A reasoning-focused fine-tune of
Qwen 3.5 2B
trained on the same structurally validated data as
Harmonic-9B
. Every row passes automated quality gates. No junk, no filler, no shallow traces.
Built primarily as a
draft model for speculative decoding
with the upcoming Harmonic-27B. Fast enough to propose tokens, trained on the same reasoning patterns so the acceptance rate stays high.
Training Approach
Same pipeline as Harmonic-9B.
799 curated rows
- a small, precisely curated dataset instead of tens of thousands of unfiltered examples.
Every training row contains explicit self-correction, verification, and multi-path exploration. The data was generated from multiple frontier models and filtered through a custom structural quality pipeline. 100% of rows pass all quality gates simultaneously.
Training Data Quality
The same reasoning data as Harmonic-9B, curated using a custom structural process supervision pipeline:
Metric
Value
Signal quality score
78.7 mean (61.5 min, 90.0 max)
Thinking trace depth
1,667 words average
Self-correction
100% of rows (17.2 per row avg)
Verification
100% of rows (10.3 per row avg)
Exploration
100% of rows (6.3 per row avg)
Quality gate pass rate
100%
Draft Model Design
Harmonic-2B is designed to pair with larger Harmonic models for speculative decoding:
Same training data
as the 9B and upcoming 27B - the models share reasoning patterns, which improves draft token acceptance rates
Same reasoning format
- uses identical
<think>
block structure
2.3B parameters
- small enough to run alongside a 27B on a single node
Same architecture family
(Qwen 3.5) - compatible tokenizer and vocab for seamless speculative decoding
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("DJLougen/Harmonic-2B")
tokenizer = AutoTokenizer.from_pretrained("DJLougen/Harmonic-2B")
As a draft model (speculative decoding)
from transformers import AutoModelForCausalLM
target = AutoModelForCausalLM.from_pretrained("DJLougen/Harmonic-9B") # or Harmonic-27B
draft = AutoModelForCausalLM.from_pretrained("DJLougen/Harmonic-2B")
# Use with assisted generation
outputs = target.generate(
**inputs,
assistant_model=draft,
max_new_tokens=512,
)
Reasoning format
The model uses think blocks for reasoning:
<|thinking|>
The user is asking about X. Let me consider two approaches...
Approach 1: ...
Approach 2: ...
I will go with Approach 1 because...
Wait, I need to be careful here - this assumes Y, which may not hold.
Let me verify by checking a special case...
Yes, that confirms the result.
<|/thinking|>
[Final answer here]
Intended Use
Draft model for speculative decoding with Harmonic-9B / Harmonic-27B
Lightweight reasoning on resource-constrained hardware
Edge deployment where reasoning quality matters but compute is limited
Base model for Stage 2 agentic fine-tuning at small scale
Limitations
2B parameter model - limited world knowledge compared to 9B/27B
Reasoning traces may be less reliable on complex multi-step problems
Designed as a draft model first, standalone use second
Harmonic-2B huggingface.co is an AI model on huggingface.co that provides Harmonic-2B's model effect (), which can be used instantly with this DJLougen Harmonic-2B model. huggingface.co supports a free trial of the Harmonic-2B model, and also provides paid use of the Harmonic-2B. Support call Harmonic-2B model through api, including Node.js, Python, http.
Harmonic-2B huggingface.co is an online trial and call api platform, which integrates Harmonic-2B's modeling effects, including api services, and provides a free online trial of Harmonic-2B, you can try Harmonic-2B online for free by clicking the link below.
DJLougen Harmonic-2B online free url in huggingface.co:
Harmonic-2B is an open source model from GitHub that offers a free installation service, and any user can find Harmonic-2B on GitHub to install. At the same time, huggingface.co provides the effect of Harmonic-2B install, users can directly use Harmonic-2B installed effect in huggingface.co for debugging and trial. It also supports api for free installation.