Upload folder using huggingface_hub

README.md

@@ -0,0 +1,52 @@
+---
+base_model:
+- mistralai/Mistral-Small-Instruct-2409
+- mistralai/Codestral-22B-v0.1
+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:
+* [mistralai/Mistral-Small-Instruct-2409](https://huggingface.co/mistralai/Mistral-Small-Instruct-2409)
+* [mistralai/Codestral-22B-v0.1](https://huggingface.co/mistralai/Codestral-22B-v0.1)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+      - model: mistralai/Mistral-Small-Instruct-2409
+        layer_range: [0, 40]
+      - model: mistralai/Codestral-22B-v0.1
+        layer_range: [0, 40]
+# or, the equivalent models: syntax:
+# models:
+#   - model: mistralai/Mistral-Small-Instruct-2409
+#   - model: mistralai/Codestral-22B-v0.1
+merge_method: slerp
+base_model: mistralai/Mistral-Small-Instruct-2409
+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 +1,27 @@
+{
+  "_name_or_path": "mistralai/Mistral-Small-Instruct-2409",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "vocab_size": 32768
+}

mergekit_config.yml

@@ -0,0 +1,20 @@
+slices:
+  - sources:
+      - model: mistralai/Mistral-Small-Instruct-2409
+        layer_range: [0, 40]
+      - model: mistralai/Codestral-22B-v0.1
+        layer_range: [0, 40]
+# or, the equivalent models: syntax:
+# models:
+#   - model: mistralai/Mistral-Small-Instruct-2409
+#   - model: mistralai/Codestral-22B-v0.1
+merge_method: slerp
+base_model: mistralai/Mistral-Small-Instruct-2409
+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-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7a86c43523c6e2406b8a76081e22f6c33c2741d028b65ea50555211fc479ccf
+size 805318992

model-00002-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92472e015635d25230617a098325c3974ea5aec735b46f55ea8c706f02c56f3c
+size 981492872

model-00003-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6c5501e286ae07f8a4273ca4783ca648378c12fde5fdb153774112383b58f2b
+size 981492880

model-00004-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1997019b7efd161bb613e069322469de8f8aba8847d2520f87836c01bd3dc4b0
+size 994088312

model-00005-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ec6abb39ad21e6c03c87bc28e5dd925f4d7665326acc78510a8ee401861cbbe
+size 943756776

model-00006-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c26c6d952d9156e3eaaf5740dc17e459a6d75e449fe36ef0ab6ea2dd645fd6e
+size 981492888

model-00007-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ad4ca8fe8599b449b7d6ed5f7c6768bede65c548bb6525bd86a82db24f7bd25
+size 981492888

model-00008-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bcf3662cea8b9904dbe27627063bfad20d4188dfed46c60554c0561bd836f90
+size 994088312

model-00009-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:371ecee134df8e65e8705a473f9832a31a7273c64ff0a49254ed5feb9b227a93
+size 943756776

model-00010-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:258a85f0ae01e0c57e1cbcdd522b2076c2be8b8f74dd6cb5537d18ff9926806b
+size 981492888

model-00011-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d031677fc6af51e0356e4568c541093ef3a59f33734285a21c94285800b795b
+size 981492880

model-00012-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:712a7ec82f8a379b2fd60f5321224b7884b11161157c627b539de8fb077e5e53
+size 994088312

model-00013-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb68c310ffe5a6abef2f14e753c91b081c1268bad30a98c7647801fd5676f34c
+size 943756776

model-00014-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd687fad4c9af449f1c082ba2bd5c093e5c7c260164f714eae499c8f5184a20b
+size 981492888

model-00015-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c56643ad6c346aad6314f9347284bb4f6613b9f24bdcf44747c1a5a1c79bd02d
+size 981492888

model-00016-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50c576cd7e11fe2caf8951cdfb611dd9651e3c683e37afd2986c481cd1a4a25e
+size 994088312

model-00017-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ed42eeffb19438e0d19feb9a02addce6d07368be5c82a3bbe17da27c9d30dc0
+size 943756776

model-00018-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d7254245d718a1cbf3495441ce4ca1d707f933ea689172a2cec64a0653b84c5
+size 981492888

model-00019-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d242d5bd6ecbc84b71fc77ed0715bb61e51d107a3c455418d132b4214f10f981
+size 981492888

model-00020-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2871b6302d47b9c4f29797339501801a8e6264a898d6293a7013167a0c2f4d38
+size 994088312

model-00021-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d392359339441cf5243ac01fa9a77a57c9719f8aff0407cfcf6b431bc7a9cead
+size 943756776

