Upload folder using huggingface_hub

README.md

@@ -0,0 +1,59 @@
+---
+base_model:
+- sophosympatheia/Midnight-Miqu-70B-v1.5
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merged_model
+
+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 passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [sophosympatheia/Midnight-Miqu-70B-v1.5](https://huggingface.co/sophosympatheia/Midnight-Miqu-70B-v1.5)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+      - model: sophosympatheia/Midnight-Miqu-70B-v1.5
+        layer_range: [0, 16]
+  - sources:
+      - model: sophosympatheia/Midnight-Miqu-70B-v1.5
+        layer_range: [8, 24]
+  - sources:
+      - model: sophosympatheia/Midnight-Miqu-70B-v1.5
+        layer_range: [16, 32]
+  - sources:
+      - model: sophosympatheia/Midnight-Miqu-70B-v1.5
+        layer_range: [24, 40]
+  - sources:
+      - model: sophosympatheia/Midnight-Miqu-70B-v1.5
+        layer_range: [32, 48]
+  - sources:
+      - model: sophosympatheia/Midnight-Miqu-70B-v1.5
+        layer_range: [40, 56]
+  - sources:
+      - model: sophosympatheia/Midnight-Miqu-70B-v1.5
+        layer_range: [48, 64]
+  - sources:
+      - model: sophosympatheia/Midnight-Miqu-70B-v1.5
+        layer_range: [56, 72]
+  - sources:
+      - model: sophosympatheia/Midnight-Miqu-70B-v1.5
+        layer_range: [64, 80]
+merge_method: passthrough
+dtype: float16
+```

config.json

@@ -0,0 +1,40 @@
+{
+    "_name_or_path": "sophosympatheia/Midnight-Miqu-70B-v1.5",
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 8192,
+    "initializer_range": 0.02,
+    "intermediate_size": 28672,
+    "max_position_embeddings": 32764,
+    "model_type": "llama",
+    "num_attention_heads": 64,
+    "num_hidden_layers": 144,
+    "num_key_value_heads": 8,
+    "pad_token_id": 0,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 1000000,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float16",
+    "transformers_version": "4.39.2",
+    "use_cache": true,
+    "vocab_size": 32000,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.0.17",
+        "bits": 4.65,
+        "head_bits": 8,
+        "calibration": {
+            "rows": 100,
+            "length": 2048,
+            "dataset": "pippa_raw_fix.parquet"
+        }
+    }
+}

mergekit_config.yml

@@ -0,0 +1,30 @@
+slices:
+  - sources:
+      - model: sophosympatheia/Midnight-Miqu-70B-v1.5
+        layer_range: [0, 16]
+  - sources:
+      - model: sophosympatheia/Midnight-Miqu-70B-v1.5
+        layer_range: [8, 24]
+  - sources:
+      - model: sophosympatheia/Midnight-Miqu-70B-v1.5
+        layer_range: [16, 32]
+  - sources:
+      - model: sophosympatheia/Midnight-Miqu-70B-v1.5
+        layer_range: [24, 40]
+  - sources:
+      - model: sophosympatheia/Midnight-Miqu-70B-v1.5
+        layer_range: [32, 48]
+  - sources:
+      - model: sophosympatheia/Midnight-Miqu-70B-v1.5
+        layer_range: [40, 56]
+  - sources:
+      - model: sophosympatheia/Midnight-Miqu-70B-v1.5
+        layer_range: [48, 64]
+  - sources:
+      - model: sophosympatheia/Midnight-Miqu-70B-v1.5
+        layer_range: [56, 72]
+  - sources:
+      - model: sophosympatheia/Midnight-Miqu-70B-v1.5
+        layer_range: [64, 80]
+merge_method: passthrough
+dtype: float16

output-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:996719ee23247f7ffcb905d1339c8ccd9411bb423b618e96a121099f67c31107
+size 8578497188

output-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c81d0f1ef252520080a9c10758827211696d35a88c320c328dc02f443891691
+size 8518821176

output-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eafeeceefaadd793f32ea0af530b7e6cd94d92428a01d0ddac1f9050bbc53c4b
+size 8532324360

output-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e830aaaf28ba59a70940cf6a798094dec012ddc51218bdd768936c5fe3876a4
+size 8555665352

output-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccefefde5148c7c4f882e50d22b0ceec30223163ff0e113265c236c62040095c
+size 8478060448

output-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a70a0149f39aaa54ccd368b37ae3f442df4e33f112bd0152b8c659541e4ed210
+size 8532042024

output-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb6095c36d7d8a7f6be3fa6f148a698ed1ae91d05b7731e442aa3fdb496208d7
+size 8579511072

output-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edb6b7e18411d812e36b130fc90587c1c4d9d001834c2ae8ce3a06cc82c2da28
+size 8532555904

output-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1a7dab7ef4d500fd75461a36ba380bc6b1802b3100f4c6274988919e4ff9aa2
+size 4100703880

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "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
+    }
+  },
+  "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": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}