Instructions to use LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints with Transformers:

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

pipe = pipeline("text-generation", model="LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints

SGLang

How to use LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints 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 "LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints with Docker Model Runner:
```
docker model run hf.co/LLM-OS-Models/KoHRM-Text-1.4B-raw-checkpoints
```

gyung commited on May 25

Commit

060d673

verified ·

1 Parent(s): 2f17c73

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage3-local-terminal-step170000/all_config.yaml +46 -0
stage3-local-terminal-step170000/carry_step_170000.0.pt +3 -0
stage3-local-terminal-step170000/carry_step_170000.1.pt +3 -0
stage3-local-terminal-step170000/carry_step_170000.2.pt +3 -0
stage3-local-terminal-step170000/carry_step_170000.3.pt +3 -0
stage3-local-terminal-step170000/carry_step_170000.4.pt +3 -0
stage3-local-terminal-step170000/carry_step_170000.5.pt +3 -0
stage3-local-terminal-step170000/carry_step_170000.6.pt +3 -0
stage3-local-terminal-step170000/carry_step_170000.7.pt +3 -0
stage3-local-terminal-step170000/fsdp2_step_170000/.metadata +3 -0
stage3-local-terminal-step170000/fsdp2_step_170000/__0_0.distcp +3 -0
stage3-local-terminal-step170000/fsdp2_step_170000/__1_0.distcp +3 -0
stage3-local-terminal-step170000/fsdp2_step_170000/__2_0.distcp +3 -0
stage3-local-terminal-step170000/fsdp2_step_170000/__3_0.distcp +3 -0
stage3-local-terminal-step170000/fsdp2_step_170000/__4_0.distcp +3 -0
stage3-local-terminal-step170000/fsdp2_step_170000/__5_0.distcp +3 -0
stage3-local-terminal-step170000/fsdp2_step_170000/__6_0.distcp +3 -0
stage3-local-terminal-step170000/fsdp2_step_170000/__7_0.distcp +3 -0
stage3-local-terminal-step170000/latest_checkpoint.txt +1 -0
stage3-local-terminal-step170000/step_170000_info.json +8 -0
stage3-local-terminal-step170000/train_metadata.yaml +13 -0
stage3-local-terminal-step170000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -222,3 +222,12 @@ stage2-hrm-full-nocap-final-epoch1/fsdp2_epoch_1/__4_0.distcp filter=lfs diff=lf
 stage2-hrm-full-nocap-final-epoch1/fsdp2_epoch_1/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2-hrm-full-nocap-final-epoch1/fsdp2_epoch_1/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2-hrm-full-nocap-final-epoch1/fsdp2_epoch_1/__5_0.distcp filter=lfs diff=lfs merge=lfs -text

 stage2-hrm-full-nocap-final-epoch1/fsdp2_epoch_1/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2-hrm-full-nocap-final-epoch1/fsdp2_epoch_1/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2-hrm-full-nocap-final-epoch1/fsdp2_epoch_1/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step170000/fsdp2_step_170000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step170000/fsdp2_step_170000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step170000/fsdp2_step_170000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step170000/fsdp2_step_170000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step170000/fsdp2_step_170000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step170000/fsdp2_step_170000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step170000/fsdp2_step_170000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step170000/fsdp2_step_170000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step170000/fsdp2_step_170000/.metadata filter=lfs diff=lfs merge=lfs -text

stage3-local-terminal-step170000/all_config.yaml ADDED Viewed

	@@ -0,0 +1,46 @@

+arch:
+  H_cycles: 2
+  H_override: {}
+  L_cycles: 3
+  bp_max_steps: 5
+  bp_warmup_ratio: 0.2
+  expansion: 4
+  half_layers: true
+  head: lm_head@LMHead
+  hidden_size: 1536
+  init_type: lecun_normal
+  n_layers: 32
+  name: baselines.hrm_nocarry_bp_warmup@HierarchicalReasoningModel
+  norm_eps: 1.0e-06
+  norm_type: pre
+  num_heads: 12
+  pos_emb_type: rope
+  rope_theta: 10000.0
+beta1: 0.9
+beta2: 0.95
+checkpoint_interval: 1
+checkpoint_keep_last: 2
+checkpoint_path: /home/work/.data/hrm_text_checkpoints/KoHRM-Text-1.4B-stage3-local-terminal-gbs180
+checkpoint_step_interval: 10000
+data:
+  path: /home/work/.data/hrm_text_prepared/local_terminal_conversations_ctx9k_resp6k_v1
+  target_only: true
+ema: 0.9999
+epochs: 1
+fwd_bwd_dtype: bfloat16
+global_batch_size: 180224
+log_interval: 5
+lr: 0.00022
+lr_min_ratio: 1.0
+lr_warmup_steps: 2000
+project_name: KoHRM-Text
+resume_epoch: null
+resume_from: /home/work/.data/hrm_text_checkpoints/KoHRM-Text-1.4B-stage2-hrm-full-nocap-gbs180
+resume_step: null
+resume_step_offset: 165617
+run_name: KoHRM-Text-1.4B-stage3-local-terminal
+seed: 0
+skip_batches: 0
+total_steps_override: 465000
+weight_decay: 0.1
+weights_only_resume_from_ema: false

