Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,36 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- google/gemma-7b-it
+- HuggingFaceH4/zephyr-7b-gemma-v0.1
+---
+
+# gemma-7b-it-zaphyr-slerp
+
+gemma-7b-it-zaphyr-slerp is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [google/gemma-7b-it](https://huggingface.co/google/gemma-7b-it)
+* [HuggingFaceH4/zephyr-7b-gemma-v0.1](https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-v0.1)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: google/gemma-7b-it
+        layer_range: [0, 28]
+      - model: HuggingFaceH4/zephyr-7b-gemma-v0.1
+        layer_range: [0, 28]
+merge_method: slerp
+base_model: google/gemma-7b-it
+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 +1,28 @@
+{
+  "_name_or_path": "google/gemma-7b-it",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 256000
+}

mergekit_config.yml

@@ -0,0 +1,18 @@
+
+slices:
+  - sources:
+      - model: google/gemma-7b-it
+        layer_range: [0, 28]
+      - model: HuggingFaceH4/zephyr-7b-gemma-v0.1
+        layer_range: [0, 28]
+merge_method: slerp
+base_model: google/gemma-7b-it
+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-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50fb1e4df2f8c67f964fe66a399d752cae48882f99d62542ef320cb4633d3a3c
+size 1912643208

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11f384aaa6852f7160d5fff6b33cbec55c0d35f3ef98bd38a874d65f79829728
+size 1509989312

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cc6e4719102de23843a011d922f5bc49e3c0f68673d5ba24c49fc117c0ac663
+size 1975518032

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:608ba7dffc3e8a8cd775a43b776cab081002327b69ac2668bc7be6ea54f37bb0
+size 1912655752

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57d74b90cd5b458ef0df3bd7b134861b9cf23d8732973ff719cfb065acf463c4
+size 1962974504

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b4a82cf3456dbdf4344f8911548e6e6f3afdd5d4519d366cf4e982e38fbfa73
+size 1912655736

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6f9104fb1226b3f2839bb81237ee989c349b8794866375fc0f98c7c26b28938
+size 1962974528

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:770ea84d1da850971c597b296c4c4dcd69d6861c0d531f153c58c0a2a3d71796
+size 1962993272

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8d4854a501dedacf8dec0c18040c526e5ab78637d98c1ac35d3e60be4a5d367
+size 1962987040

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.embed_tokens.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.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-00004-of-00009.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-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-00005-of-00009.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00005-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-00006-of-00009.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.6.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.16.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.15.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.norm.weight": "model-00008-of-00009.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.26.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.25.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.input_layernorm.weight": "model-00009-of-00009.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05e97791a5e007260de1db7e1692e53150e08cea481e2bf25435553380c147ee
+size 17477929

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}