Upload folder using huggingface_hub

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,54 @@
+---
+base_model:
+- psmathur/orca_mini_v3_13b
+- garage-bAInd/Platypus2-13B
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge
+
+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 merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [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
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+
+slices:
+  - sources:
+      - model: psmathur/orca_mini_v3_13b
+        layer_range: [0, 40]
+      - model: garage-bAInd/Platypus2-13B
+        layer_range: [0, 40]
+# or, the equivalent models: syntax:
+# models:
+#   - model: psmathur/orca_mini_v3_13b
+#   - model: garage-bAInd/Platypus2-13B
+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 # fallback for rest of tensors
+dtype: float16
+
+
+```

.ipynb_checkpoints/mergekit_config-checkpoint.yml

@@ -0,0 +1,22 @@
+
+slices:
+  - sources:
+      - model: psmathur/orca_mini_v3_13b
+        layer_range: [0, 40]
+      - model: garage-bAInd/Platypus2-13B
+        layer_range: [0, 40]
+# or, the equivalent models: syntax:
+# models:
+#   - model: psmathur/orca_mini_v3_13b
+#   - model: garage-bAInd/Platypus2-13B
+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 # fallback for rest of tensors
+dtype: float16
+

README.md

@@ -0,0 +1,41 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- psmathur/orca_mini_v3_13b
+- garage-bAInd/Platypus2-13B
+---
+
+# orca-platypus-13B-slerp
+
+orca-platypus-13B-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, 40]
+      - model: garage-bAInd/Platypus2-13B
+        layer_range: [0, 40]
+# or, the equivalent models: syntax:
+# models:
+#   - model: psmathur/orca_mini_v3_13b
+#   - model: garage-bAInd/Platypus2-13B
+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 # fallback for rest of tensors
+dtype: float16
+
+```

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "psmathur/orca_mini_v3_13b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "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": "float16",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,22 @@
+
+slices:
+  - sources:
+      - model: psmathur/orca_mini_v3_13b
+        layer_range: [0, 40]
+      - model: garage-bAInd/Platypus2-13B
+        layer_range: [0, 40]
+# or, the equivalent models: syntax:
+# models:
+#   - model: psmathur/orca_mini_v3_13b
+#   - model: garage-bAInd/Platypus2-13B
+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 # fallback for rest of tensors
+dtype: float16
+

model-00001-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9188a216947c899739d63403a5ac7d73517dc9a27135751cb5f6f34f5ad50246
+size 938486320

model-00002-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d74a1319b9a2cf3f11ce9fac03dff9b0fce7f837f4738b6810580dafa1be368e
+size 985704240

model-00003-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9da84784a24adf6068a0dc7f4334d1debef3fe551c9bdd6418bacaebeeea13d4
+size 917525768

model-00004-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1501d1038b0e64d50b8cd66b9e0113d6d108bc014047877836d290ccae0c491
+size 985704256

model-00005-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f225329747063652ee71aea3f0939049de1943fddbe40e36c6690551a29dfcb
+size 917525768

model-00006-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b6d6f1fbf7d3bf1ed2c3a9f8b4b41bd0278db7f54d14c8b9bdd275034b24506
+size 985704256

model-00007-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ccd24778d96b47640b98221bcbf921ac47b76465a9ebc7e6abe7d9edba43f9f
+size 917525768

model-00008-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b23c4ffcf89e9ee780c681274f9aea8530283b4affba9dbac05400caa0e86a2d
+size 985704256

model-00009-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efd00620068329a2bd7496e5b17af40c4116a024156c56d998c2f52d898de8a6
+size 917525760

model-00010-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1801ad30509b6a714e91cc38f067f94f86c74bc7170ba4b5a87463844cd7ca8
+size 985704248

model-00011-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cfa2ba7edec78be0efb49fd9e0f3a95d9e12c7a4e744f2ffe70f1a3128f014d
+size 917525768

model-00012-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb912cf3800fd88c5657704c20ecc7381c99fee150deb300fb28d979995b7803
+size 985704256

