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 28

Commit

055efe0

verified ·

1 Parent(s): 8cd28d5

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage3b-local-terminal-repeat-step430000/all_config.yaml +46 -0
stage3b-local-terminal-repeat-step430000/carry_step_430000.0.pt +3 -0
stage3b-local-terminal-repeat-step430000/carry_step_430000.1.pt +3 -0
stage3b-local-terminal-repeat-step430000/carry_step_430000.2.pt +3 -0
stage3b-local-terminal-repeat-step430000/carry_step_430000.3.pt +3 -0
stage3b-local-terminal-repeat-step430000/carry_step_430000.4.pt +3 -0
stage3b-local-terminal-repeat-step430000/carry_step_430000.5.pt +3 -0
stage3b-local-terminal-repeat-step430000/carry_step_430000.6.pt +3 -0
stage3b-local-terminal-repeat-step430000/carry_step_430000.7.pt +3 -0
stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/.metadata +3 -0
stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/__0_0.distcp +3 -0
stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/__1_0.distcp +3 -0
stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/__2_0.distcp +3 -0
stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/__3_0.distcp +3 -0
stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/__4_0.distcp +3 -0
stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/__5_0.distcp +3 -0
stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/__6_0.distcp +3 -0
stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/__7_0.distcp +3 -0
stage3b-local-terminal-repeat-step430000/latest_checkpoint.txt +1 -0
stage3b-local-terminal-repeat-step430000/step_430000_info.json +8 -0
stage3b-local-terminal-repeat-step430000/train_metadata.yaml +13 -0
stage3b-local-terminal-repeat-step430000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -528,3 +528,12 @@ stage3b-local-terminal-repeat-step420000/fsdp2_step_420000/__1_0.distcp filter=l
 stage3b-local-terminal-repeat-step420000/fsdp2_step_420000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage3b-local-terminal-repeat-step420000/fsdp2_step_420000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage3b-local-terminal-repeat-step420000/fsdp2_step_420000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text

 stage3b-local-terminal-repeat-step420000/fsdp2_step_420000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage3b-local-terminal-repeat-step420000/fsdp2_step_420000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage3b-local-terminal-repeat-step420000/fsdp2_step_420000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/.metadata filter=lfs diff=lfs merge=lfs -text
+stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text

stage3b-local-terminal-repeat-step430000/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-stage3b-local-terminal-repeat-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-stage2b-hrm-full-nocap-extra-epoch1-gbs180
+resume_step: null
+resume_step_offset: 398437
+run_name: KoHRM-Text-1.4B-stage3b-local-terminal-repeat
+seed: 0
+skip_batches: 0
+total_steps_override: 700000
+weight_decay: 0.1
+weights_only_resume_from_ema: false

stage3b-local-terminal-repeat-step430000/carry_step_430000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1b0e10a0862e6c07283273e6a77a4af824aec45e059bbd6c0cf6e5957aaed858
+size 1333

stage3b-local-terminal-repeat-step430000/carry_step_430000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4575d347af629789f8d6a19b907b5736afce238036f87832f97c3b3f2eaf617f
+size 1333

stage3b-local-terminal-repeat-step430000/carry_step_430000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d5c38ce366e580809a55f4632ce03170dfa8202adea4c382814ef7307bc327d3
+size 1333

stage3b-local-terminal-repeat-step430000/carry_step_430000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:12ca4a3d5f218c6f26ce59a684f4ea97e331d3bd38ac4659f4e4c5712c07cb6f
+size 1333

stage3b-local-terminal-repeat-step430000/carry_step_430000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:888e174495308ca09dd0a26b8cf605a000c2fcff1d0398fd490f493bfdc5304c
+size 1333

stage3b-local-terminal-repeat-step430000/carry_step_430000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8af7d5c327ca9034056f0d38beaee42c6f9123dc79682928242814eba43980be
+size 1333

stage3b-local-terminal-repeat-step430000/carry_step_430000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:36a01d36528f20fbced3f539e6c04fe236a5e271d42bbab189d820b52f435ac3
+size 1333

stage3b-local-terminal-repeat-step430000/carry_step_430000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5993e70dea3f48e9685867d9a85eb1e5e306e8a8ea83eb35acaca28d0c8fa429
+size 1333

stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9697a730123a3d3abde5402ef1cedf5bee9b11e9c40f7265b880d1b601a16562
+size 983814

stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b5b60ed4aeee1dd8a9c3cde0d9f871cc84625a2262167eb1352aa2bc541ac3c9
+size 2769065329

stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3c117f8fe1b287baa2ca51719a9b30e64debc3fc5f5924a1e051b06056d19ed3
+size 2769090643

stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:cb884d99e3f4dd3f1f7b327b707c42c5f414dc341286a51e9aa2b9c9418a4976
+size 2769090643

stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b7daf2caf1e8e271c286c278b9d2d3a23770f5f5a87dfbb1f21b571f5177df51
+size 2769090643

stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:68c8efcabab449e77f4cca7de24137ee48b19250b47cb7ad7b54ea02515a4e5c
+size 2769090643

stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2f7145b3f95309e9c79f3e6b5a98620abd4766c84273dfb39e466303f9b5345d
+size 2769090643

stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc6e858c43eb27a418e1901e6f508d4bdd9a67a46a1754f6f93ff531964c3f9
+size 2769091588

stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8f30ebc46afd4aaf601ba359e4c1e80d708c4265ffa425dba5088e3de33543af
+size 2769098756

stage3b-local-terminal-repeat-step430000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_430000

stage3b-local-terminal-repeat-step430000/step_430000_info.json ADDED Viewed

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

+{
+  "tag": "step_430000",
+  "global_step": 430000,
+  "stage_start_step": 398437,
+  "skip_batches_hint": 31563,
+  "data_path": "/home/work/.data/hrm_text_prepared/local_terminal_conversations_ctx9k_resp6k_v1",
+  "global_batch_size": 180224
+}

stage3b-local-terminal-repeat-step430000/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

stage3b-local-terminal-repeat-step430000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage3b-local-terminal-repeat step_430000 raw resume checkpoint