Upload 10 files

README.md

@@ -1,3 +1,48 @@
 ---
-license: apache-2.0
+base_model:
+- Qwen/Qwen3-8B
+- deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
+library_name: transformers
+tags:
+- mergekit
+- merge
+
 ---
+# Qwen3-R1-SLERP-DST-8B
+
+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 [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B)
+* [deepseek-ai/DeepSeek-R1-0528-Qwen3-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
+        layer_range: [0, 36]
+      - model: Qwen/Qwen3-8B
+        layer_range: [0, 36]
+merge_method: slerp
+base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16
+
+```

config.json

@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "attn_factor": 0.8782488562869419,
+    "factor": 4.0,
+    "original_max_position_embeddings": 32768,
+    "rope_type": "yarn"
+  },
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

mergekit_config.yml

@@ -0,0 +1,16 @@
+slices:
+  - sources:
+      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
+        layer_range: [0, 36]
+      - model: Qwen/Qwen3-8B
+        layer_range: [0, 36]
+merge_method: slerp
+base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f81f111d906209231812503bd5066984e1ac83dde2d93ab650234381c09cea6
+size 4905356184

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04057653df2dfe2539dcca824396ac63fdbf9833c141c7496b2bbf4f336e44ca
+size 4915960368

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f479c712eef70a9193259c3027d1a248f333378271ddc507c126ab9f7101d51
+size 4974672184

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2310ab9e78bacc8c6e8259c2f9c04d3504e2eded57dd46421ef0668d2e6bea52
+size 1585528048

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.1.3"}, "weight_map": {"lm_head.weight": "model-00001-of-00004.safetensors", "model.embed_tokens.weight": "model-00001-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.2.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.35.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.35.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.6.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.norm.weight": "model-00004-of-00004.safetensors"}}

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": true,
+  "model_max_length": 131072,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sp_model_kwargs": {},
+  "unk_token": null,
+  "tokenizer_class": "LlamaTokenizerFast",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true, is_last_user=false) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '\n\n' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{ bos_token }}{{ ns.system_prompt }}{%- for message in messages %}{% set content = message['content'] %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{%- set ns.is_first = false -%}{%- set ns.is_last_user = true -%}{{'<｜User｜>' + content + '<｜Assistant｜>'}}{%- endif %}{%- if message['role'] == 'assistant' %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{% endif %}{%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{%- endif %}{%- set ns.is_first = false %}{%- set ns.is_tool = false -%}{%- set ns.is_output_first = true %}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if content is none %}{{'<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- else %}{{content + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- endif %}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- endif %}{%- endfor %}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none)%}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + content + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{{content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_last_user = false -%}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_last_user and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}"
+}