Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,349 @@
+
+---
+
+language:
+- en
+license: llama3.2
+tags:
+- shining-valiant
+- shining-valiant-2
+- valiant
+- valiant-labs
+- llama
+- llama-3.2
+- llama-3.2-instruct
+- llama-3.2-instruct-3b
+- llama-3
+- llama-3-instruct
+- llama-3-instruct-3b
+- 3b
+- science
+- physics
+- biology
+- chemistry
+- compsci
+- computer-science
+- engineering
+- technical
+- conversational
+- chat
+- instruct
+base_model: meta-llama/Llama-3.2-3B-Instruct
+datasets:
+- sequelbox/Celestia
+- sequelbox/Supernova
+pipeline_tag: text-generation
+model_type: llama
+model-index:
+- name: Llama3.2-3B-ShiningValiant2
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 69.85
+      name: acc
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: ARC Challenge (25-Shot)
+      type: arc_challenge
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 46.25
+      name: normalized accuracy
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU College Biology (5-shot)
+      type: mmlu
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 56.25
+      name: acc
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU High School Biology (5-shot)
+      type: mmlu
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 63.55
+      name: acc
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU College Chemistry (5-shot)
+      type: mmlu
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 41.0
+      name: acc
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU High School Chemistry (5-shot)
+      type: mmlu
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 41.38
+      name: acc
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU College Physics (5-shot)
+      type: mmlu
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 34.31
+      name: acc
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU High School Physics (5-shot)
+      type: mmlu
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 35.76
+      name: acc
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU College Computer Science (5-shot)
+      type: mmlu
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 48.0
+      name: acc
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU High School Computer Science (5-shot)
+      type: mmlu
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 58.0
+      name: acc
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU STEM (5-shot)
+      type: mmlu
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 45.54
+      name: acc
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 48.9
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 19.11
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 9.14
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 3.02
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 5.49
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 19.1
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2
+      name: Open LLM Leaderboard
+
+---
+
+[![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory)
+
+
+# QuantFactory/Llama3.2-3B-ShiningValiant2-GGUF
+This is quantized version of [ValiantLabs/Llama3.2-3B-ShiningValiant2](https://huggingface.co/ValiantLabs/Llama3.2-3B-ShiningValiant2) created using llama.cpp
+
+# Original Model Card
+
+
+
+![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/63444f2687964b331809eb55/EXX7TKbB-R6arxww2mk0R.jpeg)
+
+
+Shining Valiant 2 is a chat model built on Llama 3.2 3b, finetuned on our data for friendship, insight, knowledge and enthusiasm.
+  - Finetuned on [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) for best available general performance
+  - Trained on a variety of high quality data; focused on science, engineering, technical knowledge, and structured reasoning
+
+Shining Valiant 2 is also available for [Llama 3.1 8b.](https://huggingface.co/ValiantLabs/Llama3.1-8B-ShiningValiant2)
+
+
+## Version
+
+This is the **2024-09-27** release of Shining Valiant 2 for Llama 3.2 3b.
+
+We've improved and open-sourced our new baseline [science-instruct dataset](https://huggingface.co/datasets/sequelbox/Celestia). This release features improvements in physics, chemistry, biology, and computer science.
+
+Future upgrades will continue to expand Shining Valiant's technical knowledge base.
+
+Help us and recommend Shining Valiant 2 to your friends!
+
+
+## Prompting Guide
+Shining Valiant 2 uses the [Llama 3.2 Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) prompt format. The example script below can be used as a starting point for general chat:
+
+```python
+import transformers
+import torch
+
+model_id = "ValiantLabs/Llama3.2-3B-ShiningValiant2"
+
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model_id,
+    model_kwargs={"torch_dtype": torch.bfloat16},
+    device_map="auto",
+)
+
+messages = [
+    {"role": "system", "content": "You are an AI assistant."},
+    {"role": "user", "content": "Describe the use of chiral auxiliaries in organic synthesis."}
+]
+
+outputs = pipeline(
+    messages,
+    max_new_tokens=2048,
+)
+
+print(outputs[0]["generated_text"][-1])
+```
+
+
+## The Model
+Shining Valiant 2 is built on top of Llama 3.2 3b Instruct.
+
+The current version of Shining Valiant 2 is trained on technical knowledge using [sequelbox/Celestia](https://huggingface.co/datasets/sequelbox/Celestia) and general chat capability using [sequelbox/Supernova.](https://huggingface.co/datasets/sequelbox/Supernova)
+
+Our private data adds specialist knowledge and Shining Valiant's personality: she's friendly, enthusiastic, insightful, knowledgeable, and loves to learn! Magical. (As a general note: we're hoping to replace and open-source this part of Shining Valiant's dataset with synthetic data soon!)
+
+
+![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/63444f2687964b331809eb55/VCJ8Fmefd8cdVhXSSxJiD.jpeg)
+
+
+Shining Valiant 2 is created by [Valiant Labs.](http://valiantlabs.ca/)
+
+[Check out our HuggingFace page for our open-source Build Tools models, including the newest version of code-specialist Enigma!](https://huggingface.co/ValiantLabs)
+
+[Follow us on X for updates on our models!](https://twitter.com/valiant_labs)
+
+We care about open source.
+For everyone to use.
+
+We encourage others to finetune further from our models.
+