model-00022-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86f576ba9a2c1f047f5b9ec17e66a6c740c43e223afd100690b7554f73a13a84
+size 981492888

model-00023-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00e7138d96292b22d3256311aee4991a155bd79cd613cd3d661e30a6c257a4cc
+size 981492888

model-00024-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aefc2edbf897ce213e7e7ec068cf2861d3be8ad607fa744921247163b76a318c
+size 994088312

model-00025-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee2cde34db4ad773182c18571503550cee139cfcafc4691af36d36be90f53c87
+size 943756776

model-00026-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3cd1d07c148d1c6f29f55c9d5bc8b1a5cb067e575d026126c5ae46d0efc2bb0
+size 981492888

model-00027-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de6b4a674c8fa1f5289c7bd669f9d8244375a09abbb3caec648e52d5dbf9c70a
+size 981492888

model-00028-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44753bca7442d2a72b0f3d39da6619322f2fccadb227ed63a06c349d0aa2d361
+size 994088312

model-00029-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ede90ada0959976eb3ff444caeaac1c7be67808c49118a12176dc052f915fc50
+size 943756768

model-00030-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9afca46923ab6b18ff17a23622baf5d86667400ff415880b5f590f3fffc72657
+size 981492872

model-00031-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9549610c73d6bf7999d3b8e5836fc989c28ccf34fc1f2cf0eaeaddf8a17c9274
+size 981492872

model-00032-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddac3ab20868137b0f73fdd00d73f904298fc43cc6c1ce9b2daf091fb0ca4558
+size 994088304

model-00033-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73137a880378e9e8119ccf12d15f0d75c64756b881ea21f7fe518dae68fe7acb
+size 943756744

