Upload folder using huggingface_hub

README.md

@@ -1,3 +1,41 @@
 ---
-license: mit
+base_model:
+- vilm/Quyen-mini-v0.1
+- Qwen/Qwen1.5-1.8B-Chat
+library_name: transformers
+tags:
+- mergekit
+- merge
+
 ---
+# mergedmodel
+
+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:
+* [vilm/Quyen-mini-v0.1](https://huggingface.co/vilm/Quyen-mini-v0.1)
+* [Qwen/Qwen1.5-1.8B-Chat](https://huggingface.co/Qwen/Qwen1.5-1.8B-Chat)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+    - model: Qwen/Qwen1.5-1.8B-Chat
+      layer_range: [0, 24]
+  - sources:
+    - model: vilm/Quyen-mini-v0.1
+      layer_range: [0, 24]
+merge_method: passthrough
+dtype: bfloat16
+
+```

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "vilm/Quyen-mini-v0.1",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "max_position_embeddings": 8192,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

mergekit_config.yml

@@ -0,0 +1,9 @@
+slices:
+  - sources:
+    - model: Qwen/Qwen1.5-1.8B-Chat
+      layer_range: [0, 24]
+  - sources:
+    - model: vilm/Quyen-mini-v0.1
+      layer_range: [0, 24]
+merge_method: passthrough
+dtype: bfloat16

model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7359a4e1befca22b75999994d37420e0bf9975ee6529f1592290d07d8b6f17a
+size 1856014944

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10c62748bea4653c1f8110dc7e399e5140cb02a7b721cd8f7ee7aaddf40db6f0
+size 1994173104

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0340c3430a992c7d10f31706f7eaabd50f23d5337459d97699e2b4bdef6f5a86
+size 1993247032

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b522d2fa9dfcf611f4929a8655c1998ed015417ce95e4fdd181496acb3a2a37
+size 1492966736

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d71347dce727d041fb0340562abf5a86cb23dae5b85f2681f7a2db0bf0bed8c
+size 622329992

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"lm_head.weight": "model-00001-of-00004.safetensors", "model.norm.weight": "model-00001-of-00004.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.47.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.46.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.45.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.44.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.43.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.42.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.41.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.40.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.39.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.38.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.37.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.36.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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_config.json

@@ -0,0 +1,43 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_end|>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}