Instructions to use Avifenesh/k2h-r1a-final with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Avifenesh/k2h-r1a-final with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Avifenesh/k2h-r1a-final", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Avifenesh/k2h-r1a-final", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Avifenesh/k2h-r1a-final with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Avifenesh/k2h-r1a-final"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Avifenesh/k2h-r1a-final",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Avifenesh/k2h-r1a-final

SGLang

How to use Avifenesh/k2h-r1a-final with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Avifenesh/k2h-r1a-final" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Avifenesh/k2h-r1a-final",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Avifenesh/k2h-r1a-final" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Avifenesh/k2h-r1a-final",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Avifenesh/k2h-r1a-final with Docker Model Runner:
```
docker model run hf.co/Avifenesh/k2h-r1a-final
```

K2H R1a final (step 800)

Continued pretraining of IFM/K2-Horizon-MoVA-36B-A4B toward LLM inference and ML systems engineering. Code and domain text improved; general skills, instruction following and tool calling stay level with the release.

Published 2026-11-07. This is the last checkpoint of the run that passes every gate below, tool calling included.

Model

Base: IFM/K2-Horizon-MoVA-36B-A4B (36B total, about 4B active, MoE). Same architecture, tokenizer and chat template.
Weights: bf16 safetensors. Load with trust_remote_code=True. Context limit as the release (524,288).
Sampling as the base model card recommends: temperature 1.0, top_p 0.95.

Training

Trainer: xLLM, FSDP2, bf16, 3 GPUs, optimizer state offloaded to host memory.
Start: the released weights. 800 steps, sequence length 65,536, about 786k tokens per step, about 629M tokens.
AdamW (0.9, 0.95), weight decay 0.06, gradient clip 1.0. Learning rate 5e-6, 20 warmup steps, then constant.
Data mix (sampling weights):
- 40%: clean domain data: inference and kernel repositories, Linux, commit history (Avifenesh/k2h-corpus-domain-clean), plus PR discussions and engineering receipts that are not published.
- 50%: script-verified replay as plain text (Avifenesh/k2h-replay-verified).
- 10%: verified chat (reasoning, instruction and Q&A sets from Avifenesh/k2h-chat-reasoning-verified) used only as a release anchor: a hinged KL(release || model) on their reply tokens (tau 0.05), no cross-entropy. From step 600 the math replay also carries the anchor next to its cross-entropy.
- The anchor reads the release's top-64 log-probabilities from a precomputed cache, so no teacher runs during training.

Evaluation

Paired per question against the release, same prompts and sampling. A checkpoint passes when no task in the family below drops significantly after Holm correction, pooled IFEval (two runs) is not more than 2 points down at p < 0.05, chat GSM8K is not more than 1.5 points down, and MMLU is not 1 point or more down at p < 0.05.

Task	Release	Step 800	p
IFEval prompt-strict, reasoning on, 2 runs pooled	83.7	84.7	0.47
GSM8K chat, reasoning on	96.6	96.2	0.41
MATH-500 chat, reasoning on	98.2	97.4	0.34
MMLU	77.3	76.7	0.18
ARC-Challenge	57.6	57.9	0.63
BoolQ	88.4	88.4	1.0
MBPP pass@1	65.2	70.6	0.0009
HumanEval pass@1	53.1	66.5	0.002
BFCL V4 live_multiple	75.0	72.5	0.03
BFCL V4 irrelevance	87.5	86.7	0.79
BFCL V4 all live categories	76.9	76.1	0.35
Held-out PR NLL (lower is better)	1.520	1.280

Long context (RULER, 13 tasks, 8 samples per task per length, paired with the release):

Length	Release	Step 800	p
32k	89.9	86.4	0.36
64k	88.5	87.4	1.0
128k	76.3	80.3	0.17

Measured again on 2026-11-08 with 24 samples per task (paired, 312 items per length): 32k 85.3 vs 90.4 (-5.1, p = 0.01), 64k 86.0 vs 87.2 (-1.2, p = 0.26). Long-context retrieval at 32k is a few points weaker than the release. Avifenesh/k2h-s1-final has no significant long-context drop and is the newer model.

Passkey retrieval at 16k to 131k context: 5/5 at every length, as the release.

Few-shot GSM8K (5-shot completion) drops 2.4 points (90.2 to 87.9). Chat GSM8K and MATH-500 hold, so this reads as drift in the few-shot completion format, not in math.

Step 1000 of the same run scores a little higher on the general tasks and on PR NLL (1.273), but BFCL live_multiple drops 3.6 points (p = 0.0015), so it is not the final checkpoint.

Downloads last month: 966

Safetensors

Model size

37B params

Tensor type

BF16

Model tree for Avifenesh/k2h-r1a-final

Base model

IFM/K2-Horizon-MoVA-36B-A4B

Finetuned

(14)

this model