GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
roskosmos19
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
roskosmos19
Model Tree
Input Modalities
Output Modalities
Supported Functionality
Rhea-4B-Coding extends Athenea-4B-Coding's structured reasoning capabilities into programming-related domains with multi-pass processing, showing strong performance on logical problem-solving, code completion, debugging scenarios, and iterative code refinement.
Key features:
<think>, <review>, and <final> tags thinking blocksThe model was fine-tuned using the dataset Aquiles-ai/Athenea-Coding-100k, which includes diverse programming challenges, structured reasoning chains, and natural language explanations across multiple programming languages.
The model uses special tokens for structured reasoning:
| Token | Purpose |
|---|---|
<think> | Start of self-review phase (Pass 2) |
</think> | End of self-review phase |
<review> | Start of review results documentation |
</review> | End of review results |
<final> | Start of final optimized version (Pass 3) |
</final> |
This structure ensures identical functionality across all passes while improving code structure, comments, and robustness.
bash
uv pip install transformers torch acceleratepython
from transformers import AutoModelForCausalLM, AutoTokenizerimport torch model = AutoModelForCausalLM.from_pretrained("Roskosmos19/Rhea-4B-Coding", dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", attn_implementation="flash_attention_2") # Requires flash-attn # Without flash-attn:# model = AutoModelForCausalLM.from_pretrained("Roskosmos19/Rhea-4B-Coding",# dtype="auto",# device_map="auto"# ) tokenizer = AutoTokenizer.from_pretrained("Roskosmos19/Rhea-4B-Coding", trust_remote_code=True) messages = [ {"role": "user", "content": "Hey, write a Python function that calculates the factorial of a number recursively."}] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt",).to('cuda') with torch.no_grad(): output = model.generate( **inputs, max_new_tokens=16384, # Increased for multi-pass output pad_token_id=tokenizer.pad_token_id, eos_token_id=tokenizer.eos_token_id, ) # Decode and print the outputprint(tokenizer.decode(output[0], skip_special_tokens=False))python
from transformers import AutoModelForCausalLM, AutoTokenizerimport torch model = AutoModelForCausalLM.from_pretrained("Roskosmos19/Rhea-4B-Coding", dtype=torch.bfloat16, trust_remote_code=True, device_map="auto") tokenizer = AutoTokenizer.from_pretrained("Roskosmos19/Rhea-4B-Coding", trust_remote_code=True) def generate_multi_pass(prompt, max_tokens_per_pass=4096): """ Generate code with 3-pass reasoning: Pass 1: First implementation Pass 2: Self-review Pass 3: Final optimized version """ # Pass 1: First implementation messages = [{"role": "user", "content": prompt}] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to('cuda') with torch.no_grad(): output1 = model.generate( **inputs, max_new_tokens=max_tokens_per_pass, temperature=0.4, pad_token_id=tokenizer.pad_token_id, eos_token_id=tokenizer.eos_token_id, ) pass1 = tokenizer.decode(output1[0], skip_special_tokens=False) # Pass 2: Self-review review_prompt = pass1 + "\n<<think>\n### PASS 2 - Self-Review:\n" inputs2 = tokenizer(review_prompt, return_tensors="pt").to('cuda') with torch.no_grad(): output2 = model.generate( **inputs2, max_new_tokens=2048, temperature=0.3, pad_token_id=tokenizer.pad_token_id, eos_token_id=tokenizer.eos_token_id, ) review = tokenizer.decode(output2[0], skip_special_tokens=False) # Pass 3: Final version final_prompt = review + "\n<<final>\n### PASS 3 - Final Version:\n" inputs3 = tokenizer(final_prompt, return_tensors="pt").to('cuda') with torch.no_grad(): output3 = model.generate( **inputs3, max_new_tokens=max_tokens_per_pass, temperature=0.2, pad_token_id=tokenizer.pad_token_id, eos_token_id=tokenizer.eos_token_id, ) final = tokenizer.decode(output3[0], skip_special_tokens=False) return { "pass1": pass1, "review": review, "pass3": final } # Example usageresult = generate_multi_pass("Write a Python function for binary search")print("=== PASS 1 ===")print(result["pass1"])print("\n=== REVIEW ===")print(result["review"])print("\n=== FINAL ===")print(result["pass3"])python
