GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
ai-forever
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
ai-forever
Model Tree
ai-sage/GigaChat3.1-10B-A1.8B-bf16
Input Modalities
Output Modalities
Supported Functionality
MuSiQue answerable validation (bdsaglam/musique), 100 queries mixing the three four-hop topologies: 50 4hop1, 25 4hop2, and 25 4hop3. Ranking is against gold supporting paragraphs at k=10 on a text-deduplicated train+validation FAISS index. Agent runs use temperature 0, retriever_k=100, agent_max_k=10, and at most six searches.
Citation scores the supporting_corpus_ids in the final answer. Search scores the union of documents retrieved over the trajectory. Searches is the mean number of search_index calls per question.
The embedder-only row is a comparison baseline (single top-10 search of the original question, no agent). Agents still call search_index as a tool; that tool uses Qwen3-Embedding-4B (2,560-d).
bash
uv venv --python python3.11 --seed .venvuv pip install -r requirements.txt \ --python .venv/bin/python \ --torch-backend=cu130 \ --index-strategy unsafe-best-matchPackage versions and license information are listed in requirements.txt. The model fits on a single 80 GB GPU.
python
import torchfrom transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig model_name = "ai-forever/SMITH-Exp"tokenizer = AutoTokenizer.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype=torch.bfloat16, device_map="auto",)model.generation_config = GenerationConfig.from_pretrained(model_name)messages = [ {"role": "user", "content": "Which corpus passages support the answer?"}]prompt = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True,)inputs = tokenizer(prompt, return_tensors="pt")inputs = {k: v.to(model.device) for k, v in inputs.items()}outputs = model.generate(**inputs, max_new_tokens=512)prompt_len = inputs["input_ids"].shape[1]print(tokenizer.decode(outputs[0][prompt_len:], skip_special_tokens=True))bash
vllm serve ai-forever/SMITH-Exp \ --trust-remote-code \ --enable-auto-tool-choice \ --tool-call-parser gigachat3 \ --tool-parser-plugin ./gigachat3_guided_decoding.py \ --chat-template ./chat_template.jinja \ --tensor-parallel-size 1 \ --dtype bfloat16bash
curl http://localhost:8000/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{ "model": "ai-forever/SMITH-Exp", "temperature": 0, "tool_choice": "required", "messages": [ {"role": "user", "content": "Which corpus passages support the answer?"} ], "tools": [ { "type": "function", "function": { "name": "search_index", "description": "Search the local semantic index and return relevant text snippets.", "parameters": { "type": "object", "properties": { "query": {"type": "string", "description": "The search query string."}, "k": {"type": "integer", "description": "Optional number of top results to return."} }, "required": ["query"] } } } ] }'uv venv --python python3.11 --seed .venvuv pip install -r requirements.txt \ --python .venv/bin/python \ --torch-backend=cu130 \ --index-strategy unsafe-best-matchimport torchfrom transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig model_name = "ai-forever/SMITH-Exp"tokenizer = AutoTokenizer.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype=torch.bfloat16, device_map="auto",)model.generation_config = GenerationConfig.from_pretrained(model_name)messages = [ {"role": "user", "content": "Which corpus passages support the answer?"}]prompt = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True,)inputs = tokenizer(prompt, return_tensors="pt")inputs = {k: v.to(model.device) for k, v in inputs.items()}outputs = model.generate(**inputs, max_new_tokens=512)prompt_len = inputs["input_ids"].shape[1]print(tokenizer.decode(outputs[0][prompt_len:], skip_special_tokens=True))vllm serve ai-forever/SMITH-Exp \ --trust-remote-code \ --enable-auto-tool-choice \ --tool-call-parser gigachat3 \ --tool-parser-plugin ./gigachat3_guided_decoding.py \ --chat-template ./chat_template.jinja \ --tensor-parallel-size 1 \ --dtype bfloat16curl http://localhost:8000/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{ "model": "ai-forever/SMITH-Exp", "temperature": 0, "tool_choice": "required", "messages": [ {"role": "user", "content": "Which corpus passages support the answer?"} ], "tools": [ { "type": "function", "function": { "name": "search_index", "description": "Search the local semantic index and return relevant text snippets.", "parameters": { "type": "object", "properties": { "query": {"type": "string", "description": "The search query string."}, "k": {"type": "integer", "description": "Optional number of top results to return."} }, "required": ["query"] } } } ] }'