127 lines
3.6 KiB
Markdown
127 lines
3.6 KiB
Markdown
---
|
|
language:
|
|
- en
|
|
library_name: transformers
|
|
pipeline_tag: text-generation
|
|
tags:
|
|
- esper
|
|
- esper-3
|
|
- valiant
|
|
- valiant-labs
|
|
- qwen
|
|
- qwen-3
|
|
- qwen-3-4b
|
|
- 4b
|
|
- 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/Qwen3-4B
|
|
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), [Qwen3-14B](https://huggingface.co/ValiantLabs/Qwen3-14B-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/Qwen3-4B) 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/Qwen3-4B-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.](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.
|
|
|