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

fac6fef

verified ·

1 Parent(s): 055efe0

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage3b-local-terminal-repeat-step440000/all_config.yaml +46 -0
stage3b-local-terminal-repeat-step440000/carry_step_440000.0.pt +3 -0
stage3b-local-terminal-repeat-step440000/carry_step_440000.1.pt +3 -0
stage3b-local-terminal-repeat-step440000/carry_step_440000.2.pt +3 -0
stage3b-local-terminal-repeat-step440000/carry_step_440000.3.pt +3 -0
stage3b-local-terminal-repeat-step440000/carry_step_440000.4.pt +3 -0
stage3b-local-terminal-repeat-step440000/carry_step_440000.5.pt +3 -0
stage3b-local-terminal-repeat-step440000/carry_step_440000.6.pt +3 -0
stage3b-local-terminal-repeat-step440000/carry_step_440000.7.pt +3 -0
stage3b-local-terminal-repeat-step440000/fsdp2_step_440000/.metadata +3 -0
stage3b-local-terminal-repeat-step440000/fsdp2_step_440000/__0_0.distcp +3 -0
stage3b-local-terminal-repeat-step440000/fsdp2_step_440000/__1_0.distcp +3 -0
stage3b-local-terminal-repeat-step440000/fsdp2_step_440000/__2_0.distcp +3 -0
stage3b-local-terminal-repeat-step440000/fsdp2_step_440000/__3_0.distcp +3 -0
stage3b-local-terminal-repeat-step440000/fsdp2_step_440000/__4_0.distcp +3 -0
stage3b-local-terminal-repeat-step440000/fsdp2_step_440000/__5_0.distcp +3 -0
stage3b-local-terminal-repeat-step440000/fsdp2_step_440000/__6_0.distcp +3 -0
stage3b-local-terminal-repeat-step440000/fsdp2_step_440000/__7_0.distcp +3 -0
stage3b-local-terminal-repeat-step440000/latest_checkpoint.txt +1 -0
stage3b-local-terminal-repeat-step440000/step_440000_info.json +8 -0
stage3b-local-terminal-repeat-step440000/train_metadata.yaml +13 -0
stage3b-local-terminal-repeat-step440000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -537,3 +537,12 @@ stage3b-local-terminal-repeat-step430000/fsdp2_step_430000/__7_0.distcp filter=l
 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/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-step440000/fsdp2_step_440000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3b-local-terminal-repeat-step440000/fsdp2_step_440000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3b-local-terminal-repeat-step440000/fsdp2_step_440000/.metadata filter=lfs diff=lfs merge=lfs -text
+stage3b-local-terminal-repeat-step440000/fsdp2_step_440000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3b-local-terminal-repeat-step440000/fsdp2_step_440000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3b-local-terminal-repeat-step440000/fsdp2_step_440000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3b-local-terminal-repeat-step440000/fsdp2_step_440000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3b-local-terminal-repeat-step440000/fsdp2_step_440000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3b-local-terminal-repeat-step440000/fsdp2_step_440000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text

stage3b-local-terminal-repeat-step440000/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-step440000/carry_step_440000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:bf239bc20452c78c2bf1bcf68d723fb89cff4c18ce330d0381fda07b43588fb3
+size 1333

stage3b-local-terminal-repeat-step440000/carry_step_440000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:eb45c8c7aa014216bc444cfa5b32ec4ed3edf48883df0fa87072832636ac8b4d
+size 1333

stage3b-local-terminal-repeat-step440000/carry_step_440000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:389a39fad081a487778b9694e63e66fa703da58487d5a1765bf69d2b70dfead6
+size 1333

stage3b-local-terminal-repeat-step440000/carry_step_440000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a521fc17043daf8279758f12e406e2651e9b6ff2259c20bfda4e4d9c9769b8b3
+size 1333

stage3b-local-terminal-repeat-step440000/carry_step_440000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:84dd984b2880a724c6a8d227342c4290904c50172b96ca400235ac79823be375
+size 1333

stage3b-local-terminal-repeat-step440000/carry_step_440000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:df5e6d53574f378b7213ed34e899dc6f393344ef7bf24c19a08cdb40b67de15c
+size 1333

stage3b-local-terminal-repeat-step440000/carry_step_440000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4a18addb418bedeaeef43bf6e3f0606b112011d0ae89d382f9ada155970b2211
+size 1333

stage3b-local-terminal-repeat-step440000/carry_step_440000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:12ed8672946fe94b0fd25fc26356bfcea139115b88fa9584e3d4e3978ee3032a
+size 1333

stage3b-local-terminal-repeat-step440000/fsdp2_step_440000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8b5b8831101fc1174506a168e4f878f4f7bd7940557dc5240f354a4caa444f62
+size 983814

stage3b-local-terminal-repeat-step440000/fsdp2_step_440000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff79a525892ae4f8d5e7a032bd0e195d170b803140c468ea51cb993bc499fb1
+size 2769065329

stage3b-local-terminal-repeat-step440000/fsdp2_step_440000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:aac141986cd489dd162eaf8a04a1230f63aca5303b659ae3eed2f4a2269608f9
+size 2769090643

stage3b-local-terminal-repeat-step440000/fsdp2_step_440000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8653e08127e8b96d939cf8ad27d0f00d41b230e85de8750ca9e5124a621effb9
+size 2769090643

stage3b-local-terminal-repeat-step440000/fsdp2_step_440000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2f7ee773d3890b43dd959408a97b512a09c7cf7c8e94cfc6488de8aa62ecaf57
+size 2769090643

stage3b-local-terminal-repeat-step440000/fsdp2_step_440000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:36a2b1a743ffc761b0dc5612cd04ed9f869f8abd07a7d85bc1c8ddda30ac84c1
+size 2769090643

stage3b-local-terminal-repeat-step440000/fsdp2_step_440000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:80541a23944b4b4944b7ee0f795aacda22394962641ed58fd5f4174e7423526c
+size 2769090643

stage3b-local-terminal-repeat-step440000/fsdp2_step_440000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9100637b92934b722e07c6de5649a090629a8b806fa9687b0606d32cb235b640
+size 2769091588

stage3b-local-terminal-repeat-step440000/fsdp2_step_440000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:03e0241819368f3cb2ee131603dde45680a98b05a530aa8cdcb4b3d61c36bcf6
+size 2769098756

stage3b-local-terminal-repeat-step440000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_440000

stage3b-local-terminal-repeat-step440000/step_440000_info.json ADDED Viewed

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

+{
+  "tag": "step_440000",
+  "global_step": 440000,
+  "stage_start_step": 398437,
+  "skip_batches_hint": 41563,
+  "data_path": "/home/work/.data/hrm_text_prepared/local_terminal_conversations_ctx9k_resp6k_v1",
+  "global_batch_size": 180224
+}

stage3b-local-terminal-repeat-step440000/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-step440000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage3b-local-terminal-repeat step_440000 raw resume checkpoint