stage3-local-terminal-step170000/carry_step_170000.0.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9e4e753db3afb9502452c588a8d589aef5f763362e89841ca213aabd7ce4e9
+size 1333

stage3-local-terminal-step170000/carry_step_170000.1.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3d85c8cd98992158e978137d1600c22b0fc4631e1af81f5bf1eaed24d1a9a0ad
+size 1333

stage3-local-terminal-step170000/carry_step_170000.2.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:990424dd81f7cbf3ae8b2d78b91673b42c08b41d5597c3543be4382b31076bc7
+size 1333

stage3-local-terminal-step170000/carry_step_170000.3.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f88737a41d3472242b364baafeadd67dd079f860305b282a573cc4a182ccf540
+size 1333

stage3-local-terminal-step170000/carry_step_170000.4.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:31df78a58d6614ebbde42d2bdb009bd7191c38f72b26d79e97988cf1e693939f
+size 1333

stage3-local-terminal-step170000/carry_step_170000.5.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:03d8ffd9c7744acd88dc95951c3d427d45a54bd07d36a0ab8857a4c1f252882d
+size 1333

stage3-local-terminal-step170000/carry_step_170000.6.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:672e825344964a43d98d14205f8c0c4201ceda7948b68f424a1ddc9d4776f029
+size 1333

stage3-local-terminal-step170000/carry_step_170000.7.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:91e9b6bb15dbdbed0c58497e811693c5e9b04dc160c11781b7f861c8247ddd92
+size 1333

stage3-local-terminal-step170000/fsdp2_step_170000/.metadata ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a56e749341c55faea03f088d533ba262b11f4ea1cd1bb521cd3b04d016e8993c
+size 983806

stage3-local-terminal-step170000/fsdp2_step_170000/__0_0.distcp ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c3e428133ce288d219bcf74ede03bea1391505cda822f8b16b7d87e3fe59d140
+size 2769065329

stage3-local-terminal-step170000/fsdp2_step_170000/__1_0.distcp ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:94e469f9547df6fd02957a2cf9a2d8b964253edced9ee32abf29c97227f57c43
+size 2769090643

stage3-local-terminal-step170000/fsdp2_step_170000/__2_0.distcp ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2c4188d1877d6128efac8860dd844854f5e2755cfe1f1667dc14698a38875121
+size 2769090643

stage3-local-terminal-step170000/fsdp2_step_170000/__3_0.distcp ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f552bfa8d5e92e87582f1524f8f7c844071490b380c91078b051447577720f03
+size 2769090643

stage3-local-terminal-step170000/fsdp2_step_170000/__4_0.distcp ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1070a60c8b37f24fa3ffb794422e1517860bd555ed38fb76199ed08442d75c1b
+size 2769090643

stage3-local-terminal-step170000/fsdp2_step_170000/__5_0.distcp ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:566aad994946f3805d24cbe5b9599edf657ecd34f34a12ce1acaed3a8220ffaa
+size 2769090643

stage3-local-terminal-step170000/fsdp2_step_170000/__6_0.distcp ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:267f558ec2030cb7e17244f1f6b3d5d70e7e9b6a7ecf05c3dbd7fa526cf96d1c
+size 2769091588

stage3-local-terminal-step170000/fsdp2_step_170000/__7_0.distcp ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d6e5ec8c5328943dfc99ba0a68c5a22b9054a16c87199688be9b78aa94422a7b
+size 2769098756

stage3-local-terminal-step170000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_170000

stage3-local-terminal-step170000/step_170000_info.json ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+  "tag": "step_170000",
+  "global_step": 170000,
+  "stage_start_step": 165617,
+  "skip_batches_hint": 4383,
+  "data_path": "/home/work/.data/hrm_text_prepared/local_terminal_conversations_ctx9k_resp6k_v1",
+  "global_batch_size": 180224
+}

stage3-local-terminal-step170000/train_metadata.yaml ADDED Viewed

	@@ -0,0 +1,13 @@

+max_seq_len: 4096
+tokenizer_info:
+  boq: <|im_start|>
+  condition_mapping:
+    cot: <|object_ref_end|>
+    direct: <|object_ref_start|>
+    noisy: <|quad_start|>
+    synth: <|quad_end|>
+  eoa: <|box_end|>
+  eoq: <|im_end|>
+  tokenizer_path: /home/work/.data/hrm_text_prepared/local_terminal_conversations_ctx9k_resp6k_v1
+total_length: 9386532467
+vocab_size: 131072

stage3-local-terminal-step170000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage3 local-terminal step_170000 raw resume checkpoint