Text Generation
Transformers
Safetensors
English
k2_horizon
k2-horizon
32b
dense
open-weights
ifm
conversational
custom_code
Instructions to use IFM/K2-Horizon-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use IFM/K2-Horizon-32B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="IFM/K2-Horizon-32B", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("IFM/K2-Horizon-32B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use IFM/K2-Horizon-32B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "IFM/K2-Horizon-32B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "IFM/K2-Horizon-32B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/IFM/K2-Horizon-32B
- SGLang
How to use IFM/K2-Horizon-32B 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 "IFM/K2-Horizon-32B" \ --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": "IFM/K2-Horizon-32B", "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 "IFM/K2-Horizon-32B" \ --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": "IFM/K2-Horizon-32B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use IFM/K2-Horizon-32B with Docker Model Runner:
docker model run hf.co/IFM/K2-Horizon-32B
Upload migration_manifest.json to mid_5
Browse files- migration_manifest.json +103 -0
migration_manifest.json
ADDED
|
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"aurora_commit": "e47c5555caa987ded29dba0624d3de1b34cf6162",
|
| 3 |
+
"aurora_repo": "/lustrefs/users/runner/workspace/code/eval360-v2/runtime/eval-runtime/releases/20260825T235203Z-e47c5555caa9-646960/repo/vendor/xllm-dataloader1",
|
| 4 |
+
"completed_utc": "2026-09-02T18:12:39Z",
|
| 5 |
+
"converter": "/lustrefs/users/runner/workspace/code/tools/conversion_aurora2horizon/convert_k2aurora_to_k2horizon.py",
|
| 6 |
+
"horizon_commit": "42ae4f88016b083a8f514655d93521d6af006de9",
|
| 7 |
+
"horizon_repo": "/lustrefs/users/runner/workspace/code/eval360-v2/runtime/eval-runtime/releases/20260825T235203Z-e47c5555caa9-646960/repo/vendor/xllm-dataloader1-horizon",
|
| 8 |
+
"output_checkpoint": "/lustrefs/users/runner/workspace/checkpoints/k2horizon_bf16_safetensors/k2v3-32B_mid5_220B_jais250k_bsz20M_seq512k_lr1.5e-5_constant_wd0.06_rope128/checkpoints/checkpoint_0011000",
|
| 9 |
+
"schema_version": 1,
|
| 10 |
+
"source_checkpoint": "/lustrefs/users/runner/shicheng.wen/eval360-v2/checkpoints/k2aurora_bf16_safetensors/k2v3-32B_mid5_220B_jais250k_bsz20M_seq512k_lr1.5e-5_constant_wd0.06_rope128/checkpoints/checkpoint_0011000",
|
| 11 |
+
"source_hashes": {
|
| 12 |
+
"config.json": "59ecabd1fad81df0727bd88268e46f4acaaf20fbc66eb30e3cd1e5caa12393c0",
|
| 13 |
+
"configuration_k2_aurora.py": "90efba266ef94d3959e7f490e56146da48225e4539cca87ed6fcfea77872ce6d",
|
| 14 |
+
"model.safetensors.index.json": "82de1ea6513d0618e5d6a1b73397a0f2f69d5d31612b083cb998e73ae3386ddd",
|
| 15 |
+
"modeling_k2_aurora.py": "aa6e3ea27c90eca3a88b7fcfaa0aa5235c6ac22e45e33ea4f0a613dc07821924"
|
| 16 |
+
},
|
| 17 |
+
"source_model_type": "k2_aurora",
|
| 18 |
+
"target_hashes": {
|
| 19 |
+
"config.json": "40025dbc5b18f276956fba48f83953f7f5074f29eac12dba1ac767be980ec834",
|
| 20 |
+
"configuration_k2_horizon.py": "5c2f993c1053d9462ebea6dea416c897fddfbb4a5edd904e486936b20d4badc5",
|
| 21 |
+
"model.safetensors.index.json": "82de1ea6513d0618e5d6a1b73397a0f2f69d5d31612b083cb998e73ae3386ddd",
|
| 22 |
+
"modeling_k2_horizon.py": "fb09e010956bd51cfa7d4055b4381cff34c9e06164066b49e3546f38b2e6242f"
|
| 23 |
+
},
|
| 24 |
+
"target_model_type": "k2_horizon",
