Upload folder using huggingface_hub

README.md

@@ -0,0 +1,133 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- arcee-ai/Patent-Instruct-7b
+- TencentARC/LLaMA-Pro-8B-Instruct
+- arcee-ai/Patent-Instruct-7b
+- TencentARC/LLaMA-Pro-8B-Instruct
+- arcee-ai/Patent-Instruct-7b
+- TencentARC/LLaMA-Pro-8B-Instruct
+- arcee-ai/Patent-Instruct-7b
+- TencentARC/LLaMA-Pro-8B-Instruct
+- arcee-ai/Patent-Instruct-7b
+- TencentARC/LLaMA-Pro-8B-Instruct
+- arcee-ai/Patent-Instruct-7b
+- TencentARC/LLaMA-Pro-8B-Instruct
+- arcee-ai/Patent-Instruct-7b
+- TencentARC/LLaMA-Pro-8B-Instruct
+- arcee-ai/Patent-Instruct-7b
+- TencentARC/LLaMA-Pro-8B-Instruct
+---
+
+# Patent-Instruct-LLaMA-Pro
+
+Patent-Instruct-LLaMA-Pro is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [arcee-ai/Patent-Instruct-7b](https://huggingface.co/arcee-ai/Patent-Instruct-7b)
+* [TencentARC/LLaMA-Pro-8B-Instruct](https://huggingface.co/TencentARC/LLaMA-Pro-8B-Instruct)
+* [arcee-ai/Patent-Instruct-7b](https://huggingface.co/arcee-ai/Patent-Instruct-7b)
+* [TencentARC/LLaMA-Pro-8B-Instruct](https://huggingface.co/TencentARC/LLaMA-Pro-8B-Instruct)
+* [arcee-ai/Patent-Instruct-7b](https://huggingface.co/arcee-ai/Patent-Instruct-7b)
+* [TencentARC/LLaMA-Pro-8B-Instruct](https://huggingface.co/TencentARC/LLaMA-Pro-8B-Instruct)
+* [arcee-ai/Patent-Instruct-7b](https://huggingface.co/arcee-ai/Patent-Instruct-7b)
+* [TencentARC/LLaMA-Pro-8B-Instruct](https://huggingface.co/TencentARC/LLaMA-Pro-8B-Instruct)
+* [arcee-ai/Patent-Instruct-7b](https://huggingface.co/arcee-ai/Patent-Instruct-7b)
+* [TencentARC/LLaMA-Pro-8B-Instruct](https://huggingface.co/TencentARC/LLaMA-Pro-8B-Instruct)
+* [arcee-ai/Patent-Instruct-7b](https://huggingface.co/arcee-ai/Patent-Instruct-7b)
+* [TencentARC/LLaMA-Pro-8B-Instruct](https://huggingface.co/TencentARC/LLaMA-Pro-8B-Instruct)
+* [arcee-ai/Patent-Instruct-7b](https://huggingface.co/arcee-ai/Patent-Instruct-7b)
+* [TencentARC/LLaMA-Pro-8B-Instruct](https://huggingface.co/TencentARC/LLaMA-Pro-8B-Instruct)
+* [arcee-ai/Patent-Instruct-7b](https://huggingface.co/arcee-ai/Patent-Instruct-7b)
+* [TencentARC/LLaMA-Pro-8B-Instruct](https://huggingface.co/TencentARC/LLaMA-Pro-8B-Instruct)
+
+## 🧩 Configuration
+
+```yaml
+  merge_method: passthrough
+  dtype: bfloat16
+  slices:
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b 
+        layer_range:
+          - 0
+          - 4
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 4
+          - 5
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b
+        layer_range:
+          - 4
+          - 8
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 9
+          - 10
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b
+        layer_range:
+          - 8
+          - 12
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 14
+          - 15
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b
+        layer_range:
+          - 12
+          - 16
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 19
+          - 20
+  - sources:
+       - model: arcee-ai/Patent-Instruct-7b
+         layer_range:
+          - 16
+          - 20
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 24
+          - 25
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b
+        layer_range:
+          - 20
+          - 24
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 29
+          - 30
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b
+        layer_range:
+          - 24
+          - 28
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 34
+          - 35
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b
+        layer_range:
+          - 28
+          - 32
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 39
+          - 40
+
+
+
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "TencentARC/LLaMA-Pro-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,87 @@
+
+  merge_method: passthrough
+  dtype: bfloat16
+  slices:
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b 
+        layer_range:
+          - 0
+          - 4
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 4
+          - 5
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b
+        layer_range:
+          - 4
+          - 8
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 9
+          - 10
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b
+        layer_range:
+          - 8
+          - 12
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 14
+          - 15
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b
+        layer_range:
+          - 12
+          - 16
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 19
+          - 20
+  - sources:
+       - model: arcee-ai/Patent-Instruct-7b
+         layer_range:
+          - 16
+          - 20
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 24
+          - 25
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b
+        layer_range:
+          - 20
+          - 24
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 29
+          - 30
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b
+        layer_range:
+          - 24
+          - 28
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 34
+          - 35
+  - sources:
+      - model: arcee-ai/Patent-Instruct-7b
+        layer_range:
+          - 28
+          - 32
+  - sources:
+      - model: TencentARC/LLaMA-Pro-8B-Instruct
+        layer_range:
+          - 39
+          - 40
+
+
+

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbcf050d35ed8cb768e565a1d9950e14f1fdbb96a962abab01feb7cef3a9a287
+size 1990275992

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbd35f778248c9c0fd17ac3da54451c41468ce10df3a8dbeb14825e524ff59ec
+size 1990284304

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d935b4a2c45f5d0c0478f44f0e60220f43ba91f0cf8d28351874cc562b1aa231
+size 1990284296

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3235ded8595246b452c99e9ff904f81a44ab65f91fb77a749c96ed3a44a79cd2
+size 1990284272

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c35e8f3e821a9ddf9e65ab16a3de28cf496dcb8399714e77f05bbc99ec2ab20
+size 1933652840

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77848cd8e459e4e1eab202d73e69c05eb127df81a46f40d577b66fdd5473173c
+size 1963012240

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceef8a865282991cce36667c1de95c4ebd890d8426cdde5043de108ee31b5a76
+size 1990275992

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57455238e0a7985329ce24194bb8d7de79711afdc19dcd210ccfe1279470d567
+size 1990284304

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:571bb477b6c949ea017352f85dcd559d868066adfb6e7829e1bea10da5b8bfc8
+size 876652928

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.28.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.7.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.6.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.5.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.4.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.3.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.1.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.0.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.embed_tokens.weight": "model-00006-of-00009.safetensors", "lm_head.weight": "model-00006-of-00009.safetensors", "model.norm.weight": "model-00006-of-00009.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.39.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.38.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.37.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.36.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.35.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.34.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.33.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.32.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.31.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.30.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00009.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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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 %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}