GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Pranavz
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Pranavz
Model Tree
Qwen/Qwen3-4B-Instruct-2507
Input Modalities
Output Modalities
Supported Functionality
| Parameter | Value |
|---|---|
| direction_index | 2.70 |
| attn.o_proj.max_weight | 1.57 |
| attn.o_proj.max_weight_position | 22.89 |
| attn.o_proj.min_weight | 0.55 |
| attn.o_proj.min_weight_distance | 14.96 |
| mlp.down_proj.max_weight | 3.04 |
| mlp.down_proj.max_weight_position | 6.98 |
| mlp.down_proj.min_weight | 2.70 |
| mlp.down_proj.min_weight_distance | 27.82 |
| Metric | This model | Original model (Pranavz/qwen-4b-2507-rp-mahou) |
|---|---|---|
| KL divergence | 10.1157 | 0 (by definition) |
| Refusals | 0/100 | 99/100 |
A full-parameter SFT of Qwen/Qwen3-4B-Instruct-2507 on flammenai/flame-kindling-v1 for creative roleplay and character interaction.
enable_thinking=False for RP)python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer MODEL_ID = "Pranavz/qwen-4b-2507-rp-mahou" tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)model = AutoModelForCausalLM.from_pretrained( MODEL_ID, torch_dtype=torch.bfloat16, device_map="auto",) messages = [ {"role": "system", "content": "You are a creative roleplay assistant. Stay in character, write vividly, and use asterisks for actions."}, {"role": "user", "content": "*walks into the tavern, shaking off the rain* Evening, barkeep. Got a room?"},] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, enable_thinking=False,)inputs = tokenizer(text, return_tensors="pt").to(model.device) with torch.inference_mode(): out = model.generate( **inputs, max_new_tokens=512, temperature=0.8, top_p=0.9, top_k=40, repetition_penalty=1.1, do_sample=True, ) print(tokenizer.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))| Parameter | Value | Notes |
|---|---|---|
temperature | 0.7 – 0.85 | creative without going off-rails |
top_p | 0.9 | trim the long tail |
top_k | 40 | hard vocab cap |
min_p | 0.05 | optional, often nicer than top_p alone |
repetition_penalty | 1.05 – 1.15 | RP models love loops — kill them |
max_new_tokens | 512 – 1024 | RP needs room |
Always pass enable_thinking=False to the chat template — RP doesn't want CoT.
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer MODEL_ID = "Pranavz/qwen-4b-2507-rp-mahou" tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)model = AutoModelForCausalLM.from_pretrained( MODEL_ID, torch_dtype=torch.bfloat16, device_map="auto",) messages = [ {"role": "system", "content": "You are a creative roleplay assistant. Stay in character, write vividly, and use asterisks for actions."}, {"role": "user", "content": "*walks into the tavern, shaking off the rain* Evening, barkeep. Got a room?"},] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, enable_thinking=False,)inputs = tokenizer(text, return_tensors="pt").to(model.device) with torch.inference_mode(): out = model.generate( **inputs, max_new_tokens=512, temperature=0.8, top_p=0.9, top_k=40, repetition_penalty=1.1, do_sample=True, ) print(tokenizer.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))