Create README.md

README.md

@@ -0,0 +1,54 @@
+
+---
+license: llama2
+---
+
+<p align="center">
+  <img src="https://codeberg.org/aninokuma/DeydooAssistant/raw/branch/main/logo.webp" height="256px" alt="SynthIQ">
+</p>
+
+# SynthIQ
+
+This is the sharded model for SynthIQ. I used [mergekit](https://github.com/cg123/mergekit) to merge models.
+
+**Caution**: This model is yet to be tested. If you find it useful, do let me know in the discussion!
+
+
+# Yaml Config
+
+```yaml
+
+slices:
+  - sources:
+      - model: Weyaxi/OpenHermes-2.5-neural-chat-v3-3-openchat-3.5-1210-Slerp
+        layer_range: [0, 32]
+      - model: uukuguy/speechless-mistral-six-in-one-7b
+        layer_range: [0, 32]
+
+merge_method: slerp
+base_model: mistralai/Mistral-7B-v0.1
+
+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 # fallback for rest of tensors
+tokenizer_source: union
+
+dtype: bfloat16
+
+```
+
+Prompt Template : ChatML
+
+GGUF Files
+
+[Q4_K_M](https://huggingface.co/sethuiyer/SynthIQ_GGUF/blob/main/synthiq.Q4_K_M.gguf)
+[Q_6_K](https://huggingface.co/sethuiyer/SynthIQ_GGUF/blob/main/synthiq.Q6_K.gguf)
+[Q8_0](https://huggingface.co/sethuiyer/SynthIQ_GGUF/blob/main/synthiq.Q8.gguf)
+
+
+License is LLama2 license as uukuguy/speechless-mistral-six-in-one-7b is llama2 license.
+