GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
hikewa
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
hikewa
Model Tree
Qwen/Qwen2.5-1.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Compared to the base Qwen2.5-1.5B-Instruct, this adapter produces responses that:
| Parameter | Value |
|---|---|
| Base model | Qwen/Qwen2.5-1.5B-Instruct |
| Method | LoRA (r=16, alpha=32) |
| Target modules | q_proj, k_proj, v_proj, o_proj |
| Training examples | 205 |
| Epochs | 3 |
| Final eval loss | 1.84 |
| Training time | 5.5 min (Apple MPS) |
| Dataset | hikewa/dialectic-reasoning-traces |
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct", torch_dtype="auto", trust_remote_code=True)model = PeftModel.from_pretrained(base, "hikewa/dialectic-qwen2.5-1.5b-lora")tokenizer = AutoTokenizer.from_pretrained("hikewa/dialectic-qwen2.5-1.5b-lora", trust_remote_code=True) messages = [ {"role": "system", "content": "You reason carefully through problems by considering competing perspectives."}, {"role": "user", "content": "Should AI systems be transparent about their reasoning?"},]text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(text, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7, do_sample=True)print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))| Model | Eval Loss | Link |
|---|---|---|
| Qwen2.5-1.5B | 1.84 | hikewa/dialectic-qwen2.5-1.5b-lora |
| Qwen3-8B | 1.26 | hikewa/dialectic-qwen3-8b-lora |
Eval losses come from different validation splits (this adapter: the 255-trace release; 8B: a 510-trace corpus), so they are not directly comparable. Other adapters from this project are not public.
This is a smaller exploratory variant. The strongest published evaluation currently belongs to the 8B model, which was trained on a larger internal 510-trace corpus rather than only the smaller public release used here.
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct", torch_dtype="auto", trust_remote_code=True)model = PeftModel.from_pretrained(base, "hikewa/dialectic-qwen2.5-1.5b-lora")tokenizer = AutoTokenizer.from_pretrained("hikewa/dialectic-qwen2.5-1.5b-lora", trust_remote_code=True) messages = [ {"role": "system", "content": "You reason carefully through problems by considering competing perspectives."}, {"role": "user", "content": "Should AI systems be transparent about their reasoning?"},]text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(text, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7, do_sample=True)print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))