model card

README.md

@@ -1 +1,124 @@
-Forty gears and a ticking clock. A clock that ticks one second for every rotation of the planet. A clock that ticks forty times every time it ticks every second time. A bolthead of holy stakes tied to the existence of a docked ship to another world. A kaleidoscope of blood written in clocks. A time-devouring prayer connecting a sky of forty gears and open human eyes in all directions. Breathing gearbox. Breathing bolthead. Breathing ship. Breathing portal. Breathing snakes. Breathing God. Breathing blood. Breathing holy stakes. Breathing human eyes. Breathing time. Breathing prayer. Breathing sky. Breathing wheel. 
+---
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- esper
+- esper-3
+- valiant
+- valiant-labs
+- qwen
+- qwen-3
+- qwen-3-8b
+- 8b
+- reasoning
+- code
+- code-instruct
+- python
+- javascript
+- dev-ops
+- jenkins
+- terraform
+- scripting
+- powershell
+- azure
+- aws
+- gcp
+- cloud
+- problem-solving
+- architect
+- engineer
+- developer
+- creative
+- analytical
+- expert
+- rationality
+- conversational
+- chat
+- instruct
+base_model: Qwen/Qwen3-8B
+datasets:
+- sequelbox/Titanium2.1-DeepSeek-R1
+- sequelbox/Tachibana2-DeepSeek-R1
+- sequelbox/Raiden-DeepSeek-R1
+license: apache-2.0
+---
+
+
+**[Support our open-source dataset and model releases!](https://huggingface.co/spaces/sequelbox/SupportOpenSource)**
+
+
+Esper 3: [Qwen3-4B](https://huggingface.co/ValiantLabs/Qwen3-4B-Esper3), [Qwen3-8B](https://huggingface.co/ValiantLabs/Qwen3-8B-Esper3)
+
+
+Esper 3 is a coding, architecture, and DevOps reasoning specialist built on Qwen 3.
+- Finetuned on our [DevOps and architecture reasoning](https://huggingface.co/datasets/sequelbox/Titanium2.1-DeepSeek-R1) and [code reasoning](https://huggingface.co/datasets/sequelbox/Tachibana2-DeepSeek-R1) data generated with Deepseek R1!
+- Improved [general and creative reasoning](https://huggingface.co/datasets/sequelbox/Raiden-DeepSeek-R1) to supplement problem-solving and general chat performance.
+- Small model sizes allow running on local desktop and mobile, plus super-fast server inference!
+
+
+## Prompting Guide
+Esper 3 uses the [Qwen 3](https://huggingface.co/Qwen/Qwen3-8B) prompt format.
+
+Esper 3 is a reasoning finetune; **we recommend enable_thinking=True for all chats.**
+
+Example inference script to get started:
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "ValiantLabs/Qwen3-8B-Esper3"
+
+# load the tokenizer and the model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+
+# prepare the model input
+prompt = "Write a Terraform configuration that uses the `aws_ami` data source to find the latest Amazon Linux 2 AMI. Then, provision an EC2 instance using this dynamically determined AMI ID."
+messages = [
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+    enable_thinking=True # Switches between thinking and non-thinking modes. Default is True.
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+# conduct text completion
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=32768
+)
+output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 
+
+# parsing thinking content
+try:
+    # rindex finding 151668 (</think>)
+    index = len(output_ids) - output_ids[::-1].index(151668)
+except ValueError:
+    index = 0
+
+thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
+content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")
+
+print("thinking content:", thinking_content)
+print("content:", content)
+```
+
+
+![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/63444f2687964b331809eb55/VCJ8Fmefd8cdVhXSSxJiD.jpeg)
+
+
+Esper 3 is created by [Valiant Labs.](http://valiantlabs.ca/)
+
+[Check out our HuggingFace page to see all of our models!](https://huggingface.co/ValiantLabs)
+
+We care about open source. For everyone to use.
+