README.md

metadata

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!

Esper 3: Qwen3-4B, Qwen3-8B, Qwen3-14B

Esper 3 is a coding, architecture, and DevOps reasoning specialist built on Qwen 3.

• Finetuned on our DevOps and architecture reasoning and code reasoning data generated with Deepseek R1!
• Improved general and creative reasoning 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 prompt format.

Esper 3 is a reasoning finetune; we recommend enable_thinking=True for all chats.

Example inference script to get started:

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)

Esper 3 is created by Valiant Labs.

Check out our HuggingFace page to see all of our models!

We care about open source. For everyone to use.