GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
cs-552-2026-ma-que
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
cs-552-2026-ma-que
Model Tree
Qwen/Qwen3-1.7B-Base
Input Modalities
Output Modalities
Supported Functionality
The group model is produced by task-vector merging (Ilharco et al., 2023),
with no additional training. Each specialist defines a task vector
τ_i = θ_specialist_i − θ_base; the merged weights are
text
θ_group = θ_base + Σ_i λ_i · τ_iThe per-task coefficients λ_i are tuned on held-out validation: Mathematics
benefits from its task vector, while Multilinguality and Safety are kept close to
the base (which already performs best there). This adds each expert's learned
direction back onto the shared Qwen3-1.7B base, so a single checkpoint inherits
all four specialisations while remaining architecturally identical to the base.
Thinking mode is ON. Values below are exactly those in
generation_config.json:
| param | value |
|---|---|
do_sample | true |
temperature | 0.6 |
top_k | 20 |
top_p | 0.95 |
max_new_tokens | not set in generation_config.json; the course CI uses 4096 (nightly) / 16384 (final grading) |
python
from transformers import AutoModelForCausalLM, AutoTokenizer repo = "cs-552-2026-ma-que/group_model"tok = AutoTokenizer.from_pretrained(repo)model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype="auto", device_map="auto") messages = [{"role": "user", "content": "Which planet is known as the Red Planet?\nA) Venus\nB) Mars\nC) Jupiter\nD) Mercury"}]text = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tok(text, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=4096)print(tok.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))text
tokenizer.apply_chat_template(messages, add_generation_prompt=True)generation_config.json.from transformers import AutoModelForCausalLM, AutoTokenizer repo = "cs-552-2026-ma-que/group_model"tok = AutoTokenizer.from_pretrained(repo)model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype="auto", device_map="auto") messages = [{"role": "user", "content": "Which planet is known as the Red Planet?\nA) Venus\nB) Mars\nC) Jupiter\nD) Mercury"}]text = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tok(text, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=4096)print(tok.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))