992b5e275d87061e119ee07
+size 932233880

model-00010-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23be913560d9be6b20f106b51ac55dacda1e9baee315d0931b08842d1eb0e8d5
+size 932233888

model-00011-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f090ba0968b8d43b75f09348161542940a83193c9b684b17ac309049ff209765
+size 932233888

model-00012-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:482ec5159d0fb0c0023d540c693bcbe5a9d36e0ca0159af54231672cb4b7d01d
+size 932233888

model-00013-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9c27648a78a962ff2b65bcb924a91b1d3a6906d4894d6970bb8072bc6d62fdc
+size 932233880

model-00014-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98b11f3f40ed992867b246a3a3aa41d9d535ef542c97b851af1ef49fddd7077c
+size 932233864

model-00015-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8138babe46230cfb4a7c89a9b80ca606464496894b73a0a4590b2eaecbaae7a
+size 932233864

model-00016-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcc732b0a1665dae2d9efb27365ff28d69617d7945e1b1008e78864e9fcb4bd3
+size 932233848

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.1.3"}, "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"}}

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\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\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|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": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}