Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ 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
+ak4ri-7b.IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+ak4ri-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+ak4ri-7b.fp16.gguf filter=lfs diff=lfs merge=lfs -text
+ak4ri-7b.fp16.gguf.Imatrix.dat filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,65 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- Virt-io/Irene-RP-v3-7B
+- Smuggling1710/Erosumika-MistralLayla-Slerp
+base_model:
+- Virt-io/Irene-RP-v3-7B
+- Smuggling1710/Erosumika-MistralLayla-Slerp
+---
+
+# Ak4ri-7b
+
+Ak4ri-7b is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [Virt-io/Irene-RP-v3-7B](https://huggingface.co/Virt-io/Irene-RP-v3-7B)
+* [Smuggling1710/Erosumika-MistralLayla-Slerp](https://huggingface.co/Smuggling1710/Erosumika-MistralLayla-Slerp)
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63b79573ca2f378e71027268/rQLmJqepFBl0ui8baHqRw.png)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: Virt-io/Irene-RP-v3-7B
+        layer_range: [0, 32]
+      - model: Smuggling1710/Erosumika-MistralLayla-Slerp
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: Smuggling1710/Erosumika-MistralLayla-Slerp
+parameters:
+  t:
+    - filter: self_attn
+      value: [0.6, 0.5, 0.3, 0.7, 0.4]
+    - filter: mlp
+      value: [0.4, 0.5, 0.7, 0.3, 0.6]
+    - value: 0.5
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "Smuggling1710/Ak4ri-7b"
+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"])
+```

ak4ri-7b.IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a468a8dafe6ae7bff9a60256497a53846c94308d8733783205eae1265e93997
+size 4125693664

ak4ri-7b.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afcdf09323ecb9f8845c1133663f62e0213825530fea5e8ff207cbb8b490216c
+size 7695857376

ak4ri-7b.fp16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc9e19a92cd3e102f487796d5f38aa05b9541e91b839462b7b0195303ca30c26
+size 14484731584

ak4ri-7b.fp16.gguf.Imatrix.dat

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68e39e9640a0e76f01e1258d054e2c2150491807d421156271e80f17dc680c2b
+size 4988126