Upload folder using huggingface_hub

README.md

@@ -0,0 +1,36 @@
+---
+base_model:
+- TheDrummer/Cydonia-22B-v1.2
+tags:
+- merge
+- mergekit
+- lazymergekit
+- TheDrummer/Cydonia-22B-v1.2
+---
+
+# Cydonia-Mini-18B
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "Ttimofeyka/Cydonia-Mini-18B"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "TheDrummer/Cydonia-22B-v1.2",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 32768
+}

mergekit_config.yml

@@ -0,0 +1,13 @@
+
+slices:
+  - sources:
+      - model: TheDrummer/Cydonia-22B-v1.2
+        layer_range: [0, 16]
+      - model: TheDrummer/Cydonia-22B-v1.2
+        layer_range: [20, 36]
+      - model: TheDrummer/Cydonia-22B-v1.2
+        layer_range: [38, 54]
+
+merge_method: passthrough
+base_model: TheDrummer/Cydonia-22B-v1.2
+dtype: bfloat16

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4e28915b07cf7ebb42391800a106b9bcea379a2122a0cd1e372d67841125c7b
+size 805318992

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70d6f2bc8a99a7f2d8e4dc0a0c93e04946875e0e06dd2e97113812799565c16f
+size 981492888

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7b94d64be142bf540c02b79e613e3cc2656f7d76a2e55d7bbe5add0136b4b5e
+size 981492888

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c07d792955d7f3525c30a4ed3cc0b85b634505b61ef1b72d1f755bd548c7a42b
+size 994088312

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0776ca00023260b3e8534b7b35061798e68bf5ff39f9e2724b83daf723da4dee
+size 943756776

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:983660312bc9e33b872c317a6d12dcad479b0706152271cfd13f0db8ce1d88cd
+size 981492888

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b38ccd7f5aed4a31861a9a978dc46081f6357e615c0e128bfc82dc41ca9e91d
+size 981492888

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb266c5316cc972107c2cd78a7aba47a36b7dcbe2f58a511e52a96d737eb6e92
+size 994088312

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9e9402992fb1e75a715667f54b4082f6b3c8eecc2342645c4fddb33c01b2909
+size 943756768

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:387eed6cb5129bc4be3229fcf76310ce0f8745457d4f7c044a966580e90fabfe
+size 981492896

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dad9e814ab05cd3ba5934fed40b31d7237ed04657fd70c6e08aa8754913e0d9
+size 981492896

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8349904866d7954c59eba544341f5fc6be6ae765a8b586eea93023a6f6ed431f
+size 994088328

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b42dcc668b1487bfdb2e815392caf31e5a8408f639eb6368b76e52561f125ab
+size 943756792

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb6dd76bea44841d657be6667d9aa243150f46a9e4882e24bb2adcfed51b247d
+size 780166168

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.1", "total_size": 13287960576}, "weight_map": {"lm_head.weight": "model-00001-of-00014.safetensors", "model.embed_tokens.weight": "model-00001-of-00014.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.7.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.12.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.13.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.14.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.norm.weight": "model-00014-of-00014.safetensors"}}

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": "</s>",
+    "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 sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
+size 587583