Instructions to use Avifenesh/k2h-main-step900 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Avifenesh/k2h-main-step900 with Transformers:

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

pipe = pipeline("text-generation", model="Avifenesh/k2h-main-step900", 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-main-step900", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Avifenesh/k2h-main-step900 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Avifenesh/k2h-main-step900"
# 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-main-step900",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Avifenesh/k2h-main-step900

SGLang

How to use Avifenesh/k2h-main-step900 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-main-step900" \
    --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-main-step900",
		"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-main-step900" \
        --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-main-step900",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Avifenesh/k2h-main-step900 with Docker Model Runner:
```
docker model run hf.co/Avifenesh/k2h-main-step900
```

K2H main run, step 900

Step 900 of a planned 7,391-step continued-pretraining run on IFM/K2-Horizon-MoVA-36B-A4B. The run was stopped here because general skills were drifting down; the shorter clean-data arms (k2h-c1-clean, k2h-c2-sft, k2h-c4-ctrl) followed.

Research checkpoint, published 2026-11-03. It is not a release candidate. Compare it with the release, not in isolation.

Model

Base: IFM/K2-Horizon-MoVA-36B-A4B (36B total, about 4B active, MoE). Same architecture, tokenizer and chat template.
Weights: bf16 safetensors. The custom modeling code ships with the weights, so load with trust_remote_code=True.
Sampling as the base model card recommends: temperature 1.0, top_p 0.95.

Training

Trainer: xLLM, FSDP2, bf16, 3 GPUs.
Start: the released weights of IFM/K2-Horizon-MoVA-36B-A4B.
900 steps of a planned 7,391. Sequence length 32,768, about 786k tokens per step, about 0.71B tokens in total.
AdamW, beta1 0.9, beta2 0.95, weight decay 0.06, gradient clip 1.0.
Learning rate 1.5e-5, 100 warmup steps, warmup-stable-decay schedule (stopped in the stable phase).

Data mix (sampling weights):

Domain code, commits, pull requests and papers before the verification pass, plus synthetic and web replay, a math slice and a small TxT360 instruct share.
The cleaned code and commit slices are in Avifenesh/k2h-corpus-domain-clean. The web replay is in Avifenesh/k2h-sources-unverified.

Evaluation

All numbers come from the same harness as the release column (lm-evaluation-harness against a vLLM server). IFEval and chat GSM8K use the chat template with reasoning on, temperature 1.0, top_p 0.95, 14,336 new tokens, and score only the text after the reasoning block. The PR NLL is the mean token NLL on 150 held-out pull requests (530k tokens).

Task	Release	This model	Change
GSM8K, 5-shot, strict	90.1	84.6	-5.5
GSM8K, chat zero-shot (reasoning on)	96.6	not measured
IFEval, prompt-strict (reasoning on)	84.3	71.2	-13.1
MMLU	77.3	76.0	-1.3
ARC-Challenge	57.6	56.4	-1.2
ARC-Easy	85.6	85.3	-0.3
BoolQ	88.4	87.5	-0.9
HellaSwag (norm)	67.6	67.5	-0.1
PIQA	80.5	81.0	+0.5
WinoGrande	69.1	70.6	+1.5
MBPP pass@1	65.2	69.6	+4.4
HumanEval pass@1 (4 samples)	53.0	63.4	+10.4
Held-out PR NLL (lower is better)	1.519	1.173	-0.346

What the numbers say:

The held-out PR NLL drops from 1.519 to 1.173: the domain gain is large.
General skills drift down: GSM8K -5.5, IFEval -13.1, MMLU -1.3, ARC-Challenge -1.2. Coding goes up (MBPP +4.4, HumanEval +10.4).
Chat-format GSM8K was not measured for this checkpoint.
The full training state (with optimizer) is in Avifenesh/k2h-ckpt900-xllm.

License

Apache-2.0, the license of the base model.

Downloads last month: 332

Safetensors

Model size

37B params

Tensor type

BF16

Model tree for Avifenesh/k2h-main-step900

Base model

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

Finetuned

(12)

this model