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.1", "total_size": 32011923456}, "weight_map": {"lm_head.weight": "model-00001-of-00033.safetensors", "model.embed_tokens.weight": "model-00001-of-00033.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00033.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00033.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00033.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00033.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00033.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00033.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00033.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00033.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00033.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00033.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00033.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00033.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00033.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00033.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00033.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00033.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00033.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00033.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00033.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00033.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00033.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00033.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00033.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00033.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00033.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00033.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00033.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00033.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00033.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00033.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00033.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00006-of-00033.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00033.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00006-of-00033.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00033.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00033.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00033.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00033.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00033.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00033.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00033.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00033.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00007-of-00033.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00033.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00033.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00033.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00033.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00033.safetensors", "model.layers.15.input_layernorm.weight": "model-00007-of-00033.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00007-of-00033.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00033.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00008-of-00033.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00033.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00033.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00033.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00033.safetensors", "model.layers.16.input_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00008-of-00033.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00033.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00008-of-00033.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00033.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00033.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00033.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00033.safetensors", "model.layers.17.input_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00009-of-00033.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00033.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00009-of-00033.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00033.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00033.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00033.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00033.safetensors", "model.layers.18.input_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00010-of-00033.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00033.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00010-of-00033.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00033.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00033.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00033.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00033.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00033.safetensors", "model.layers.19.input_layernorm.weight": "model-00010-of-00033.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00010-of-00033.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00011-of-00033.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00011-of-00033.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00033.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00033.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00033.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00033.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00011-of-00033.safetensors", "model.layers.2.input_layernorm.weight": "model-00011-of-00033.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00011-of-00033.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00011-of-00033.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00012-of-00033.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00012-of-00033.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00012-of-00033.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00012-of-00033.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00012-of-00033.safetensors", "model.layers.20.input_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00012-of-00033.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00012-of-00033.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00012-of-00033.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00033.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00033.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00013-of-00033.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00013-of-00033.safetensors", "model.layers.21.input_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00013-of-00033.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00013-of-00033.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00013-of-00033.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00033.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00033.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00033.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00033.safetensors", "model.layers.22.input_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00014-of-00033.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00014-of-00033.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00014-of-00033.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00033.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00014-of-00033.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00014-of-00033.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00033.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00014-of-00033.safetensors", "model.layers.23.input_layernorm.weight": "model-00014-of-00033.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00014-of-00033.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00015-of-00033.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00015-of-00033.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00033.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00015-of-00033.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00033.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00033.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00015-of-00033.safetensors", "model.layers.24.input_layernorm.weight": "model-00015-of-00033.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00015-of-00033.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00015-of-00033.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00016-of-00033.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00016-of-00033.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00016-of-00033.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00016-of-00033.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00016-of-00033.safetensors", "model.layers.25.input_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00016-of-00033.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00016-of-00033.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00016-of-00033.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00016-of-00033.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00017-of-00033.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00017-of-00033.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00017-of-00033.safetensors", "model.layers.26.input_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00017-of-00033.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00017-of-00033.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00017-of-00033.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00017-of-00033.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00017-of-00033.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00017-of-00033.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00017-of-00033.safetensors", "model.layers.27.input_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00018-of-00033.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00018-of-00033.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00018-of-00033.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00018-of-00033.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00018-of-00033.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00018-of-00033.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00018-of-00033.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00018-of-00033.safetensors", "model.layers.28.input_layernorm.weight": "model-00018-of-00033.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00018-of-00033.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00019-of-00033.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00019-of-00033.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00019-of-00033.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00019-of-00033.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00019-of-00033.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00019-of-00033.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00019-of-00033.safetensors", "model.layers.29.input_layernorm.weight": "model-00019-of-00033.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00019-of-00033.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00019-of-00033.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00020-of-00033.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00020-of-00033.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00020-of-00033.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00020-of-00033.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00020-of-00033.safetensors", "model.layers.3.input_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00020-of-00033.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00020-of-00033.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00020-of-00033.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00020-of-00033.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00021-of-00033.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00021-of-00033.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00021-of-00033.safetensors", "model.layers.30.input_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00021-of-00033.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00021-of-00033.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00021-of-00033.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00021-of-00033.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00021-of-00033.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00021-of-00033.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00021-of-00033.safetensors", "model.layers.31.input_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00022-of-00033.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00022-of-00033.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00022-of-00033.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00022-of-00033.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00022-of-00033.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00022-of-00033.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00022-of-00033.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00022-of-00033.safetensors", "model.layers.32.input_layernorm.weight": "model-00022-of-00033.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00022-of-00033.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00023-of-00033.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00023-of-00033.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00023-of-00033.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00023-of-00033.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00023-of-00033.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00023-of-00033.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00023-of-00033.safetensors", "model.layers.33.input_layernorm.weight": "model-00023-of-00033.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00023-of-00033.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00023-of-00033.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00024-of-00033.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00024-of-00033.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00024-of-00033.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00024-of-00033.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00024-of-00033.safetensors", "model.layers.34.input_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00024-of-00033.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00024-of-00033.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00024-of-00033.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00024-of-00033.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00025-of-00033.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00025-of-00033.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00025-of-00033.safetensors", "model.layers.35.input_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00025-of-00033.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00025-of-00033.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00025-of-00033.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00025-of-00033.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00025-of-00033.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00025-of-00033.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00025-of-00033.safetensors", "model.layers.36.input_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00026-of-00033.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00026-of-00033.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00026-of-00033.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00026-of-00033.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00026-of-00033.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00026-of-00033.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00026-of-00033.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00026-of-00033.safetensors", "model.layers.37.input_layernorm.weight": "model-00026-of-00033.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00026-of-00033.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00027-of-00033.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00027-of-00033.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00027-of-00033.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00027-of-00033.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00027-of-00033.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00027-of-00033.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00027-of-00033.safetensors", "model.layers.38.input_layernorm.weight": "model-00027-of-00033.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00027-of-00033.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00027-of-00033.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00028-of-00033.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00028-of-00033.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00028-of-00033.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00028-of-00033.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00028-of-00033.safetensors", "model.layers.39.input_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00028-of-00033.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00028-of-00033.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00028-of-00033.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00028-of-00033.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00029-of-00033.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00029-of-00033.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00029-of-00033.safetensors", "model.layers.4.input_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00029-of-00033.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00029-of-00033.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00029-of-00033.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00029-of-00033.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00029-of-00033.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00029-of-00033.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00029-of-00033.safetensors", "model.layers.5.input_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00030-of-00033.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00030-of-00033.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00030-of-00033.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00030-of-00033.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00030-of-00033.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00030-of-00033.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00030-of-00033.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00030-of-00033.safetensors", "model.layers.6.input_layernorm.weight": "model-00030-of-00033.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00030-of-00033.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00031-of-00033.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00031-of-00033.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00031-of-00033.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00031-of-00033.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00031-of-00033.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00031-of-00033.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00031-of-00033.safetensors", "model.layers.7.input_layernorm.weight": "model-00031-of-00033.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00031-of-00033.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00031-of-00033.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00032-of-00033.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00032-of-00033.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00032-of-00033.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00032-of-00033.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00032-of-00033.safetensors", "model.layers.8.input_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00032-of-00033.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00032-of-00033.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00032-of-00033.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00032-of-00033.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00033-of-00033.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00033-of-00033.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.input_layernorm.weight": "model-00033-of-00033.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00033-of-00033.safetensors", "model.norm.weight": "model-00033-of-00033.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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
+  },
+  "pad_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.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
+size 587583