Upload folder using huggingface_hub

README.md

@@ -0,0 +1,60 @@
+---
+base_model:
+- aws-prototyping/MegaBeam-Mistral-7B-512k
+- djuna-test-lab/TEST-Ocerus-7B
+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:
+* [aws-prototyping/MegaBeam-Mistral-7B-512k](https://huggingface.co/aws-prototyping/MegaBeam-Mistral-7B-512k)
+* [djuna-test-lab/TEST-Ocerus-7B](https://huggingface.co/djuna-test-lab/TEST-Ocerus-7B)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+      - model: djuna-test-lab/TEST-Ocerus-7B
+        layer_range: [0, 16]
+      - model: aws-prototyping/MegaBeam-Mistral-7B-512k
+        layer_range: [0, 16]
+    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: [0.6,0.35,0.5]
+  - sources:
+      - model: djuna-test-lab/TEST-Ocerus-7B
+        layer_range: [16, 32]
+      - model: aws-prototyping/MegaBeam-Mistral-7B-512k
+        layer_range: [16, 32]
+    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
+merge_method: slerp
+base_model: aws-prototyping/MegaBeam-Mistral-7B-512k
+dtype: float32
+out_dtype: bfloat16
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "aws-prototyping/MegaBeam-Mistral-7B-512k",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 524288,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 75000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,29 @@
+slices:
+  - sources:
+      - model: djuna-test-lab/TEST-Ocerus-7B
+        layer_range: [0, 16]
+      - model: aws-prototyping/MegaBeam-Mistral-7B-512k
+        layer_range: [0, 16]
+    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: [0.6,0.35,0.5]
+  - sources:
+      - model: djuna-test-lab/TEST-Ocerus-7B
+        layer_range: [16, 32]
+      - model: aws-prototyping/MegaBeam-Mistral-7B-512k
+        layer_range: [16, 32]
+    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
+merge_method: slerp
+base_model: aws-prototyping/MegaBeam-Mistral-7B-512k
+dtype: float32
+out_dtype: bfloat16

model-00001-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2b75b3ebf5c5a912e2b7b2c2c40d48a8d71c9dafefcddccfb42c40b9f579c35
+size 262144128

model-00002-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29e101e32e5700059d29bd0f6a1a4e0cee717aacaca76736c58253b956a2e0d3
+size 497033688

model-00003-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1b42da30912475ebfc67b647a36e743eff98773f95c1073e95a58b7bebce765
+size 436225056

model-00004-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54d14fad1c9e102d5bc6f72185b536c328a10f5094156ef56078e801c048603a
+size 436225064

model-00005-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:323c2310ec577c748152ce41db3349ce0982304959f0b1da39647cb692ba1434
+size 436225072

model-00006-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0543970026025b646284ce070153dcc9b471507638c5a54a227641a04f12f60
+size 436225072

model-00007-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:954e8063df515cfd2515939c0e3d554bb04a3e967b9f7f7e3a5edd7eb9cb4ad4
+size 436225072

model-00008-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1e47a93d275eb5284c75789154e69f6771ffe747dbcfb98a14f0717255bb375
+size 436225072

model-00009-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3013a26611145e9bb4708e3fe086f405f392bdb125d67b5a6da3b28c9d1fcf5
+size 436225072

model-00010-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:238594270ed47fafa7647b0c9e8fb57e941a965ac230b46923cbabb40c06fdcc
+size 436225072

model-00011-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:229d5015afd77d82388b03378fcf728cff06c71b38ef94c960c59efcd5a786e7
+size 436225072

model-00012-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f053bb9b6b50ceeb043219d94bb51e6a895ec3e7ac241cada0e1252cc94c274
+size 436225072

model-00013-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8900fde86629c8afef241a453f79545328834edd43f4c719d9aafcaeb8223e9e
+size 436225072

model-00014-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cce746adc9b01fabfe5cd5e992ce9392bce6d46ae7150cea3d23fbc068425f9e
+size 436225064

model-00015-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:267bccc37233922ae59c8acaf4abca758b849e3d39fcf1cb6c3afe391a823513
+size 436225064

model-00016-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b40d83d98ea813e9a6e175669b932d38dd12a8466f04247b696335269ef2154b
+size 436225072

model-00017-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ece7a871514ed2e477cb69b3ae6c7b00101822c79cd56dfdf7e1d3046710d731
+size 436225072

model-00018-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:945bd769c4fb78c13596fecd3e1506e103f3797ed88c09727dbfdad9abeaf7b6
+size 436225072

model-00019-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d23d5a8cb4ee4a42962d9ab48bd3efa6bc6464c5b69d3d82a2f224d33d939659
+size 436225072

model-00020-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eed80773b93abec7e7260901083b2fea6639a53ebcba6a8cd40fa1a05e60766
+size 436225072

model-00021-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0ef78ba053db61bb2898c7d109c461169cb1a8cecb3b42699d26476a51efe8a
+size 436225072

model-00022-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60df103d8e93e384cff0bf5f6d72c81cc8d0933ea7041c3687a58634535ce1bc
+size 436225072

