Upload folder using huggingface_hub

.ipynb_checkpoints/mergekit_config-checkpoint.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: mistralai/Mixtral-8x22B-Instruct-v0.1
+        layer_range: [0, 55]
+      - model: alpindale/WizardLM-2-8x22B
+        layer_range: [0, 55]
+merge_method: slerp
+base_model: mistralai/Mixtral-8x22B-Instruct-v0.1
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16

README.md

@@ -0,0 +1,48 @@
+---
+base_model:
+- alpindale/WizardLM-2-8x22B
+- mistralai/Mixtral-8x22B-Instruct-v0.1
+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:
+* [alpindale/WizardLM-2-8x22B](https://huggingface.co/alpindale/WizardLM-2-8x22B)
+* [mistralai/Mixtral-8x22B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+
+slices:
+  - sources:
+      - model: mistralai/Mixtral-8x22B-Instruct-v0.1
+        layer_range: [0, 55]
+      - model: alpindale/WizardLM-2-8x22B
+        layer_range: [0, 55]
+merge_method: slerp
+base_model: mistralai/Mixtral-8x22B-Instruct-v0.1
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16
+
+```

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "mistralai/Mixtral-8x22B-Instruct-v0.1",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 65536,
+  "model_type": "mixtral",
+  "num_attention_heads": 48,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 55,
+  "num_key_value_heads": 8,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 32768
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: mistralai/Mixtral-8x22B-Instruct-v0.1
+        layer_range: [0, 55]
+      - model: alpindale/WizardLM-2-8x22B
+        layer_range: [0, 55]
+merge_method: slerp
+base_model: mistralai/Mixtral-8x22B-Instruct-v0.1
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16

model-00001-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1fd5d31ebbc5ed89cca64f456877d4c69f37c6837235fc9758a0c5f4b4e9630
+size 9805561216

model-00002-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e4d446d880625f3c02442f9a0dac2467063731309dc343a7d3d3b555aa0c02a
+size 9814924936

model-00003-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dd1ced32770785d7ed87a4bfdcbc84c29ec62268453926fa4895a8d4ec2d58c
+size 9814924936

model-00004-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3d60cb1bd5a5238ab6e81f06fab01669d9da89d6ffff1c5cc5f44a0ae2efad9
+size 9814924936

model-00005-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c933f6547636d02eacbd9d6f78cb29a036adece4743597d4672e2af26abc631
+size 9814924944

model-00006-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3f3dc925874365a3708bf0786b7d4d5744dffbd2f1b34f678b1458a2bb06fce
+size 9814924984

model-00007-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66c84afb211f080c430c1a3a5f0f65108edb52bbc6867c7be5577eb1120e899f
+size 9991086240

model-00008-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00027f8a9e7f63551a4571e9dab70e010e8c04436c97a80dc4b76815636a78d8
+size 9814925000

model-00009-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51e0cb2593c25c9e3068f34b98eaabcf395baa31661f98b5809e7712bbd94ff7
+size 9814925000

model-00010-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:574ed920cfb695141769b486eb5a1510952d8cd9318a55afa06e9b909127fc86
+size 9814925000

model-00011-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43d99e0a9b013f54c8f251507a562b17bec6498c619b8689fd904d8635e6e135
+size 9940655712

model-00012-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b16074696d554352ff9e35d00d39d380fa4be32b3b2595050a7d2799e3816dd
+size 9903005048

model-00013-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94f45e8063306bacc73a305f0baa3dac2853acb6601413cb53c1ff404cdc1ef3
+size 9852673512

model-00014-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1583987edc206bb85eea4ad7b6d1ee77eb37051e90d5274bb71c61fabcaad17c
+size 9814900192

model-00015-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6844de9ea4a39750a653aac336663f75340b426e9a559239929eae1ce11f396f
+size 9814925000

model-00016-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:499ca69fde43bb98a3d7028eb222ac7acfc6f9391e7e818990d8e83609dc9dcc
+size 9814925000

model-00017-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cdccf252c8a3b1212528fd57de23b373a3e55ac2cc2731e6d6ae926a252b65f
+size 9991086240

model-00018-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b416567c08865bac8bb73445cafaede13ce5a74db4aa9e0a06ce91306cfe1e04
+size 9814925000

model-00019-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2a3931d046ed76bc140432744cf196b3a225c1a778db7ec91a688c32e976cb7
+size 9814925000

model-00020-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:698954ccdbb85fd0dd7d3bf1a358a4eef0d57df557fff9af1a4c5093b65cc85b
+size 9814925000

model-00021-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4824cd37a6974ef6ad5ce4cdce701b91dc0c68b5e0e9fc00d7bdef0e6ec1897e
+size 9814925000

model-00022-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee3960ee13975fe563a0159b2be01b2687f9938ca4ea163d9d37527ec3021b31
+size 9814925000

model-00023-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d17c55edd605bb0189d4c0de8dc94a555cc8426ff65ba61d6dd6d807eb58792d
+size 9814925000

model-00024-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e6d349c476e0b4dfc9875c9d87a493c5ab30f925158720b6b80eecd3aca6b7c
+size 9991209472

model-00025-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:633dccfc64f65e476f22341df67b7bdf1908b5e5d64a88ced0e5b346515a03e6
+size 9852575088

model-00026-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:249de0009241cb022fde369e655a169d3b7c2d9dd7ce91b713cc61e9afefc818
+size 9903005048

model-00027-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8deb756217580fc4bd026aa81638267fabbb664c33f95abf994a2c1a41e7a01
+size 9940729328

model-00028-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:effe431ac18d0c0fedcfaefb4d92db5daa655b6483141847e7e89b5c167f497c
+size 9814851384

model-00029-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a064cd5e16c62ce675986decb58cdec894c480f7b4957ea2955210e8516a1203
+size 393228504

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_config.json

@@ -0,0 +1,99 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "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
+    },
+    "3": {
+      "content": "[INST]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[/INST]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[TOOL_CALLS]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "[AVAILABLE_TOOLS]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "[/AVAILABLE_TOOLS]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "[/TOOL_RESULTS]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32768": {
+      "content": "[TOOL_RESULT]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{bos_token}}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ ' [INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'] + ' ' + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "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
+}