|
| 25 |
+
"weight_mode": "hardlink",
|
| 26 |
+
"weights": {
|
| 27 |
+
"dtypes": [
|
| 28 |
+
"BF16"
|
| 29 |
+
],
|
| 30 |
+
"filenames": [
|
| 31 |
+
"model-00001-of-00064.safetensors",
|
| 32 |
+
"model-00002-of-00064.safetensors",
|
| 33 |
+
"model-00003-of-00064.safetensors",
|
| 34 |
+
"model-00004-of-00064.safetensors",
|
| 35 |
+
"model-00005-of-00064.safetensors",
|
| 36 |
+
"model-00006-of-00064.safetensors",
|
| 37 |
+
"model-00007-of-00064.safetensors",
|
| 38 |
+
"model-00008-of-00064.safetensors",
|
| 39 |
+
"model-00009-of-00064.safetensors",
|
| 40 |
+
"model-00010-of-00064.safetensors",
|
| 41 |
+
"model-00011-of-00064.safetensors",
|
| 42 |
+
"model-00012-of-00064.safetensors",
|
| 43 |
+
"model-00013-of-00064.safetensors",
|
| 44 |
+
"model-00014-of-00064.safetensors",
|
| 45 |
+
"model-00015-of-00064.safetensors",
|
| 46 |
+
"model-00016-of-00064.safetensors",
|
| 47 |
+
"model-00017-of-00064.safetensors",
|
| 48 |
+
"model-00018-of-00064.safetensors",
|
| 49 |
+
"model-00019-of-00064.safetensors",
|
| 50 |
+
"model-00020-of-00064.safetensors",
|
| 51 |
+
"model-00021-of-00064.safetensors",
|
| 52 |
+
"model-00022-of-00064.safetensors",
|
| 53 |
+
"model-00023-of-00064.safetensors",
|
| 54 |
+
"model-00024-of-00064.safetensors",
|
| 55 |
+
"model-00025-of-00064.safetensors",
|
| 56 |
+
"model-00026-of-00064.safetensors",
|
| 57 |
+
"model-00027-of-00064.safetensors",
|
| 58 |
+
"model-00028-of-00064.safetensors",
|
| 59 |
+
"model-00029-of-00064.safetensors",
|
| 60 |
+
"model-00030-of-00064.safetensors",
|
| 61 |
+
"model-00031-of-00064.safetensors",
|
| 62 |
+
"model-00032-of-00064.safetensors",
|
| 63 |
+
"model-00033-of-00064.safetensors",
|
| 64 |
+
"model-00034-of-00064.safetensors",
|
| 65 |
+
"model-00035-of-00064.safetensors",
|
| 66 |
+
"model-00036-of-00064.safetensors",
|
| 67 |
+
"model-00037-of-00064.safetensors",
|
| 68 |
+
"model-00038-of-00064.safetensors",
|
| 69 |
+
"model-00039-of-00064.safetensors",
|
| 70 |
+
"model-00040-of-00064.safetensors",
|
| 71 |
+
"model-00041-of-00064.safetensors",
|
| 72 |
+
"model-00042-of-00064.safetensors",
|
| 73 |
+
"model-00043-of-00064.safetensors",
|
| 74 |
+
"model-00044-of-00064.safetensors",
|
| 75 |
+
"model-00045-of-00064.safetensors",
|
| 76 |
+
"model-00046-of-00064.safetensors",
|
| 77 |
+
"model-00047-of-00064.safetensors",
|
| 78 |
+
"model-00048-of-00064.safetensors",
|
| 79 |
+
"model-00049-of-00064.safetensors",
|
| 80 |
+
"model-00050-of-00064.safetensors",
|
| 81 |
+
"model-00051-of-00064.safetensors",
|
| 82 |
+
"model-00052-of-00064.safetensors",
|
| 83 |
+
"model-00053-of-00064.safetensors",
|
| 84 |
+
"model-00054-of-00064.safetensors",
|
| 85 |
+
"model-00055-of-00064.safetensors",
|
| 86 |
+
"model-00056-of-00064.safetensors",
|
| 87 |
+
"model-00057-of-00064.safetensors",
|
| 88 |
+
"model-00058-of-00064.safetensors",
|
| 89 |
+
"model-00059-of-00064.safetensors",
|
| 90 |
+
"model-00060-of-00064.safetensors",
|
| 91 |
+
"model-00061-of-00064.safetensors",
|
| 92 |
+
"model-00062-of-00064.safetensors",
|
| 93 |
+
"model-00063-of-00064.safetensors",
|
| 94 |
+
"model-00064-of-00064.safetensors"
|
| 95 |
+
],
|
| 96 |
+
"index_sha256": "82de1ea6513d0618e5d6a1b73397a0f2f69d5d31612b083cb998e73ae3386ddd",
|
| 97 |
+
"logical_bytes": 69558609920,
|
| 98 |
+
"physical_bytes": 69558691048,
|
| 99 |
+
"shards": 64,
|
| 100 |
+
"tensors": 579
|
| 101 |
+
},
|
| 102 |
+
"weights_reencoded": false
|
| 103 |
+
}
|