model-00013-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59c27ccc7ec93708dd4d66c1a15160efdfbb83eaeb6787aac252e8837aebe4e7
+size 917525768

model-00014-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dd181f5e197232ec0a62584b1ee7c8fe8c8e3c051675df538b46f19d945141b
+size 985704256

model-00015-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c79fd2556ed40b3bdfbdf1a635cd4ec3c09ed422b99a009adba86d6fb3f9abb8
+size 917525768

model-00016-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6925ba824e5e43a0a7d1a6379829d8499b78df61dfc6dcd149b9b9d468b2df89
+size 985704256

model-00017-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cb17302fa156e58092c6123f4478150cffaf12c25824012673952e78d43e7df
+size 917525760

model-00018-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fc5f2899d3bdb6b36e5f6560809342b8293bb215f503d5f7490804a53b59a3e
+size 985704256

model-00019-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a05f81a6e541f55908f05de96d6c903251002fcb8083c5b6ddb657d3b531a42
+size 917525768

model-00020-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:299c6d31ad3968fa2c984315c9949208f0d38e4499a9ea477d8accd1cf3f8672
+size 985704256

model-00021-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec461fcfb937414a80d14938763e8eda8abe1781d50fa8d97684d36c2cb67c76
+size 917525768

model-00022-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b11dae82ef1020d44dd8c307a30dd4f91db82189521609d1dbda28143c159ffd
+size 985704256

model-00023-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5604fa6040dd1210eb62562b33e6161d925d807408a6d9621639ce059c44e5ba
+size 917525768

model-00024-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57e0c6768a5c7313ea2e9b056818704d4c06dd7be28a8d5f3d48dce7252222ef
+size 985704248

model-00025-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9785d9f44adbcab51fb0e1724aef73f66ef8b2c8b10fe00bb9bba20e7284fcda
+size 917525752

model-00026-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c951fb4d67fe32c4b27354d631784b75bcc3bb5637a9a4780a23bf1bf40a7dce
+size 985704240

model-00027-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4433a8c52fdee63437c47fe92bd905740e6fbb2685f8aa853f2d52a0bd0a7a02
+size 917525752

model-00028-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ec326e36be6c1097d302c74efb95a697a14441a086e191bfb34f2f82b3268f6
+size 351294248

