Upload model weights (#1)

- de917d9b012698f37e51d46b1f9a75eedfd79174784bdcf70d8034f9045fe99d (385bc9a6303166155c7d040604ed0e0922baf31d)
- 8a5292769d802d5ffc8cce8ec443080787f5f2b4e40fba7267f3bae55b8185f6 (9a7bab25e07c0049b2043e4af1b16d3fa2cd4cdf)
- d09c0caf6c9aab3d1745f89260c4edb6b61aa783d4ee5d6547084266eeb66e7e (a8be07353e303adb852544d62f787ed07f8896a9)
- 514e053f024f5eb3a561051d4af4163356403f125dcad7c372a2a27353a5757f (9e5b812bc5fb2fba507771c2bd04ae8b94d70fb0)
- 226c9183d7dd56688e9b967bb0ca212e49ff04f6ab1d5aea2be32a16b6871077 (227a4faae6a28f8b93c2b4581c6ac175cf252f3f)
- 6730c9bf985788c3aa5ccb1fef2e0eb0f1817789915c128d149c1465907f6ff7 (b059b18d3e84cb421967fd11c09b2f535ff82140)
- 71b6cf5c7a1c791ac86674ddfa463fb657419bea3eb67ce4efb5a92b6757e6c1 (3d5a2aad111293e6156c46e8ad7a3ca558a2341c)
- cdbb61b6bfa699a2dc7285e8dac555d54a2648f1e17066378800f91f30402808 (692fccc5b8bd87a8fdc57a47d4a5e9d39f00fcf3)
- 6f986a2e754b6980b39d43a5b326ca575d1c62cd75558a095fdc267216eddec0 (cce06821e6b5e3cd3eb728a28a6e0a0ce625b17f)
- 012a52b282053343ceb10b2cdaf8c53643330f99aa39e0f19bcc073890bf2aef (bed7bf5dcfbc9a8ed6279af36380a93fc09431f5)
- e03f3a5f8a4c1e2e7212c7cecf64ad99c2ed95c9e087da847f8fd57b1d85068a (ea4f1bb73b79439e7b8dd3e14ed923892c84117b)
- 57adfa1d7679f0e5069c42f1fb0c4e32ea79dad322c07401674ee8b617449a38 (90ca84fa5d601d8516bc6f11b89e5f009d2f28df)

README.md

@@ -0,0 +1,49 @@
+---
+base_model:
+- alpindale/WizardLM-2-8x22B
+- lightblue/Karasu-Mixtral-8x22B-v0.1
+- openbmb/Eurux-8x22b-nca
+- cognitivecomputations/dolphin-2.9.2-mixtral-8x22b
+- migtissera/Tess-2.0-Mixtral-8x22B
+- fireworks-ai/mixtral-8x22b-instruct-oh
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# Untitled Model (1)
+
+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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [alpindale/WizardLM-2-8x22B](https://huggingface.co/alpindale/WizardLM-2-8x22B) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [lightblue/Karasu-Mixtral-8x22B-v0.1](https://huggingface.co/lightblue/Karasu-Mixtral-8x22B-v0.1)
+* [openbmb/Eurux-8x22b-nca](https://huggingface.co/openbmb/Eurux-8x22b-nca)
+* [cognitivecomputations/dolphin-2.9.2-mixtral-8x22b](https://huggingface.co/cognitivecomputations/dolphin-2.9.2-mixtral-8x22b)
+* [migtissera/Tess-2.0-Mixtral-8x22B](https://huggingface.co/migtissera/Tess-2.0-Mixtral-8x22B)
+* [fireworks-ai/mixtral-8x22b-instruct-oh](https://huggingface.co/fireworks-ai/mixtral-8x22b-instruct-oh)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: alpindale/WizardLM-2-8x22B
+  - model: lightblue/Karasu-Mixtral-8x22B-v0.1
+  - model: fireworks-ai/mixtral-8x22b-instruct-oh
+  - model: cognitivecomputations/dolphin-2.9.2-mixtral-8x22b
+  - model: openbmb/Eurux-8x22b-nca
+  - model: migtissera/Tess-2.0-Mixtral-8x22B
+base_model: alpindale/WizardLM-2-8x22B
+merge_method: model_stock
+dtype: bfloat16
+
+```

config.json

@@ -0,0 +1,42 @@
+{
+    "_name_or_path": "alpindale/WizardLM-2-8x22B",
+    "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": 56,
+    "num_key_value_heads": 8,
+    "num_local_experts": 8,
+    "output_router_logits": false,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000,
+    "router_aux_loss_coef": 0.001,
+    "router_jitter_noise": 0.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.41.2",
+    "use_cache": false,
+    "vocab_size": 32000,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.1.5",
+        "bits": 5.0,
+        "head_bits": 8,
+        "calibration": {
+            "rows": 100,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

mergekit_config.yml

@@ -0,0 +1,10 @@
+models:
+  - model: alpindale/WizardLM-2-8x22B
+  - model: lightblue/Karasu-Mixtral-8x22B-v0.1
+  - model: fireworks-ai/mixtral-8x22b-instruct-oh
+  - model: cognitivecomputations/dolphin-2.9.2-mixtral-8x22b
+  - model: openbmb/Eurux-8x22b-nca
+  - model: migtissera/Tess-2.0-Mixtral-8x22B
+base_model: alpindale/WizardLM-2-8x22B
+merge_method: model_stock
+dtype: bfloat16

output-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba2ed5844907dcbd12d4d7448b51f37a1ef2e525e399c40792fa09594384d972
+size 8582403256

output-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:381ed05b3fd3d80afaa36bac553d347d4fb3392277aa761a89e188ecd7d66d27
+size 8565071856

output-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2651b36dd9f05bc7bd5badcb812a3fc38f15e7287ed1dda12026171fb3d0faba
+size 8590035128

output-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ced1e75ca927ae8db0d7f9fb91901ef59c3d974d1870ef44b8fc5ed2632245d8
+size 8540755304

output-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3004ebe40f0d973425744b176ecc9bb521e97dad2f45bbc18b399189bf68bea4
+size 8565227016

output-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bf75363117826e89a605dcb0e18a95c6d70e01fe973b6f4e389e9e62076df0e
+size 8547459424

output-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66825bb4abc0f1604ee3fd2a4d22af7d7d2122644cf3a4dd7243e86aa673a850
+size 8589884640

output-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e872feb36b3a999e6f5bf43041404dd8790cc51a48cf668e51f631f43dc874d
+size 8531085864

output-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fa367d094f193e2c6593ea7b0f50cbf8324426956c297d237fd294023a0c0ab
+size 8571494552

output-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40b42a54eb2d88c12dbfc22a39021c820010ec2a00bacc1633c05b61bf26b477
+size 8572023344

output-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d7e290f42e3253051c5739f871c7e5bcd2675ce3af61b49a8976e858e96b716
+size 2497409856

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": "<unk>",
+    "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 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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' %}{% set loop_messages = messages[1:] %}{{ messages[0]['content'].strip() }}{% else %}{% set loop_messages = messages %}{{ 'A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user\\'s questions.' }}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{% if message['role'] == 'system' or message['role'] == 'user' %}{{ ' USER: ' + message['content'].strip() }}{% else %}{{ ' ASSISTANT: ' + message['content'].strip() + eos_token }}{% endif %}{% else %}{% if message['role'] == 'system' or message['role'] == 'user' %}{{ '\nUSER: ' + message['content'].strip() }}{% else %}{{ ' ASSISTANT: ' + message['content'].strip() + eos_token }}{% endif %}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ ' ASSISTANT:' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}