Upload model weights (#1)

- 6e216a9de97d10086d3955aedeea21cf753c7b3a6a8a4ca2e68a458df7257172 (aa4faff33c3d49951138646b12e0a9c1bbab0df7)
- a764a25f6a733bac4f4ddf17a3624dedeb71b913766ce04c19918e0fa4cb2ce8 (f999b8681fc44aacb244214d478f7bd3e4dbeb47)
- 10266a03e975e83492a63cc6454454c3c2f67e44b821e10216f52eea64c968d5 (afb5791ce05e89e8ad19a9ca176889b9f08ba347)
- af2b400764717725fb40f636ef3bb53cd2061fb4f9b485cc6ea7b6dae8c55c07 (4ba91fd99ca221a38614a88a7ca8518a4507df5e)
- e6a970f1279a5604fecd410b48d28187d50f25c9a9f4da2ce284cf14d04e465f (cd36ee43c4981fd7bc8afc3b1f2f350c1ebf76de)
- d7c1c6d4c7253fbd9ce283f9fb92331ac374dfff7370c527920634024ffd1ded (bed2b31a1de55ec13195b942c759fe965217d5fd)
- 4db53726bc59bbd14b94a399e86063dbf0c053eae88df122afd3d0e153a049c2 (0fbbd3f94193e6f0457cf68ef303a65509912a54)
- 73cc2fac3231b61d020aa71132a525c704cea6246162c403e2d487e7db7b7bfa (8c18f5d06cbadde212e1c63e81726ff11a57ba4f)
- 35199060f04dd4fc381393e22ee1e28aea030dc55d918eee997859503bb8aa80 (3ab8ef12c828b0d0abd02cb003193a491a9c0c64)

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": 4.0,
+        "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-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a591eab53bbc2c0e5e148e9519c76c686f6ae9fb9768860ff8b4ce08f3428523
+size 8580907600

output-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd29d89e7316adb8c594c25019ddfacdf21d11b809b6a2aa9578c3a434bff435
+size 8544364032

output-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:847255f59dbe3563c9bf75eefd709174494d1084ad18fc6117bda6edb0926a66
+size 8589756280

output-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db87c2151175e5331649a8886a44635f82dad81a303ab08c71111f75120aa231
+size 8586933800

output-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bc9e349a4f8d5f23fe42a24f217962b635e5836af2f7ca40dda4102f09059d1
+size 8558700576

output-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45c861075dfaf00fe8dff97a601ffc4ec8f0230ce3fc52f49cac397dac98e54d
+size 8589525528

output-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4101f1fcd2d3bc5d0b45b2fcdabb3fcee1a4443de0c53048577354fef56f6321
+size 8555766200

output-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:705c6849a2d76a9a07c7da7969a7cb27285d0f3ad515629ca743057829f52fe7
+size 8589628776

output-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7090506d4a9a57b2798dcdf971ead61d0ffc672fa0f9eab52d1cc98ea6b75603
+size 2033915552

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
+}