Upload folder using huggingface_hub

README.md

@@ -0,0 +1,49 @@
+---
+base_model:
+- IlyaGusev/saiga_mistral_7b_merged
+- ResplendentAI/Aura_v3_7B
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merged
+
+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:
+* [IlyaGusev/saiga_mistral_7b_merged](https://huggingface.co/IlyaGusev/saiga_mistral_7b_merged)
+* [ResplendentAI/Aura_v3_7B](https://huggingface.co/ResplendentAI/Aura_v3_7B)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+      - model: ResplendentAI/Aura_v3_7B
+        layer_range: [0, 32]
+      - model: IlyaGusev/saiga_mistral_7b_merged
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: ResplendentAI/Aura_v3_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: bfloat16
+tokenizer_source: union
+
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "ResplendentAI/Aura_v3_7B",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "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,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.3",
+  "use_cache": true,
+  "vocab_size": 32002
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+slices:
+  - sources:
+      - model: ResplendentAI/Aura_v3_7B
+        layer_range: [0, 32]
+      - model: IlyaGusev/saiga_mistral_7b_merged
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: ResplendentAI/Aura_v3_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: bfloat16
+tokenizer_source: union

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d16685dad684dc3074ad753917265603b2da919a7d9cb77cd68d34f7eb3e843
+size 960554320

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:312ae11711ae1c01c008126f58d6891b06fb130ce07e9aa4a79582d7888cbe0f
+size 989890720

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:def3b1d3b76449aa10d0b90c08a35222cf7f4b2a2e0492fc6384c83e8eddaf5f
+size 989890728

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6027ebdf938ed4574748103997f1f250aa1eccb8798042146f87d09eb97be4ca
+size 998287760

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b1ea82785622e8cff14a01b7a22cc7962c255fb737b2114efcfdd46a8bbcc94
+size 947956216

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd8f27984b71cf40419ee47efc0fbdbc342ac12695a1413921efc5e3e55c2003
+size 989890728

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed22f5cf4393e0007eb3b3afab239f4dbb9e3629c215012e5dd8088367662b5
+size 989890720

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:476a124be75ff8a220c957cd845c6895facc125493e91586a32810ad86e8d140
+size 998287760

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d090cc795f5acf364dba71c61be645fd88a394c78600f2250084a0c58890c50
+size 947956216

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b49329a3149d1f9bfa3c475265fadd86242eedac63075b442e5a77ed99e79f8
+size 989890728

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75c975bf9bcebab5dea98af429fdf72420b9ced56f1ecadc457ac76104bcc463
+size 989890728

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9fd6f87e8eee7f5f81885acd47b22f746e05a18e724715113c4ef29ad5fce6b
+size 998287752

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:281aa2a199c82b652d23d466bac69e8243a90e687c210332bf0a4217593ecdde
+size 947956200

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe5780baf23ead8e6fc74628ef577ebec53ec32844bc245f32777efed53aea1b
+size 989890712

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7903a400de629dafb3ae59c89e8399e3e7461f8d6caf1782a60d729450a39ec
+size 755009440

model.safetensors.index.json

@@ -0,0 +1,299 @@
+{
+  "metadata": {
+    "total_size": 14483496960,
+    "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 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": true,
+      "normalized": true,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "max_length": 16384,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}