Upload folder using huggingface_hub

README.md

@@ -0,0 +1,49 @@
+---
+base_model:
+- teknium/OpenHermes-2.5-Mistral-7B
+- Gryphe/MythoMist-7b
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merged_model
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B)
+* [Gryphe/MythoMist-7b](https://huggingface.co/Gryphe/MythoMist-7b)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+
+slices:
+  - sources:
+      - model: teknium/OpenHermes-2.5-Mistral-7B
+        layer_range: [0, 32]
+      - model: Gryphe/MythoMist-7b
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: teknium/OpenHermes-2.5-Mistral-7B
+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: float16
+
+```

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float16",
+  "eos_token_id": 32000,
+  "head_dim": null,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.2",
+  "use_cache": false,
+  "vocab_size": 32002
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: teknium/OpenHermes-2.5-Mistral-7B
+        layer_range: [0, 32]
+      - model: Gryphe/MythoMist-7b
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: teknium/OpenHermes-2.5-Mistral-7B
+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: float16

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5ad649e12e391613aade7916be4de72bf357a068308590109e8fbc52b34f323
+size 960521544

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:543df304258fce5682aa63581b802c9d43efc1b86a4ee1e449b567ba75b595e3
+size 989890704

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04ed801bb070c9362408c46ec57f0e1cf08a928d87196340c04db3010574566a
+size 989890712

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c6a0dccdac79133269023bbf1de9af604be0f01903c85e4a16daa7d477287f2
+size 998287736

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2877b2e7fa7952ba72a2544700d643363964bc5befe99e496c66979e2ee7946
+size 947956192

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92c3f70c08fe369abbdb25ab3d03d5dff79fbcf737abe4794b97bc283ab0a5d7
+size 989890704

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97d279e344c27b1203e0888804dc4b4ca1fb1674114f2240eabca8bc5098d777
+size 989890704

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bea161c85f54709dac24821ab83f58ab3c1418905f7b7924f8e4ccc33a1496ba
+size 998287736

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:875832531928a3246c85aa5f3d524666775f89f64aeab5ae1c650b8da8ef84e5
+size 947956192

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a64700bc0900ffb556ba7e00e63886771581471f7c8a53d76967b575415368bc
+size 989890712

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c930662279520f14b06a1f9424a5edf0c79db6f1bf889c6ce76711ce580fa899
+size 989890704

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13feb33a4b42e4c948b2aed0a199441278c2fda32837f248bbada1eea34f1f46
+size 998287736

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae208d1787522d86eab209a277d769258e24b3756ba85938c36a89d2c8af37a0
+size 947956176

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ece98e6d0ab84a924a4ffb9f99813e585d7001abf25e34ddd3c5cb677485a51
+size 989890688

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad87741a49de5fba47f6005493e6b8fb4c90225cc157252d032741b94fe8094c
+size 755009424

model.safetensors.index.json

@@ -0,0 +1,299 @@
+{
+  "metadata": {
+    "total_size": 14483464192,
+    "mergekit_version": "0.1.4"
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00015.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.norm.weight": "model-00015-of-00015.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "<|im_end|>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}