Upload folder using huggingface_hub

README.md

@@ -0,0 +1,37 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- liminerity/1
+- liminerity/merge
+---
+
+# mm1Plus2-slerp-3b
+
+mm1Plus2-slerp-3b is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [liminerity/1](https://huggingface.co/liminerity/1)
+* [liminerity/merge](https://huggingface.co/liminerity/merge)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: liminerity/1
+        layer_range: [0, 40]
+      - model: liminerity/merge
+        layer_range: [0, 40]
+merge_method: slerp
+base_model: liminerity/1
+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 +1,31 @@
+{
+  "_name_or_path": "liminerity/1",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dim_model_base": 256,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2304,
+  "initializer_range": 0.1,
+  "intermediate_size": 5760,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 36,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 36,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "scale_depth": 1.4,
+  "scale_emb": 12,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": false,
+  "vocab_size": 122753
+}

mergekit_config.yml

@@ -0,0 +1,18 @@
+
+slices:
+  - sources:
+      - model: liminerity/1
+        layer_range: [0, 40]
+      - model: liminerity/merge
+        layer_range: [0, 40]
+merge_method: slerp
+base_model: liminerity/1
+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:df378786d083b2a8c310bf08e31dbf182c960a96971d0c5017317eb60362bcdb
+size 1985512032

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b00d3543cd89895eb5a688376578e960ca803b46b66e8199b453b9a21b59df4
+size 1980203320

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78a217f29d6230210d14129e534dc116fed399045fc88f59a03e97c01804f411
+size 1986023368

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1db7057009ad288b6e58e5d33ed94b67cf2190829d4e9e4bd9df71f5d42f18fd
+size 63710792

model.safetensors.index.json

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

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9aafcd7da1f5611dab6be545db74d5552a2ccc9c2a12c72ea7be63aac4a25d7
+size 1994871

tokenizer_config.json

@@ -0,0 +1,51 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{'<用户>' + message['content'].strip() + '<AI>'}}{% else %}{{message['content'].strip()}}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "</s>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}