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")

# pip install -U transformers accelerate
# 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 Jun 2

Commit

f2dedc4

verified ·

1 Parent(s): e9446f6

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +9 -0
stage3d-local-terminal-repeat3-step870000/all_config.yaml +46 -0
stage3d-local-terminal-repeat3-step870000/carry_step_870000.0.pt +3 -0
stage3d-local-terminal-repeat3-step870000/carry_step_870000.1.pt +3 -0
stage3d-local-terminal-repeat3-step870000/carry_step_870000.2.pt +3 -0
stage3d-local-terminal-repeat3-step870000/carry_step_870000.3.pt +3 -0
stage3d-local-terminal-repeat3-step870000/carry_step_870000.4.pt +3 -0
stage3d-local-terminal-repeat3-step870000/carry_step_870000.5.pt +3 -0
stage3d-local-terminal-repeat3-step870000/carry_step_870000.6.pt +3 -0
stage3d-local-terminal-repeat3-step870000/carry_step_870000.7.pt +3 -0
stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/.metadata +3 -0
stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/__0_0.distcp +3 -0
stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/__1_0.distcp +3 -0
stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/__2_0.distcp +3 -0
stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/__3_0.distcp +3 -0
stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/__4_0.distcp +3 -0
stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/__5_0.distcp +3 -0
stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/__6_0.distcp +3 -0
stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/__7_0.distcp +3 -0
stage3d-local-terminal-repeat3-step870000/latest_checkpoint.txt +1 -0
stage3d-local-terminal-repeat3-step870000/step_870000_info.json +8 -0
stage3d-local-terminal-repeat3-step870000/train_metadata.yaml +13 -0
stage3d-local-terminal-repeat3-step870000/upload_manifest.json +1 -0

.gitattributes CHANGED Viewed

@@ -1050,3 +1050,12 @@ stage2d-hrm-full-nocap-repeat3/fsdp2_epoch_1/__3_0.distcp filter=lfs diff=lfs me
 stage2d-hrm-full-nocap-repeat3/fsdp2_epoch_1/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2d-hrm-full-nocap-repeat3/fsdp2_epoch_1/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2d-hrm-full-nocap-repeat3/fsdp2_epoch_1/__5_0.distcp filter=lfs diff=lfs merge=lfs -text

 stage2d-hrm-full-nocap-repeat3/fsdp2_epoch_1/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2d-hrm-full-nocap-repeat3/fsdp2_epoch_1/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
 stage2d-hrm-full-nocap-repeat3/fsdp2_epoch_1/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/.metadata filter=lfs diff=lfs merge=lfs -text

stage3d-local-terminal-repeat3-step870000/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-stage3d-local-terminal-repeat3-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-stage2d-hrm-full-nocap-repeat3-gbs180
+resume_step: null
+resume_step_offset: 864195
+run_name: KoHRM-Text-1.4B-stage3d-local-terminal-repeat3
+seed: 0
+skip_batches: 0
+total_steps_override: 934306
+weight_decay: 0.1
+weights_only_resume_from_ema: false

stage3d-local-terminal-repeat3-step870000/carry_step_870000.0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b9b611a9e9a6c758e96fd76e0f62d97baa9654f64453bc50892aeac0a74cbeb2
+size 1333

stage3d-local-terminal-repeat3-step870000/carry_step_870000.1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:68304540e1e52b4576104cefe77718b51a84b267ca63ca33757fd125b1df9762
+size 1333

stage3d-local-terminal-repeat3-step870000/carry_step_870000.2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2acf02393146b57213d3483edf54115aa50f5b97b10ede76601d21ac193b054d
+size 1333

stage3d-local-terminal-repeat3-step870000/carry_step_870000.3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d4608086c7a2117254ae6ec805029c92bee0d3989ddbe42a8ff9f629a9a3026f
+size 1333

stage3d-local-terminal-repeat3-step870000/carry_step_870000.4.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ed7435f835222805bfc668ae5209f934ef0c481257393449521167354e2f1412
+size 1333

stage3d-local-terminal-repeat3-step870000/carry_step_870000.5.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:09954034cbe7bf34b8dda1c6b49411e61fa9a73cb0451bb759a590c8de8e7c6f
+size 1333

stage3d-local-terminal-repeat3-step870000/carry_step_870000.6.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c899e5e80d3ecf9fb06a10c38fdfc6a5a48ae02b50c0c421e84d0c395a0a42c5
+size 1333

stage3d-local-terminal-repeat3-step870000/carry_step_870000.7.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7e3fa992cc49b6dda2757a8842047d3bfbbb2818643c9678f0af2609407567c1
+size 1333

stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/.metadata ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:79d6223f6e87187a6a1e87b0a50a0d0ba6291d81b71ffa86f8c7dcdd9766c954
+size 983815

stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/__0_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:abba260f13b13a68e25c50ad0a3c71d2c9f8bf18480d4a4e94acd7680be1d25f
+size 2769065329

stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/__1_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:17f6064069b8550c98439f63f9ef88cc6bc4f75122486102ce8eaf13d5272967
+size 2769090643

stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/__2_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f15248be0ea9f5535fc9a87d1060d8f8d8058f40718f1c86b0d884d50b5b737b
+size 2769090643

stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/__3_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d077318f0afabc9e681ac669089b0e7c76fa5ebbbff8f52371d2c590831c8875
+size 2769090643

stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/__4_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8adb3f4064312f04838711db028b4b5f2b5597f606a4effc16f62299901dc986
+size 2769090643

stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/__5_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:081ed3e3f5a7e055a738e1a2d2d973ad3be03ac5c50af492486859a280d4265c
+size 2769090643

stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/__6_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:19e9e5aae447fe86ed745ce44bd6f3540e1dd588830a7d85cab146bfbf7dde36
+size 2769091588

stage3d-local-terminal-repeat3-step870000/fsdp2_step_870000/__7_0.distcp ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ea4307bce0a2fea2a26041fa67018553e2719811e8bd08baad0095d95bd44d46
+size 2769098756

stage3d-local-terminal-repeat3-step870000/latest_checkpoint.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ step_870000

stage3d-local-terminal-repeat3-step870000/step_870000_info.json ADDED Viewed

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

+{
+  "tag": "step_870000",
+  "global_step": 870000,
+  "stage_start_step": 864195,
+  "skip_batches_hint": 5805,
+  "data_path": "/home/work/.data/hrm_text_prepared/local_terminal_conversations_ctx9k_resp6k_v1",
+  "global_batch_size": 180224
+}

stage3d-local-terminal-repeat3-step870000/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

stage3d-local-terminal-repeat3-step870000/upload_manifest.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ stage3d-local-terminal-repeat3 step_870000 raw resume checkpoint