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": 5.0,
+        "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-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e00afe35c6abc7802cb23d365c8713ecc75fa2a4e6f79a5b156aa7e86132821e
+size 8575200660

output-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e04bb5cfd77b85e7630d2a81ca9d3a547e5d21618660e54d1aa7fe165e79b554
+size 8472106164

output-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96de572b070d65bcd5a6b068e686e9420e4521ebc363d41febb679e1219a7f11
+size 8479272752

output-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46dae2656c546f51e7d897b1e5d3722beec48e43b56d94b4fe292038675933d0
+size 8572432288

output-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7050980e99e1d11685d33daebb12a8aba4550261238c15385db1c092a87707d7
+size 8441524000

output-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a54de5312f6e0a0403c7e9fd3313755ebeb74406f0ea52d6715aa0447f115f0a
+size 8463544216

output-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8996b3ec904bbb90a122a600697aa45f0a184fad12dd38e131281e736eb6e66
+size 8484693920

output-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1b6f0f81baade0aad42389c7bf9df1746c434cfde6a2c0508cbc18f0473108b
+size 8588731344

output-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3981b6d9885a2aa4eab14052acff47460e799d8ed5e275016d7fea757e4b46e3
+size 8467864360

output-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:628a2b09e2a5382ac807006b0df26a3e3252d9f3ab9034f65fdf2974a8317816
+size 1250082312

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
+}