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 +1,118 @@
+---
+base_model:
+- Qwen/Qwen2.5-Coder-1.5B-Instruct
+- Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+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 passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [Qwen/Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct)
+* [Etherll/Qwen2.5-Coder-1.5B-CodeFIM](https://huggingface.co/Etherll/Qwen2.5-Coder-1.5B-CodeFIM)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+- sources:
+  - layer_range: [0, 1]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [1, 2]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+- sources:
+  - layer_range: [3, 3]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [3, 4]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+- sources:
+  - layer_range: [5, 5]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [5, 6]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+- sources:
+  - layer_range: [7, 7]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [7, 8]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+- sources:
+  - layer_range: [9, 9]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [9, 10]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+- sources:
+  - layer_range: [11, 11]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [11, 12]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+- sources:
+  - layer_range: [13, 13]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [13, 14]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+- sources:
+  - layer_range: [15, 15]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [15, 16]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+- sources:
+  - layer_range: [17, 17]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [17, 18]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+- sources:
+  - layer_range: [19, 19]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [19, 20]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+- sources:
+  - layer_range: [21, 21]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [21, 22]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+- sources:
+  - layer_range: [23, 23]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [23, 24]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+- sources:
+  - layer_range: [25, 25]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [25, 26]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+- sources:
+  - layer_range: [27, 27]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [27, 28]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+merge_method: passthrough
+dtype: bfloat16
+```

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": "Qwen/Qwen2.5-Coder-1.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 15,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

mergekit_config.yml

@@ -0,0 +1,87 @@
+slices:
+- sources:
+  - layer_range: [0, 1]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [1, 2]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+- sources:
+  - layer_range: [3, 3]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [3, 4]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+- sources:
+  - layer_range: [5, 5]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [5, 6]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+- sources:
+  - layer_range: [7, 7]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [7, 8]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+- sources:
+  - layer_range: [9, 9]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [9, 10]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+- sources:
+  - layer_range: [11, 11]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [11, 12]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+- sources:
+  - layer_range: [13, 13]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [13, 14]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+- sources:
+  - layer_range: [15, 15]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [15, 16]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+- sources:
+  - layer_range: [17, 17]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [17, 18]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+- sources:
+  - layer_range: [19, 19]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [19, 20]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+- sources:
+  - layer_range: [21, 21]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [21, 22]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+- sources:
+  - layer_range: [23, 23]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [23, 24]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+- sources:
+  - layer_range: [25, 25]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [25, 26]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+- sources:
+  - layer_range: [27, 27]
+    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+- sources:
+  - layer_range: [27, 28]
+    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
+merge_method: passthrough
+dtype: bfloat16

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cfd01e261689a59da15160038b76f1d79ec499e0fd5779b97c104e6834602d5
+size 466747520

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebf861bf15620cf39c490db8d93195d0895f81c0e1bd4176ec0b78081aecae3f
+size 494275944

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07e2d4a6af9e836b4b43ea692067b96e2ab4ab07006a76852ce63144e3bf2e75
+size 495510192

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3079abf961d50a479e2952b6d36c7c300afa2fbcd15010efa8648ff14ae1ada
+size 496300584

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4aecdab7d7729d66f1dea77d473373ace2e6c835f2c0f3155af073bf3dfb72b
+size 384618880

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 2337432576}, "weight_map": {"lm_head.weight": "model-00001-of-00005.safetensors", "model.embed_tokens.weight": "model-00002-of-00005.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00005.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00005.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00005.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00005.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00005.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00005.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.2.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00005-of-00005.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.3.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00005-of-00005.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.4.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00005-of-00005.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.5.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00005-of-00005.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.norm.weight": "model-00005-of-00005.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": "<|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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

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
+}