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

f5d23c6

verified ·

1 Parent(s): 060d673

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage3-local-terminal-step180000/all_config.yaml +46 -0
stage3-local-terminal-step180000/carry_step_180000.0.pt +3 -0
stage3-local-terminal-step180000/carry_step_180000.1.pt +3 -0
stage3-local-terminal-step180000/carry_step_180000.2.pt +3 -0
stage3-local-terminal-step180000/carry_step_180000.3.pt +3 -0
stage3-local-terminal-step180000/carry_step_180000.4.pt +3 -0
stage3-local-terminal-step180000/carry_step_180000.5.pt +3 -0
stage3-local-terminal-step180000/carry_step_180000.6.pt +3 -0
stage3-local-terminal-step180000/carry_step_180000.7.pt +3 -0
stage3-local-terminal-step180000/fsdp2_step_180000/.metadata +3 -0
stage3-local-terminal-step180000/fsdp2_step_180000/__0_0.distcp +3 -0
stage3-local-terminal-step180000/fsdp2_step_180000/__1_0.distcp +3 -0
stage3-local-terminal-step180000/fsdp2_step_180000/__2_0.distcp +3 -0
stage3-local-terminal-step180000/fsdp2_step_180000/__3_0.distcp +3 -0
stage3-local-terminal-step180000/fsdp2_step_180000/__4_0.distcp +3 -0
stage3-local-terminal-step180000/fsdp2_step_180000/__5_0.distcp +3 -0
stage3-local-terminal-step180000/fsdp2_step_180000/__6_0.distcp +3 -0
stage3-local-terminal-step180000/fsdp2_step_180000/__7_0.distcp +3 -0
stage3-local-terminal-step180000/latest_checkpoint.txt +1 -0
stage3-local-terminal-step180000/step_180000_info.json +8 -0
stage3-local-terminal-step180000/train_metadata.yaml +13 -0
stage3-local-terminal-step180000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -231,3 +231,12 @@ stage3-local-terminal-step170000/fsdp2_step_170000/__4_0.distcp filter=lfs diff=
 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/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-step180000/fsdp2_step_180000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step180000/fsdp2_step_180000/.metadata filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step180000/fsdp2_step_180000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step180000/fsdp2_step_180000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step180000/fsdp2_step_180000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step180000/fsdp2_step_180000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step180000/fsdp2_step_180000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step180000/fsdp2_step_180000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step180000/fsdp2_step_180000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text

stage3-local-terminal-step180000/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-step180000/carry_step_180000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9b9fa740b5f160099bb358a8237c5334016056bc5669a104919aab157d698b20
+size 1333

stage3-local-terminal-step180000/carry_step_180000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:fe5955230573754577d6a97b0ec1e70df7c6b6121c41d5674d2fa47a3cf49547
+size 1333

stage3-local-terminal-step180000/carry_step_180000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:033c37a9ee261e8666170bebeae9da3638ba15d5475b08d4307c162487333b53
+size 1333

stage3-local-terminal-step180000/carry_step_180000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1c2fe0718c20cbb8ef155d36f8c487393beb0c5cbcd6ba37d98a1f8458b3ae60
+size 1333

stage3-local-terminal-step180000/carry_step_180000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9d45e563b1d33e3dc9196317bbc2a13bf451eee79a335748bb963b3a07714b6b
+size 1333

stage3-local-terminal-step180000/carry_step_180000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5bf5e4cdc9a878db664eee399cbb71d2fece0b9309637be4e1fc663b554515b6
+size 1333

stage3-local-terminal-step180000/carry_step_180000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8276cc6db02d2c9be5eee52892881b652494c84ba5731f628176171574aa7820
+size 1333

stage3-local-terminal-step180000/carry_step_180000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:35ded5b1149535cc07e5b66a35ee405b30dd9c3f8d1375b2b829e8a486b62874
+size 1333

stage3-local-terminal-step180000/fsdp2_step_180000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b148b0e597a9fb576277e1e3ce192023fbca8ff107da7d1ad16acdcd78bed68c
+size 983806

stage3-local-terminal-step180000/fsdp2_step_180000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1947139db6981a5d146e59175c278cf300c13905b09183e7174c652f7084cd31
+size 2769065329

stage3-local-terminal-step180000/fsdp2_step_180000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0f487a7a552d24dd9a789ff078c3ee27fdc752c2546c2b474933080a25df633e
+size 2769090643

stage3-local-terminal-step180000/fsdp2_step_180000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:beba4d2a3ac6f52c6afba6d2cb11c14ba0033ebd269f525a07138cf329b88cd3
+size 2769090643

stage3-local-terminal-step180000/fsdp2_step_180000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0187b87fd6703e085f2df408dc9aca0781264efd03da33b6f48f33825c4a5751
+size 2769090643

stage3-local-terminal-step180000/fsdp2_step_180000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3c6b31675a83f82c5c271a1c1f6e7ac7c9a70c5a1f57e2286cfd5882482d65b6
+size 2769090643

stage3-local-terminal-step180000/fsdp2_step_180000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4223a535041c7a7df544e6c0b8cde877ddd9d833a08a6ddc78045da2c11a42e6
+size 2769090643

stage3-local-terminal-step180000/fsdp2_step_180000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:dd8e26fff307a0f9765b47b87340442e820873f681d8c6d01949979053e64109
+size 2769091588

stage3-local-terminal-step180000/fsdp2_step_180000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:cd6355ac1ac4028608a729df0a51fd228de835d133e50c2a81ef478fd5d86230
+size 2769098756

stage3-local-terminal-step180000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_180000

stage3-local-terminal-step180000/step_180000_info.json ADDED Viewed

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

+{
+  "tag": "step_180000",
+  "global_step": 180000,
+  "stage_start_step": 165617,
+  "skip_batches_hint": 14383,
+  "data_path": "/home/work/.data/hrm_text_prepared/local_terminal_conversations_ctx9k_resp6k_v1",
+  "global_batch_size": 180224
+}

stage3-local-terminal-step180000/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-step180000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage3-local-terminal step_180000 raw resume checkpoint