Upload folder using huggingface_hub

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,48 @@
+---
+base_model:
+- alpindale/WizardLM-2-8x22B
+- mistralai/Mixtral-8x22B-Instruct-v0.1
+tags:
+- mergekit
+- merge
+
+---
+# merge.py
+
+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, 56]
+      - model: alpindale/WizardLM-2-8x22B
+        layer_range: [0, 56]
+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
+
+```

.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,31 @@
+{
+  "_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": 56,
+  "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,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0",
+  "use_cache": true,
+  "vocab_size": 32768
+}

.ipynb_checkpoints/mergekit_config-checkpoint.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: mistralai/Mixtral-8x22B-Instruct-v0.1
+        layer_range: [0, 56]
+      - model: alpindale/WizardLM-2-8x22B
+        layer_range: [0, 56]
+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.py
+
+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, 56]
+      - model: alpindale/WizardLM-2-8x22B
+        layer_range: [0, 56]
+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 +1,31 @@
+{
+  "_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": 56,
+  "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,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0",
+  "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, 56]
+      - model: alpindale/WizardLM-2-8x22B
+        layer_range: [0, 56]
+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:cc8567b571939ae5dfb5d48c49b16563253dc36e69cf117e0e7df3c1d2ef6e1a
+size 9805561216

model-00002-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35da0fa5000f7e5f08eeec69b68bd2660a8862e1f60ded9f7f79823310538301
+size 9814924936

model-00003-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e87dd44a050a913508f46c78617264149c6c3c47fbcecbd58a25fb4aa7824fd
+size 9814924936

model-00004-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63b89941a6ec1fe3c6173b3e36fd489da7274fe0b52b7902a57aed087a4b1847
+size 9814924936

model-00005-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d6dff6be8d77dedaa4d31f32ae303c541f7a886505c12fad9397d2c905834f5
+size 9814924944

model-00006-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8624892ac9044964c875b06c2db7c91745393a0a290874358d97c343d4db31ec
+size 9814924984

model-00007-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a46d253d6919362f1ae2927bf19840ba814210a8bf27785579ade33a2c22bbc1
+size 9991086240

model-00008-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e55b5f572ff519aadb1accec22ac4050842b0c9cb03c216affe3f56985197b41
+size 9814925000

model-00009-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a9ca4a8ceff1b6970da8b2aed31030efcd0084fee696308a2289d21a8c50311
+size 9814925000

model-00010-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2450a798bcac95c61b49766c317329352db1ee9725003193fb27981bb8cc70c
+size 9814925000

model-00011-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1069ffd8bd4db1ad5bdf344048ae8fac17aef5d0c110ec043f48f57cda65c913
+size 9940655712

model-00012-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5e260cb350e31366b700bd76e22f9369caefa1a2484275c64785c0b55215736
+size 9903005048

model-00013-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d5da31c3d475f3276ba8f1bbddee5e3f117879bb11a92ea04e2786ff89b16b1
+size 9852673512

model-00014-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af4302d1e5cda294fc68265486372af50246345bcd1ed6a471fd217bda73be1b
+size 9814900192

model-00015-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0862d1164d0266502a32f41fa8a85388dc82d7d4e132f4a9a1167710752620cd
+size 9814925000

model-00016-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0521ccafb1043fdf2a1c8eebc493914feb0d204e88aa213b071f4691fae4cb03
+size 9814925000

model-00017-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1beffd9064e76c73b2993f9767544812a6a9b6b035dbb5cb7a8a46aeaf3bbb46
+size 9991086240

model-00018-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29b2b3f60f4a9eb4da537ff1198caa8d07dd9d4c6bc0ad904fe7d767de01c5fa
+size 9814925000

model-00019-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a1974226df47d63d8ebac3036baf463a325ba933576201aec4a8416d5292232
+size 9814925000

model-00020-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3dc866ff028b49ab85fa20ebf15812b0cc2b4ad2e3690d75120af530da747da
+size 9814925000

model-00021-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be418005d1dedfc40b44af4087a6f5288a6bedd02427b34f7e4e7574f990e352
+size 9814925000

model-00022-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6f3b58bbadb2bdf320cc04b75f23fa7d0da01b64e1c53bada73090e4e3f41c2
+size 9814925000

model-00023-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d41167ae5d1c97049642000b60b8a5cb4781f8af6618d80602d40f2ab2a558d
+size 9814925000

model-00024-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0586c1baf7eb695b0866b3000c26963f855f587eb7b10ad4f23840e6fd8a81a5
+size 9991209472

model-00025-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d14c1b8276a62786f3f6987db8035453f862ad6832705ab5db9e3a1d48105b2c
+size 9852575088

model-00026-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0395ea255b66391c1278012a323d36ed7e63ecb1d2d31ef23f9d32dbafe9b00c
+size 9903005048

model-00027-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7db19d71c9dcd7ea6f4c5b2f067fe5ed9be0b321ae42478a26272ddf36e0d610
+size 9940729328

model-00028-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0d2bdb93a12602e3a7c06c999f380485ff8f3ac3cedc1396351398881e4b355
+size 9814925000

model-00029-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9ab71c0185b7a860b4764439440202e7ab67883b7c770c9d21ce2032ab18a6f
+size 5401280728

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
+    },
+    "8": {
+      "content": "[TOOL_RESULTS]",
+      "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
+    }
+  },
+  "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
+}