model-00023-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8186404ccf1b1f1fe8a79a05abf804fa122eeba47feb7acd9692559535256514
+size 436225072

model-00024-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29241b6de5a1bd765880a12a38a17282c2b3ccec221829cae03030b4defb1eb7
+size 436225072

model-00025-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a6925afdccb093d80ebc47b748a4a7a528994b24b9053e61bec80734baa454a
+size 436225064

model-00026-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e69cf06b6ea698d0f06724810955ffcb6f3623c24b8fafa0f5682473333f76e
+size 436225064

model-00027-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4fec3892de7b359813bbf69d894dcabd71e4474d7da015a179db0901d54dc8e
+size 436225072

model-00028-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3396196c269a792e547cfa5510f1d9d5506777e8bbb73df6028399dd976a86e5
+size 436225064

model-00029-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51f923912a2bc8238c524bcd54d54965c19afbc542cbdf4d6e6b8b73b9656f34
+size 436225056

model-00030-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50bc1eb96953fbdb083a155eceafc3c80687244e556232293fbb0906df97bc10
+size 436225056

model-00031-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a10b66b67b3343ae5059d6bf833201632109519d1483b307ffdfbe7e43bb6984
+size 436225056

model-00032-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89d2a88a735ae8f266cca9fbba3e2c53acba6f56c9c6c7fd551b3aff48c92929
+size 436225056

model-00033-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e733d002a1fcddccf9cdffa7366fe85e174bc075dce3a88442efb0e07d799b2
+size 436225056

model-00034-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10fc3993acaef693d7efd27b4b9407747d53197d30f0967841851256cd2a816d
+size 201343792

