GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
oleh13
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
oleh13
Model Tree
Qwen/Qwen2.5-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
This model is intended for structured retrosynthesis assistance:
Use RDKit or another chemistry toolkit to validate generated SMILES before acting on model output.
Use explicit task labels and request JSON only. Low temperature is recommended for repeatable API calls.
text
System: You are a retrosynthesis assistant. Return valid JSON only.User: Task: predict_reactantsProduct SMILES: CC(=O)Oc1ccccc1C(=O)OReturn JSON with keys: reactants_smiles, confidence, rationale.text
System: You are a reaction condition assistant. Return valid JSON only.User: Task: predict_conditionsProduct SMILES: CC(=O)Oc1ccccc1C(=O)OReactants SMILES: CC(=O)O.Oc1ccccc1C(=O)OReturn JSON with keys: solvent, reagents, catalyst, temperature_celsius, time, confidence, rationale.text
System: You are a retrosynthesis assistant. Return valid JSON only.User: Task: retrosynthesis_stepTarget product SMILES: CC(=O)Oc1ccccc1C(=O)OReturn one JSON object with keys: reactants_smiles, conditions, confidence, rationale.python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "<your-namespace>/retro-agent-qwen25-7b-merged-fp16" tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.float16, device_map="auto", trust_remote_code=True,) messages = [ {"role": "system", "content": "You are a retrosynthesis assistant. Return valid JSON only."}, {"role": "user", "content": "Task: retrosynthesis_step\nTarget product SMILES: CC(=O)Oc1ccccc1C(=O)O\nReturn one JSON object with keys: reactants_smiles, conditions, confidence, rationale."},] text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(text, return_tensors="pt").to(model.device) with torch.no_grad(): output_ids = model.generate( **inputs, max_new_tokens=512, temperature=0.1, do_sample=False, ) new_tokens = output_ids[0][inputs.input_ids.shape[-1]:]print(tokenizer.decode(new_tokens, skip_special_tokens=True))This works only if the model is available through Hugging Face Inference Providers. For custom merged models, a dedicated endpoint is often more reliable.
bash
export HF_TOKEN=hf_... curl https://router.huggingface.co/v1/chat/completions \ -H "Authorization: Bearer $HF_TOKEN" \ -H "Content-Type: application/json" \ -d '{ "model": "<your-namespace>/retro-agent-qwen25-7b-merged-fp16", "messages": [ {"role": "system", "content": "You are a retrosynthesis assistant. Return valid JSON only."}, {"role": "user", "content": "Task: retrosynthesis_step\nTarget product SMILES: CC(=O)Oc1ccccc1C(=O)O"} ], "temperature": 0.1, "max_tokens": 512, "stream": false }'Create a dedicated endpoint from this model repository, then call the endpoint URL directly.
bash
export HF_TOKEN=hf_...export ENDPOINT_URL=https://<your-endpoint>.<region>.<provider>.endpoints.huggingface.cloud curl "$ENDPOINT_URL" \ -X POST \ -H "Authorization: Bearer $HF_TOKEN" \ -H "Content-Type: application/json" \ -d '{ "inputs": "Task: retrosynthesis_step\nTarget product SMILES: CC(=O)Oc1ccccc1C(=O)O\nReturn one JSON object with keys: reactants_smiles, conditions, confidence, rationale.", "parameters": { "max_new_tokens": 512, "temperature": 0.1, "return_full_text": false } }'This model merges adapters trained for related but distinct tasks. Evaluate both reactant prediction and condition prediction after merge, because independently trained LoRA adapters can interfere with each other.
System: You are a retrosynthesis assistant. Return valid JSON only.User: Task: predict_reactantsProduct SMILES: CC(=O)Oc1ccccc1C(=O)OReturn JSON with keys: reactants_smiles, confidence, rationale.System: You are a reaction condition assistant. Return valid JSON only.User: Task: predict_conditionsProduct SMILES: CC(=O)Oc1ccccc1C(=O)OReactants SMILES: CC(=O)O.Oc1ccccc1C(=O)OReturn JSON with keys: solvent, reagents, catalyst, temperature_celsius, time, confidence, rationale.System: You are a retrosynthesis assistant. Return valid JSON only.User: Task: retrosynthesis_stepTarget product SMILES: CC(=O)Oc1ccccc1C(=O)OReturn one JSON object with keys: reactants_smiles, conditions, confidence, rationale.import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "<your-namespace>/retro-agent-qwen25-7b-merged-fp16" tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.float16, device_map="auto", trust_remote_code=True,) messages = [ {"role": "system", "content": "You are a retrosynthesis assistant. Return valid JSON only."}, {"role": "user", "content": "Task: retrosynthesis_step\nTarget product SMILES: CC(=O)Oc1ccccc1C(=O)O\nReturn one JSON object with keys: reactants_smiles, conditions, confidence, rationale."},] text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(text, return_tensors="pt").to(model.device) with torch.no_grad(): output_ids = model.generate( **inputs, max_new_tokens=512, temperature=0.1, do_sample=False, ) new_tokens = output_ids[0][inputs.input_ids.shape[-1]:]print(tokenizer.decode(new_tokens, skip_special_tokens=True))export HF_TOKEN=hf_... curl https://router.huggingface.co/v1/chat/completions \ -H "Authorization: Bearer $HF_TOKEN" \ -H "Content-Type: application/json" \ -d '{ "model": "<your-namespace>/retro-agent-qwen25-7b-merged-fp16", "messages": [ {"role": "system", "content": "You are a retrosynthesis assistant. Return valid JSON only."}, {"role": "user", "content": "Task: retrosynthesis_step\nTarget product SMILES: CC(=O)Oc1ccccc1C(=O)O"} ], "temperature": 0.1, "max_tokens": 512, "stream": false }'export HF_TOKEN=hf_...export ENDPOINT_URL=https://<your-endpoint>.<region>.<provider>.endpoints.huggingface.cloud curl "$ENDPOINT_URL" \ -X POST \ -H "Authorization: Bearer $HF_TOKEN" \ -H "Content-Type: application/json" \ -d '{ "inputs": "Task: retrosynthesis_step\nTarget product SMILES: CC(=O)Oc1ccccc1C(=O)O\nReturn one JSON object with keys: reactants_smiles, conditions, confidence, rationale.", "parameters": { "max_new_tokens": 512, "temperature": 0.1, "return_full_text": false } }'