model file

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,48 @@
 ---
-license: apache-2.0
+base_model:
+- BarryFutureman/WildMarcoroni-Variant1-7B
+- nbeerbower/bruphin-delta
+tags:
+- mergekit
+- merge
+
 ---
+# bruphin-epsilon-GGUF-q4_0
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+Quantized using [llama.cpp](https://github.com/ggerganov/llama.cpp).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the SLERP merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [BarryFutureman/WildMarcoroni-Variant1-7B](https://huggingface.co/BarryFutureman/WildMarcoroni-Variant1-7B)
+* [nbeerbower/bruphin-delta](https://huggingface.co/nbeerbower/bruphin-delta)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: nbeerbower/bruphin-delta
+    layer_range: [0, 32]
+  - model: BarryFutureman/WildMarcoroni-Variant1-7B
+    layer_range: [0, 32]
+merge_method: slerp
+base_model: BarryFutureman/WildMarcoroni-Variant1-7B
+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 +1,28 @@
+{
+  "_name_or_path": "nbeerbower/bruphin-epsilon",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.0.dev0",
+  "unsloth_version": "2024.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

ggml-model-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7672ecdbd93c08ef0328cb75fed0fb36ace6f539b447e6bc5b8d4ab10d24546a
+size 4108916928

mergekit_config.yml

@@ -0,0 +1,15 @@
+models:
+  - model: nbeerbower/bruphin-delta
+    layer_range: [0, 32]
+  - model: BarryFutureman/WildMarcoroni-Variant1-7B
+    layer_range: [0, 32]
+merge_method: slerp
+base_model: BarryFutureman/WildMarcoroni-Variant1-7B
+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