Upload model weights (#1)

- 2bd9c6248da8a46f133f968199627954c1289e0a6a4e239cd22bf5f160932ab3 (7092f8bd97637dc669ef189f2f6fea7d294cfab7)
- 4ee54d02ee62735021bf4b46470ab6b5813bb3984e5b25deaccbe141a1342c9c (3de5a709311b7c51441e376a9d77c1e83f80d96c)
- f4300c834f142771ac203447860ae8a99df6e20e47a18959c9ef7b371a99ce01 (ef5302b92a190be81c43d112b7cfa4d3c42914f5)
- 88156a1c7996c59192eff7781caba31e7729bda056cddadcd0c19a8c8fb47f73 (834d79a1c920e58828d76dd7ff8df45d90786939)
- e2f2295d19ed300c352ecc847a1db67b5f42959e66e3619bd5970fa214ce70ff (a6c323cabb452df39e64f3f25ede27f336ba6f15)
- bf9f6d7aa1f7a6853107fb20a643a9fb2bbdc40eb734e657cd30f43402b8fc94 (d2017e19c641a04de6e7c548feff5e4cacfe1f76)
- 986e044f1342e8f3a9e280a3778d87d9d0a4224dac86f139f471ae7825d8b47c (1a1e082d27f3c3fa084bc4618861c561639438b4)
- aae61de004cfc35e743251185c38fe7c3939a83a8001e53253fae30f09c2833f (9098d28901c8b6b4d4ba33f8c17de02e4636f28f)
- 98dd7ae8721f1a1a2167c2a7a52aedc2c3c88c3a9e1bfd203c337c2d9b93f0a7 (d4d20d884fc987686c3fb884eaef037d8ce2b32a)
- d3a66b0d6d372bed6f71f4fbcd41662cb30503956cc2073acb1cb41ccce8086e (b7731975eb6d2655e37731dd273c45ee2ec7f57c)
- 490ca352fe2e6daeb800e4acfc6afca6738cc569f96b6b065d36bc78e1b6f19d (25ecbae018f8c85ce7abe4c1f1a02f3c01e8a33e)
- 489227951736f7e3523de476f4154f9803b1504440e3fa4578894df8ec5c9292 (e770f3d978f9a4db4a4c8e10562b6d1ffac6220d)
- 2753e6ccc03ca50d769b195a2911d0655d515230ee73c2074372a0ece53163d8 (0d7801b6b22e5d9d37c16403402860dc1186f8b6)
- 85b25caa07d327608e4d7561c49658da7d891fef3d06df79f6c1de554b857bf7 (c8c60cce9f382b9c10b86ca4f318046a0669a898)

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": 8.0,
+        "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-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8e01cdc2d09e5237bc861f3e73c115790d004139f27f75e02f8e2e9ed2673d4
+size 8566293128

output-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7870a6b2033249683fe4be0004a38e39c046bd71ec06712549a8bd5a8596ce1
+size 8582301048

output-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:089cb6b03f6b3b8da30567b723cf7740f5184b2dfbf314cbc063e4c9928ecdb8
+size 8584576848

output-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c097436e62b6811e5437e638ead83a5e1aabef5e7383e93a218f03167bf5793
+size 8572694216

output-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f38832370cded4731067e80a693100e3bb2ab65fda4c2584638aad7c145584a6
+size 8531360536

output-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a0e04aa9db0dd2b9de3463dd00e4a30cc4751a14a34b86f8af8e118a950a3ff
+size 8577096072

output-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2b8bf5383aa280aaea9184475bffaf123439c220600ad97965bd0ea2d6038b4
+size 8579397208

output-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb7364f3d8095bc87f4d17c04dfba8d86309c7bcd40a0e3b76ebcc7d6752338c
+size 8538069944

output-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a389fd9f5a3a4fc1ff36a664ce531c8d8152f9b55ef0f1152319c278aebcdaf7
+size 8587507232

output-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2088ac16d458db86ff3e33827eff163cb9909ffbb12cffc83a177d977f71642
+size 8498589896

output-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44a296d41bc3603dac370a3e31dcd204b255ee3e08ba6e751c543826c762471f
+size 8566876328

output-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29aa913fc81601cdd1f4b792080cb7434da78d54ebc953111ea63c4b4c8c3b93
+size 8571072200

output-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3251c1d54fee304719c1fc423567996470faf2e869266e9276c0b60ec3ce173
+size 8588437240

output-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1fcdaa01ac6b184852b7a719f281335c9fed415e087dec4cdb4ab23554f5318
+size 1839486200

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
+}