Upload 2 files

README.md

@@ -0,0 +1,49 @@
+---
+base_model:
+- HuggingFaceH4/zephyr-7b-beta
+- Project44/BioMistral-7B-0.1-PubMed-V2
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# BioMistral-7B-zephyr-beta-slerp
+
+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 SLERP merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta)
+* [Project44/BioMistral-7B-0.1-PubMed-V2](https://huggingface.co/Project44/BioMistral-7B-0.1-PubMed-V2)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+
+slices:
+  - sources:
+      - model: HuggingFaceH4/zephyr-7b-beta
+        layer_range: [0, 32]
+      - model: Project44/BioMistral-7B-0.1-PubMed-V2
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: HuggingFaceH4/zephyr-7b-beta
+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 +1,27 @@
+{
+  "_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
+  "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": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}