e9ca6ebd0d555778088e9fa1c7c0645e40f43e339249d7cceed02fd0b6132adb

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