Upload folder using huggingface_hub

README.md

@@ -0,0 +1,37 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- psmathur/orca_mini_v3_13b
+- garage-bAInd/Platypus2-13B
+---
+
+# ainao-7B-slerp
+
+ainao-7B-slerp is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [psmathur/orca_mini_v3_13b](https://huggingface.co/psmathur/orca_mini_v3_13b)
+* [garage-bAInd/Platypus2-13B](https://huggingface.co/garage-bAInd/Platypus2-13B)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: psmathur/orca_mini_v3_13b
+        layer_range: [0, 32]
+      - model: garage-bAInd/Platypus2-13B
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: psmathur/orca_mini_v3_13b
+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": "psmathur/orca_mini_v3_13b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,18 @@
+
+slices:
+  - sources:
+      - model: psmathur/orca_mini_v3_13b
+        layer_range: [0, 32]
+      - model: garage-bAInd/Platypus2-13B
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: psmathur/orca_mini_v3_13b
+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-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b41fdc6318764c03ab0203939caad78a2cbd66243bef77e24797c932cf7bdf7
+size 1955648616

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6682b541c1d5a5b6d07b6443b5df60ca4887b0d974a63f3b825ab7b545c8a42c
+size 1955669296

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:024a369d7d01daf0fd50c157f95188680480a2603d1931feeab6230ebd57565c
+size 1903230008

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21f305884233cf17a2965386dbd6c1c96019bc7a45947063d05f964f48c490b3
+size 1903230008

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9442000f23609071c910449cb3f452bd6bb5faf75fea774dc388bcdcec2e3e6
+size 1903230008

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3821d79d647c6d6997eabc319bbefc823b3906ac3da5ad4bf7955417c49b771
+size 1984463376

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e2ae50c9283500ff4c4ee1002b1c836317fc90b5052dc29695520226b1b20b5
+size 1955658968

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:239bd534e270cc1ebe9b36c06e0b4a153879fbd9542e0ea69c0fdc4c2b85826a
+size 1955669304

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8be449b98d724bf633d45464601df349f75675f52fd48b7dfe860a9d0bfde83d
+size 1903230032

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07796758f4d9e58d553bd62bc3c33b4ae1d3dd81db96efd5e2e8a5719b41f4ec
+size 1903230032

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:493029fac02ffd2cb08d5143e9d5aadb6f8ef6bf9a6915b4d9eacae0af03da43
+size 1633231208

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.embed_tokens.weight": "model-00006-of-00011.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00011-of-00011.safetensors", "lm_head.weight": "model-00011-of-00011.safetensors", "model.norm.weight": "model-00011-of-00011.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00011-of-00011.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "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 +1,37 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 4096,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}