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.1", "total_size": 26031728640}, "weight_map": {"lm_head.weight": "model-00001-of-00028.safetensors", "model.embed_tokens.weight": "model-00001-of-00028.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00028.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00028.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00028.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00028.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00028.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00028.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00028.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00028.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00028.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00028.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00028.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00028.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00028.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00028.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00028.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00028.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00028.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00028.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00028.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00028.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00028.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00028.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00028.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00028.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00028.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00028.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00028.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00028.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00028.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00028.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00028.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00028.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00028.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00028.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00028.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00028.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00028.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00028.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00028.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00028.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00028.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00028.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00028.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00028.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00028.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00028.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00007-of-00028.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00028.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00007-of-00028.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00028.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00028.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00028.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00028.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00028.safetensors", "model.layers.17.input_layernorm.weight": "model-00007-of-00028.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00007-of-00028.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00028.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00008-of-00028.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00028.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00028.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00028.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00028.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00008-of-00028.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00028.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00008-of-00028.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00028.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00028.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00028.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00028.safetensors", "model.layers.19.input_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00009-of-00028.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00028.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00009-of-00028.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00028.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00028.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00028.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00028.safetensors", "model.layers.2.input_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00009-of-00028.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00009-of-00028.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00010-of-00028.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00010-of-00028.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00010-of-00028.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00010-of-00028.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.input_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00028.safetensors", "model.layers.21.input_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00011-of-00028.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00011-of-00028.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00011-of-00028.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00028.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00028.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00028.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00028.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00028.safetensors", "model.layers.22.input_layernorm.weight": "model-00011-of-00028.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00011-of-00028.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00028.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00012-of-00028.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00012-of-00028.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00028.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00028.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.input_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00028.safetensors", "model.layers.24.input_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00013-of-00028.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00013-of-00028.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00013-of-00028.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00013-of-00028.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00028.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00028.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00028.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00028.safetensors", "model.layers.25.input_layernorm.weight": "model-00013-of-00028.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00013-of-00028.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00013-of-00028.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00014-of-00028.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00014-of-00028.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00014-of-00028.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00014-of-00028.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00014-of-00028.safetensors", "model.layers.26.input_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00014-of-00028.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00014-of-00028.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00014-of-00028.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00014-of-00028.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00014-of-00028.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00014-of-00028.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00014-of-00028.safetensors", "model.layers.27.input_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00015-of-00028.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00015-of-00028.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00015-of-00028.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00015-of-00028.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00015-of-00028.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00015-of-00028.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00015-of-00028.safetensors", "model.layers.28.input_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00015-of-00028.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00015-of-00028.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00016-of-00028.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00016-of-00028.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00016-of-00028.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00016-of-00028.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00016-of-00028.safetensors", "model.layers.29.input_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00016-of-00028.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00016-of-00028.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00016-of-00028.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00016-of-00028.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00016-of-00028.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00016-of-00028.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00016-of-00028.safetensors", "model.layers.3.input_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00017-of-00028.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00017-of-00028.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00017-of-00028.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00017-of-00028.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00017-of-00028.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00017-of-00028.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00017-of-00028.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00017-of-00028.safetensors", "model.layers.30.input_layernorm.weight": "model-00017-of-00028.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00017-of-00028.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00017-of-00028.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00018-of-00028.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00018-of-00028.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00018-of-00028.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00028.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00018-of-00028.safetensors", "model.layers.31.input_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00018-of-00028.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00018-of-00028.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00018-of-00028.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00018-of-00028.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00018-of-00028.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00018-of-00028.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00018-of-00028.safetensors", "model.layers.32.input_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00019-of-00028.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00019-of-00028.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00019-of-00028.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00019-of-00028.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00019-of-00028.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00019-of-00028.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00019-of-00028.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00019-of-00028.safetensors", "model.layers.33.input_layernorm.weight": "model-00019-of-00028.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00019-of-00028.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00019-of-00028.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00020-of-00028.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00020-of-00028.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00020-of-00028.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00020-of-00028.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00020-of-00028.safetensors", "model.layers.34.input_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00020-of-00028.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00020-of-00028.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00020-of-00028.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00020-of-00028.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00020-of-00028.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00020-of-00028.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00020-of-00028.safetensors", "model.layers.35.input_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00021-of-00028.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00021-of-00028.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00021-of-00028.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00021-of-00028.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00021-of-00028.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00021-of-00028.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00021-of-00028.safetensors", "model.layers.36.input_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00021-of-00028.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00021-of-00028.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00022-of-00028.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00022-of-00028.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00022-of-00028.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00022-of-00028.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00022-of-00028.safetensors", "model.layers.37.input_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00022-of-00028.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00022-of-00028.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00022-of-00028.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00022-of-00028.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00022-of-00028.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00022-of-00028.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00022-of-00028.safetensors", "model.layers.38.input_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00023-of-00028.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00023-of-00028.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00023-of-00028.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00023-of-00028.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00023-of-00028.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00023-of-00028.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00023-of-00028.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00023-of-00028.safetensors", "model.layers.39.input_layernorm.weight": "model-00023-of-00028.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00023-of-00028.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00023-of-00028.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00024-of-00028.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00024-of-00028.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00024-of-00028.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00024-of-00028.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.input_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00024-of-00028.safetensors", "model.layers.5.input_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00025-of-00028.safetensors", "model.layers.6.input_layernorm.weight": "model-00025-of-00028.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00025-of-00028.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00025-of-00028.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.input_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00026-of-00028.safetensors", "model.layers.8.input_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00027-of-00028.safetensors", "model.layers.9.input_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00027-of-00028.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00027-of-00028.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00028-of-00028.safetensors", "model.norm.weight": "model-00028-of-00028.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 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}