from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamerimport torchfrom threading import Thread model = AutoModelForCausalLM.from_pretrained("Roskosmos19/Rhea-4B-Coding", dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", attn_implementation="flash_attention_2") tokenizer = AutoTokenizer.from_pretrained("Roskosmos19/Rhea-4B-Coding", trust_remote_code=True) messages = [ {"role": "user", "content": "Hey, write a Python function that implements the binary search algorithm recursively."}] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt",).to('cuda') # Create the streamerstreamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=False) # Build kwargs for generategenerate_kwargs = dict( **inputs, max_new_tokens=16384, # Increased for multi-pass output pad_token_id=tokenizer.pad_token_id, eos_token_id=tokenizer.eos_token_id, streamer=streamer,) def _generate_thread(model, kwargs): with torch.no_grad(): model.generate(**kwargs) thread = Thread(target=_generate_thread, args=(model, generate_kwargs))thread.start() for chunk in streamer: print(chunk, end="", flush=True)Start server:
bash
vllm serve Roskosmos19/Rhea-4B-Coding \ --host 0.0.0.0 \ --port 8000 \ --api-key dummyapikey \ --max-model-len=262144 \ --async-scheduling \ --gpu-memory-utilization=0.90Request to the server from the OpenAI client:
python
from openai import OpenAIclient = OpenAI(api_key="dummyapikey", base_url="http://127.0.0.1:8000/v1")stream = client.chat.completions.create( model="roskosmos19/Rhea-4B-Coding", messages=[{ "role": "user", "content": "Hey, write a Python function that determines if a string is a palindrome, ignoring case, spaces, and punctuation." }], max_tokens=16384, # Increased for multi-pass output stream=True)for chunk in stream: if chunk.choices[0].delta.content: print(chunk.choices[0].delta.content, end="", flush=True)vLLM Benefits: 20-30x faster inference, OpenAI-compatible API, continuous batching, async scheduling.
| Parameter | Value | Description |
|---|---|---|
temperature | 0.4 | Balanced creativity and consistency |
max_new_tokens | 32768 | Full multi-pass output capacity |
repetition_penalty | 1.0 | No penalty for intentional code repetition |
no_repeat_ngram_size | 0 | Allows code structure repetition |
| File | Changes |
|---|---|
generation_config.json | Extended tokens, optimized for multi-pass |
config.json | Enabled caching, full context window |
tokenizer_config.json | Added <think>, <review>, <final> tokens |
special_tokens_map.json | Registered new special tokens |
chat_template.jinja |
| End of final version |
use_cache | true | Faster inference for long outputs |
| 3-pass prompt structure |
uv pip install transformers torch acceleratevllm serve Roskosmos19/Rhea-4B-Coding \ --host 0.0.0.0 \ --port 8000 \ --api-key dummyapikey \ --max-model-len=262144 \ --async-scheduling \ --gpu-memory-utilization=0.90from transformers import AutoModelForCausalLM, AutoTokenizerimport torch model = AutoModelForCausalLM.from_pretrained("Roskosmos19/Rhea-4B-Coding", dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", attn_implementation="flash_attention_2") # Requires flash-attn # Without flash-attn:# model = AutoModelForCausalLM.from_pretrained("Roskosmos19/Rhea-4B-Coding",# dtype="auto",# device_map="auto"# ) tokenizer = AutoTokenizer.from_pretrained("Roskosmos19/Rhea-4B-Coding", trust_remote_code=True) messages = [ {"role": "user", "content": "Hey, write a Python function that calculates the factorial of a number recursively."}] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt",).to('cuda') with torch.no_grad(): output = model.generate( **inputs, max_new_tokens=16384, # Increased for multi-pass output pad_token_id=tokenizer.pad_token_id, eos_token_id=tokenizer.eos_token_id, ) # Decode and print the outputprint(tokenizer.decode(output[0], skip_special_tokens=False))from transformers import AutoModelForCausalLM, AutoTokenizerimport torch model = AutoModelForCausalLM.from_pretrained("Roskosmos19/Rhea-4B-Coding", dtype=torch.bfloat16, trust_remote_code=True, device_map="auto") tokenizer = AutoTokenizer.from_pretrained("Roskosmos19/Rhea-4B-Coding", trust_remote_code=True) def generate_multi_pass(prompt, max_tokens_per_pass=4096): """ Generate code with 3-pass reasoning: Pass 1: First implementation Pass 2: Self-review Pass 3: Final optimized version """ # Pass 1: First implementation messages = [{"role": "user", "content": prompt}] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to('cuda') with torch.no_grad(): output1 = model.generate( **inputs, max_new_tokens=max_tokens_per_pass, temperature=0.4, pad_token_id=tokenizer.pad_token_id, eos_token_id=tokenizer.eos_token_id, ) pass1 = tokenizer.decode(output1[0], skip_special_tokens=False) # Pass 2: Self-review review_prompt = pass1 + "\n<<think>\n### PASS 2 - Self-Review:\n" inputs2 = tokenizer(review_prompt, return_tensors="pt").to('cuda') with torch.no_grad(): output2 = model.generate( **inputs2, max_new_tokens=2048, temperature=0.3, pad_token_id=tokenizer.pad_token_id, eos_token_id=tokenizer.eos_token_id, ) review = tokenizer.decode(output2[0], skip_special_tokens=False) # Pass 3: Final version final_prompt = review + "\n<<final>\n### PASS 3 - Final Version:\n" inputs3 = tokenizer(final_prompt, return_tensors="pt").to('cuda') with torch.no_grad(): output3 = model.generate( **inputs3, max_new_tokens=max_tokens_per_pass, temperature=0.2, pad_token_id=tokenizer.pad_token_id, eos_token_id=tokenizer.eos_token_id, ) final = tokenizer.decode(output3[0], skip_special_tokens=False) return { "pass1": pass1, "review": review, "pass3": final } # Example usageresult = generate_multi_pass("Write a Python function for binary search")print("=== PASS 1 ===")print(result["pass1"])print("\n=== REVIEW ===")print(result["review"])print("\n=== FINAL ===")print(result["pass3"])from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamerimport torchfrom threading import Thread model = AutoModelForCausalLM.from_pretrained("Roskosmos19/Rhea-4B-Coding", dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", attn_implementation="flash_attention_2") tokenizer = AutoTokenizer.from_pretrained("Roskosmos19/Rhea-4B-Coding", trust_remote_code=True) messages = [ {"role": "user", "content": "Hey, write a Python function that implements the binary search algorithm recursively."}] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt",).to('cuda') # Create the streamerstreamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=False) # Build kwargs for generategenerate_kwargs = dict( **inputs, max_new_tokens=16384, # Increased for multi-pass output pad_token_id=tokenizer.pad_token_id, eos_token_id=tokenizer.eos_token_id, streamer=streamer,) def _generate_thread(model, kwargs): with torch.no_grad(): model.generate(**kwargs) thread = Thread(target=_generate_thread, args=(model, generate_kwargs))thread.start() for chunk in streamer: print(chunk, end="", flush=True)from openai import OpenAIclient = OpenAI(api_key="dummyapikey", base_url="http://127.0.0.1:8000/v1")stream = client.chat.completions.create( model="roskosmos19/Rhea-4B-Coding", messages=[{ "role": "user", "content": "Hey, write a Python function that determines if a string is a palindrome, ignoring case, spaces, and punctuation." }], max_tokens=16384, # Increased for multi-pass output stream=True)for chunk in stream: if chunk.choices[0].delta.content: print(chunk.choices[0].delta.content, end="", flush=True)