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

f34b5a3

verified ·

1 Parent(s): f5d23c6

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage3-local-terminal-step190000/all_config.yaml +46 -0
stage3-local-terminal-step190000/carry_step_190000.0.pt +3 -0
stage3-local-terminal-step190000/carry_step_190000.1.pt +3 -0
stage3-local-terminal-step190000/carry_step_190000.2.pt +3 -0
stage3-local-terminal-step190000/carry_step_190000.3.pt +3 -0
stage3-local-terminal-step190000/carry_step_190000.4.pt +3 -0
stage3-local-terminal-step190000/carry_step_190000.5.pt +3 -0
stage3-local-terminal-step190000/carry_step_190000.6.pt +3 -0
stage3-local-terminal-step190000/carry_step_190000.7.pt +3 -0
stage3-local-terminal-step190000/fsdp2_step_190000/.metadata +3 -0
stage3-local-terminal-step190000/fsdp2_step_190000/__0_0.distcp +3 -0
stage3-local-terminal-step190000/fsdp2_step_190000/__1_0.distcp +3 -0
stage3-local-terminal-step190000/fsdp2_step_190000/__2_0.distcp +3 -0
stage3-local-terminal-step190000/fsdp2_step_190000/__3_0.distcp +3 -0
stage3-local-terminal-step190000/fsdp2_step_190000/__4_0.distcp +3 -0
stage3-local-terminal-step190000/fsdp2_step_190000/__5_0.distcp +3 -0
stage3-local-terminal-step190000/fsdp2_step_190000/__6_0.distcp +3 -0
stage3-local-terminal-step190000/fsdp2_step_190000/__7_0.distcp +3 -0
stage3-local-terminal-step190000/latest_checkpoint.txt +1 -0
stage3-local-terminal-step190000/step_190000_info.json +8 -0
stage3-local-terminal-step190000/train_metadata.yaml +13 -0
stage3-local-terminal-step190000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -240,3 +240,12 @@ stage3-local-terminal-step180000/fsdp2_step_180000/__5_0.distcp filter=lfs diff=
 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/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-step190000/fsdp2_step_190000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step190000/fsdp2_step_190000/.metadata filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step190000/fsdp2_step_190000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step190000/fsdp2_step_190000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step190000/fsdp2_step_190000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step190000/fsdp2_step_190000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step190000/fsdp2_step_190000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step190000/fsdp2_step_190000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3-local-terminal-step190000/fsdp2_step_190000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text

stage3-local-terminal-step190000/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-step190000/carry_step_190000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:53025234e5fe1cde561088cf11054ebf1658b27e09e17768846447ae359ebfcb
+size 1333

stage3-local-terminal-step190000/carry_step_190000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e693c32118ebb4ee09a3506b9cd83dd0933bebc335bcba1075cc9167822a0322
+size 1333

stage3-local-terminal-step190000/carry_step_190000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:dbf69d3e078c701bfcb79fda7744dd364567a7f612d4d6d24133208a27ea54eb
+size 1333

stage3-local-terminal-step190000/carry_step_190000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1e7ac45f725896960d3b6d8e06d91f88a79b36810b487c40c9365f224a31f868
+size 1333

stage3-local-terminal-step190000/carry_step_190000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9f0e775b2908913e7f156d75d78c9de5b93e17987063278bdbf4e9ce5c2ca7e1
+size 1333

stage3-local-terminal-step190000/carry_step_190000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:be1ee7fbb9062a225d1268c38b1ca7cd59bd9e3e2bd1299c089f3d8ac56886b8
+size 1333

stage3-local-terminal-step190000/carry_step_190000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a966e81d9b5a994386ed4ebc3d4f25dd071abc42be1e32e311380fd903b5b8c4
+size 1333

stage3-local-terminal-step190000/carry_step_190000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d53b48e1216844a8635c84cf2d82982664f6d968a60a1315c6c0a3ab9d2fc888
+size 1333

stage3-local-terminal-step190000/fsdp2_step_190000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:315dcb6f6b074d6c8c90be3540d3784295275d36edfae0823a3af1e070382a69
+size 983806

stage3-local-terminal-step190000/fsdp2_step_190000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:31e1fd5e9b9f6394019312109399a856d4b143908a5d4c5e8817aca6df6622ae
+size 2769065329

stage3-local-terminal-step190000/fsdp2_step_190000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:888bb145af702d28fa1f36976d6e2d8066ec17debb7c07fdf8771da70e7ef72b
+size 2769090643

stage3-local-terminal-step190000/fsdp2_step_190000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4801e923ca0fb295d2498863e4e3ed34fbae26d25e6adbc25bfe3f8947927dea
+size 2769090643

stage3-local-terminal-step190000/fsdp2_step_190000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:fd3565448c696d6d2753e5161e31e12f5197912f56c4cc2156e2f0b38c6d83e5
+size 2769090643

stage3-local-terminal-step190000/fsdp2_step_190000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:615504e3b6a19eb4d93db80e1ea79e53313eff54972696a56546ca352a5dcbdc
+size 2769090643

stage3-local-terminal-step190000/fsdp2_step_190000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0ec656977d9869a668d4a8d16d3289066b243271560b496d8e0f4459097364fa
+size 2769090643

stage3-local-terminal-step190000/fsdp2_step_190000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f2a16c2cc836d034cbdf3671a1a4a947f01fb897077cdb24818a1e51ff3d1f0b
+size 2769091588

stage3-local-terminal-step190000/fsdp2_step_190000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d791797260a7e7fb374e4918537374bd2d64d55e53eb247912010d9f9e1bd268
+size 2769098756

stage3-local-terminal-step190000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_190000

stage3-local-terminal-step190000/step_190000_info.json ADDED Viewed

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

+{
+  "tag": "step_190000",
+  "global_step": 190000,
+  "stage_start_step": 165617,
+  "skip_batches_hint": 24383,
+  "data_path": "/home/work/.data/hrm_text_prepared/local_terminal_conversations_ctx9k_resp6k_v1",
+  "global_batch_size": 180224
+}

stage3-local-terminal-step190000/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-step190000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage3-local-terminal step_190000 raw resume checkpoint