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.1", "total_size": 14483464192}, "weight_map": {"lm_head.weight": "model-00001-of-00034.safetensors", "model.embed_tokens.weight": "model-00002-of-00034.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00034.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00034.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00034.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00034.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00034.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00034.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00034.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00034.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00034.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00034.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00034.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00034.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00004-of-00034.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00034.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00004-of-00034.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00034.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00034.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00034.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00034.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00034.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00034.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00005-of-00034.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00034.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00034.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00034.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00034.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00034.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00034.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00005-of-00034.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00034.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00006-of-00034.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00034.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00034.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00034.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00034.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00034.safetensors", "model.layers.12.input_layernorm.weight": "model-00006-of-00034.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00006-of-00034.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00034.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00007-of-00034.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00034.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00034.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00034.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00034.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00034.safetensors", "model.layers.13.input_layernorm.weight": "model-00007-of-00034.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00007-of-00034.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00034.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00008-of-00034.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00008-of-00034.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00034.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00034.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00034.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00034.safetensors", "model.layers.14.input_layernorm.weight": "model-00008-of-00034.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00008-of-00034.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00008-of-00034.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00009-of-00034.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00034.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00009-of-00034.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00034.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00034.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00034.safetensors", "model.layers.15.input_layernorm.weight": "model-00009-of-00034.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00009-of-00034.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00009-of-00034.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00010-of-00034.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00034.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00034.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00010-of-00034.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00010-of-00034.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00010-of-00034.safetensors", "model.layers.16.input_layernorm.weight": "model-00010-of-00034.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00010-of-00034.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00010-of-00034.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00011-of-00034.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00034.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00011-of-00034.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00011-of-00034.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00011-of-00034.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00011-of-00034.safetensors", "model.layers.17.input_layernorm.weight": "model-00011-of-00034.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00011-of-00034.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00011-of-00034.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00012-of-00034.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00012-of-00034.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00012-of-00034.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00012-of-00034.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00012-of-00034.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00012-of-00034.safetensors", "model.layers.18.input_layernorm.weight": "model-00012-of-00034.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00012-of-00034.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00012-of-00034.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00013-of-00034.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00013-of-00034.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00013-of-00034.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00013-of-00034.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00013-of-00034.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00013-of-00034.safetensors", "model.layers.19.input_layernorm.weight": "model-00013-of-00034.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00013-of-00034.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00013-of-00034.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00014-of-00034.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00014-of-00034.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00014-of-00034.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00014-of-00034.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00014-of-00034.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00014-of-00034.safetensors", "model.layers.2.input_layernorm.weight": "model-00014-of-00034.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00014-of-00034.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00014-of-00034.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00015-of-00034.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00015-of-00034.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00015-of-00034.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00015-of-00034.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00015-of-00034.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00015-of-00034.safetensors", "model.layers.20.input_layernorm.weight": "model-00015-of-00034.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00015-of-00034.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00015-of-00034.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00016-of-00034.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00016-of-00034.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00016-of-00034.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00016-of-00034.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00016-of-00034.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00016-of-00034.safetensors", "model.layers.21.input_layernorm.weight": "model-00016-of-00034.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00016-of-00034.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00016-of-00034.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00017-of-00034.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00017-of-00034.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00017-of-00034.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00017-of-00034.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00017-of-00034.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00017-of-00034.safetensors", "model.layers.22.input_layernorm.weight": "model-00017-of-00034.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00017-of-00034.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00017-of-00034.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00018-of-00034.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00018-of-00034.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00018-of-00034.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00018-of-00034.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00018-of-00034.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00018-of-00034.safetensors", "model.layers.23.input_layernorm.weight": "model-00018-of-00034.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00018-of-00034.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00018-of-00034.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00019-of-00034.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00019-of-00034.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00019-of-00034.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00019-of-00034.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00019-of-00034.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00019-of-00034.safetensors", "model.layers.24.input_layernorm.weight": "model-00019-of-00034.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00019-of-00034.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00019-of-00034.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00020-of-00034.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00020-of-00034.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00020-of-00034.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00020-of-00034.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00020-of-00034.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00020-of-00034.safetensors", "model.layers.25.input_layernorm.weight": "model-00020-of-00034.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00020-of-00034.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00020-of-00034.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00021-of-00034.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00021-of-00034.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00021-of-00034.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00021-of-00034.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00021-of-00034.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00021-of-00034.safetensors", "model.layers.26.input_layernorm.weight": "model-00021-of-00034.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00021-of-00034.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00021-of-00034.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00022-of-00034.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00022-of-00034.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00022-of-00034.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00022-of-00034.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00022-of-00034.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00022-of-00034.safetensors", "model.layers.27.input_layernorm.weight": "model-00022-of-00034.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00022-of-00034.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00022-of-00034.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00023-of-00034.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00023-of-00034.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00023-of-00034.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00023-of-00034.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00023-of-00034.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00023-of-00034.safetensors", "model.layers.28.input_layernorm.weight": "model-00023-of-00034.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00023-of-00034.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00023-of-00034.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00024-of-00034.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00024-of-00034.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00024-of-00034.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00024-of-00034.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00024-of-00034.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00024-of-00034.safetensors", "model.layers.29.input_layernorm.weight": "model-00024-of-00034.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00024-of-00034.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00024-of-00034.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00025-of-00034.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00025-of-00034.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00025-of-00034.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00025-of-00034.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00025-of-00034.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00025-of-00034.safetensors", "model.layers.3.input_layernorm.weight": "model-00025-of-00034.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00025-of-00034.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00025-of-00034.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00026-of-00034.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00026-of-00034.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00026-of-00034.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00026-of-00034.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00026-of-00034.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00026-of-00034.safetensors", "model.layers.30.input_layernorm.weight": "model-00026-of-00034.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00026-of-00034.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00026-of-00034.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00027-of-00034.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00027-of-00034.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00027-of-00034.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00027-of-00034.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00027-of-00034.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00027-of-00034.safetensors", "model.layers.31.input_layernorm.weight": "model-00027-of-00034.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00027-of-00034.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00027-of-00034.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00028-of-00034.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00028-of-00034.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00028-of-00034.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00028-of-00034.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00028-of-00034.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00028-of-00034.safetensors", "model.layers.4.input_layernorm.weight": "model-00028-of-00034.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00028-of-00034.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00028-of-00034.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00029-of-00034.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00029-of-00034.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00029-of-00034.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00029-of-00034.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00029-of-00034.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00029-of-00034.safetensors", "model.layers.5.input_layernorm.weight": "model-00029-of-00034.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00029-of-00034.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00029-of-00034.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00030-of-00034.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00030-of-00034.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00030-of-00034.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00030-of-00034.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00030-of-00034.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00030-of-00034.safetensors", "model.layers.6.input_layernorm.weight": "model-00030-of-00034.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00030-of-00034.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00030-of-00034.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00031-of-00034.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00031-of-00034.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00031-of-00034.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00031-of-00034.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00031-of-00034.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00031-of-00034.safetensors", "model.layers.7.input_layernorm.weight": "model-00031-of-00034.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00031-of-00034.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00031-of-00034.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00032-of-00034.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00032-of-00034.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00032-of-00034.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00032-of-00034.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00032-of-00034.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00032-of-00034.safetensors", "model.layers.8.input_layernorm.weight": "model-00032-of-00034.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00032-of-00034.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00032-of-00034.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00033-of-00034.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00033-of-00034.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00033-of-00034.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00033-of-00034.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00033-of-00034.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00033-of-00034.safetensors", "model.layers.9.input_layernorm.weight": "model-00033-of-00034.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00033-of-00034.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00033-of-00034.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00034-of-00034.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00034-of-00034.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00034-of-00034.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00034-of-00034.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00034-of-00034.safetensors", "model.norm.weight": "model-00034-of-00034.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n        {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n    {%- endif %}\n    {%- if message['role'] == 'user' %}\n        {%- if loop.first and system_message is defined %}\n            {{- ' [INST] ' + system_message + '\\n\\n' + message['content'] + ' [/INST]' }}\n        {%- else %}\n            {{- ' [INST] ' + message['content'] + ' [/INST]' }}\n        {%- endif %}\n    {%- elif message['role'] == 'assistant' %}\n        {{- ' ' + message['content'] + eos_token}}\n    {%- else %}\n        {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}\n    {%- endif %}\n{%- endfor %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}