Upload folder using huggingface_hub (#1)

- 6c3ae9936a1e7251ae37f2f27b93981ca191b25c9d024592d48dbd984c94d8c6 (862fbc1a17d64f8c47653717ee06fd91428aa7c1)
- 8d01a80cb685f86446a6e015c1b60920d9a1089fd58a8085b48fbe7d58f32b68 (6156b777ea751aca6fc7006016a0160367ac886e)
- dfabdbced20890dd90356e01e17c037e432bf5bc57fd1b41f689ecfab6ca6cf2 (d6da1f79848cb356b31f0ae11719bb6c6f5ac7f1)
- 1931afd00344ebab065356dbd51fa36312b316e34858fa35c4f977dbdb2d67e4 (678fdc854d4373105b30dfa6efcf5da4ba3e3852)
- cba5fa4e633e9d8443996d7faaeb1dbd1bf5011d2aec39928e197340eb8b8286 (833088774e498f436ac14e2e5d9ab282169a86c8)
- e9ca6ebd0d555778088e9fa1c7c0645e40f43e339249d7cceed02fd0b6132adb (6cf5e5cdf025e3dc9116cc67bd991026b161857a)

.gitattributes

@@ -33,3 +33,8 @@ 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
+ChatHercules-2.5-Mistral-7B_Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+ChatHercules-2.5-Mistral-7B_Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+ChatHercules-2.5-Mistral-7B_Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+ChatHercules-2.5-Mistral-7B_Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+ChatHercules-2.5-Mistral-7B_Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

ChatHercules-2.5-Mistral-7B_Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6917215fcdd2be50b9c9957013689f540ac6e9456f9ebc8d001f2efdff520f2
+size 3518985984

ChatHercules-2.5-Mistral-7B_Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ffb1267ab8c3ad19326b1d3f2e99f2f2a95470a04bd19d436a626e9ce3b0723
+size 4368439040

ChatHercules-2.5-Mistral-7B_Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fc91cbb6a55c837a0d2548c755e40fe7cb4071113a7b57ec4d6da3db095e634
+size 5131409152

ChatHercules-2.5-Mistral-7B_Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b0dd41a2bdc3aa967f5f4e793766f2f4cdf322512bebdbe518ed33c38016549
+size 5942064896

ChatHercules-2.5-Mistral-7B_Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c5f0ee77797cba19ea61147e50baa647ac53e7286f46340c09dddbf6ac7a4db
+size 7695857408

README.md

@@ -0,0 +1,191 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- Locutusque/Hercules-2.5-Mistral-7B
+- openchat/openchat-3.5-0106
+base_model:
+- Locutusque/Hercules-2.5-Mistral-7B
+- openchat/openchat-3.5-0106
+model-index:
+- name: ChatHercules-2.5-Mistral-7B
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 65.1
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hydra-project/ChatHercules-2.5-Mistral-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 84.61
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hydra-project/ChatHercules-2.5-Mistral-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 65.35
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hydra-project/ChatHercules-2.5-Mistral-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 47.52
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hydra-project/ChatHercules-2.5-Mistral-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 81.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hydra-project/ChatHercules-2.5-Mistral-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 64.97
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hydra-project/ChatHercules-2.5-Mistral-7B
+      name: Open LLM Leaderboard
+---
+
+# ChatHercules-2.5-Mistral-7B
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6437292ecd93f4c9a34b0d47/VW32vrPx2giqo5Od8Tyz0.png)
+
+ChatHercules-2.5-Mistral-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [Locutusque/Hercules-2.5-Mistral-7B](https://huggingface.co/Locutusque/Hercules-2.5-Mistral-7B)
+* [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106)
+
+
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: Locutusque/Hercules-2.5-Mistral-7B
+        layer_range: [0, 32]
+      - model: openchat/openchat-3.5-0106
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: Locutusque/Hercules-2.5-Mistral-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
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "hydra-project/ChatHercules-2.5-Mistral-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"])
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_hydra-project__ChatHercules-2.5-Mistral-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |68.24|
+|AI2 Reasoning Challenge (25-Shot)|65.10|
+|HellaSwag (10-Shot)              |84.61|
+|MMLU (5-Shot)                    |65.35|
+|TruthfulQA (0-shot)              |47.52|
+|Winogrande (5-shot)              |81.85|
+|GSM8k (5-shot)                   |64.97|
+
+
+
+***
+
+Quantization of Model [hydra-project/ChatHercules-2.5-Mistral-7B](https://huggingface.co/hydra-project/ChatHercules-2.5-Mistral-7B).
+Created using [llm-quantizer](https://github.com/Nold360/llm-quantizer) Pipeline