Upload folder using huggingface_hub

README.md

@@ -0,0 +1,64 @@
+---
+base_model:
+- PleIAs/Baguettotron
+- PleIAs/Monad
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge
+
+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 using [PleIAs/Monad](https://huggingface.co/PleIAs/Monad) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [PleIAs/Baguettotron](https://huggingface.co/PleIAs/Baguettotron)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+merge_method: passthrough
+dtype: bfloat16
+out_dtype: float32
+base_model: PleIAs/Monad
+slices:
+  - sources:
+    - model: PleIAs/Monad
+      layer_range: [0,64]
+  - sources:
+    - model: PleIAs/Monad
+      layer_range: [10,36]
+  - sources:
+    - model: PleIAs/Monad
+      layer_range: [12,30]
+  - sources:
+    - model: PleIAs/Monad
+      layer_range: [0,24]
+  - sources:
+    - model: PleIAs/Monad
+      layer_range: [16,32]
+  - sources:
+    - model: PleIAs/Monad
+      layer_range: [48,64]
+  - sources:
+    - model: PleIAs/Baguettotron
+      layer_range: [0,40]
+  - sources:
+    - model: PleIAs/Baguettotron
+      layer_range: [40,80]
+tokenizer:
+  source: base
+parameters:
+  normalize: true
+
+```

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 768,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 244,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "vocab_size": 8192
+}

mergekit_config.yml

@@ -0,0 +1,33 @@
+merge_method: passthrough
+dtype: bfloat16
+out_dtype: float32
+base_model: PleIAs/Monad
+slices:
+  - sources:
+    - model: PleIAs/Monad
+      layer_range: [0,64]
+  - sources:
+    - model: PleIAs/Monad
+      layer_range: [10,36]
+  - sources:
+    - model: PleIAs/Monad
+      layer_range: [12,30]
+  - sources:
+    - model: PleIAs/Monad
+      layer_range: [0,24]
+  - sources:
+    - model: PleIAs/Monad
+      layer_range: [16,32]
+  - sources:
+    - model: PleIAs/Monad
+      layer_range: [48,64]
+  - sources:
+    - model: PleIAs/Baguettotron
+      layer_range: [0,40]
+  - sources:
+    - model: PleIAs/Baguettotron
+      layer_range: [40,80]
+tokenizer:
+  source: base
+parameters:
+  normalize: true

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:169d8b339d7817e127316a5cc2721f0805d97ff4ade72f04a102d88f06815487
+size 1700696960

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|end_of_text|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}