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
- Transformers
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", dtype="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
Add files using upload-large-folder tool
Browse files- .gitattributes +9 -0
- stage2c-hrm-full-nocap-repeat2-step580000/all_config.yaml +46 -0
- stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.0.pt +3 -0
- stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.1.pt +3 -0
- stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.2.pt +3 -0
- stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.3.pt +3 -0
- stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.4.pt +3 -0
- stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.5.pt +3 -0
- stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.6.pt +3 -0
- stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.7.pt +3 -0
- stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/.metadata +3 -0
- stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__0_0.distcp +3 -0
- stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__1_0.distcp +3 -0
- stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__2_0.distcp +3 -0
- stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__3_0.distcp +3 -0
- stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__4_0.distcp +3 -0
- stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__5_0.distcp +3 -0
- stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__6_0.distcp +3 -0
- stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__7_0.distcp +3 -0
- stage2c-hrm-full-nocap-repeat2-step580000/latest_checkpoint.txt +1 -0
- stage2c-hrm-full-nocap-repeat2-step580000/step_580000_info.json +8 -0
- stage2c-hrm-full-nocap-repeat2-step580000/train_metadata.yaml +13 -0
- stage2c-hrm-full-nocap-repeat2-step580000/upload_manifest.json +1 -0
.gitattributes
CHANGED
|
@@ -699,3 +699,12 @@ stage2c-hrm-full-nocap-repeat2-step570000/fsdp2_step_570000/__4_0.distcp filter=
|
|
| 699 |
stage2c-hrm-full-nocap-repeat2-step570000/fsdp2_step_570000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 700 |
stage2c-hrm-full-nocap-repeat2-step570000/fsdp2_step_570000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 701 |
stage2c-hrm-full-nocap-repeat2-step570000/fsdp2_step_570000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 699 |
stage2c-hrm-full-nocap-repeat2-step570000/fsdp2_step_570000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 700 |
stage2c-hrm-full-nocap-repeat2-step570000/fsdp2_step_570000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 701 |
stage2c-hrm-full-nocap-repeat2-step570000/fsdp2_step_570000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 702 |
+
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 703 |
+
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 704 |
+
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 705 |
+
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 706 |
+
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 707 |
+
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 708 |
+
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 709 |
+
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 710 |
+
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
stage2c-hrm-full-nocap-repeat2-step580000/all_config.yaml
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
arch:
|
| 2 |
+
H_cycles: 2
|
| 3 |
+
H_override: {}
|
| 4 |
+
L_cycles: 3
|
| 5 |
+
bp_max_steps: 5
|
| 6 |
+
bp_warmup_ratio: 0.2
|
| 7 |
+
expansion: 4
|
| 8 |
+
half_layers: true
|
| 9 |
+
head: lm_head@LMHead
|
| 10 |
+
hidden_size: 1536
|
| 11 |
+
init_type: lecun_normal
|
| 12 |
+
n_layers: 32
|
| 13 |
+
name: baselines.hrm_nocarry_bp_warmup@HierarchicalReasoningModel
|
| 14 |
+
norm_eps: 1.0e-06
|
| 15 |
+
norm_type: pre
|
| 16 |
+
num_heads: 12
|
| 17 |
+
pos_emb_type: rope
|
| 18 |
+
rope_theta: 10000.0
|
| 19 |
+
beta1: 0.9
|
| 20 |
+
beta2: 0.95
|
| 21 |
+
checkpoint_interval: 1
|
| 22 |
+
checkpoint_keep_last: 2
|
| 23 |
+
checkpoint_path: /home/work/.data/hrm_text_checkpoints/KoHRM-Text-1.4B-stage2c-hrm-full-nocap-repeat2-gbs180
|
| 24 |
+
checkpoint_step_interval: 10000
|
| 25 |
+
data:
|
| 26 |
+
path: /home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_full_nocap_v1
|
| 27 |
+
target_only: true
|
| 28 |
+
ema: 0.9999
|
| 29 |
+
epochs: 1
|
| 30 |
+
fwd_bwd_dtype: bfloat16
|
| 31 |
+
global_batch_size: 180224
|
| 32 |
+
log_interval: 5
|
| 33 |
+
lr: 0.00022
|
| 34 |
+
lr_min_ratio: 1.0
|
| 35 |
+
lr_warmup_steps: 2000
|
| 36 |
+
project_name: KoHRM-Text
|
| 37 |
+
resume_epoch: null
|
| 38 |
+
resume_from: /home/work/.data/hrm_text_checkpoints/KoHRM-Text-1.4B-stage1c-hrm-fastcap-repeat2-gbs180
|
| 39 |
+
resume_step: null
|
| 40 |
+
resume_step_offset: 550699
|
| 41 |
+
run_name: KoHRM-Text-1.4B-stage2c-hrm-full-nocap-repeat2
|
| 42 |
+
seed: 0
|
| 43 |
+
skip_batches: 0
|
| 44 |
+
total_steps_override: 700000
|
| 45 |
+
weight_decay: 0.1
|
| 46 |
+
weights_only_resume_from_ema: false
|
stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a9895594d496487455846598fa83d899165393a4ac5b0f80f1c068558afc626
|
| 3 |
+
size 1333
|
stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.1.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfa55f89ae381c724efe0d23cee12e200402630e2c265c428275ee84ba804792
|
| 3 |
+
size 1333
|
stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.2.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01db223a23443f249b3834afcb1edf7661feb6f697088d5ad5ef6d4176d30ff1
|
| 3 |
+
size 1333
|
stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.3.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d173bb52e06289a3d3d262de543f41688701636b6a447ba69867789ddfe5658
|
| 3 |
+
size 1333
|
stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.4.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61ae520fb82e85b584bc70f11b475793f43b41037e8fc769a6d78b4e880d3f82
|
| 3 |
+
size 1333
|
stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.5.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f6be86ddd69c2e789193b167a071db3b1a495748b2ddac7a922286ca7872df9
|
| 3 |
+
size 1333
|
stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.6.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aad98caf77797b33dc50f3a179bfa5ab5328df0b231e11f53a2e4b71a2788154
|
| 3 |
+
size 1333
|
stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.7.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d2821347776181c41e9115d3d3edd7326a7a5052cbcbc87a927c6c79c4bb7bb
|
| 3 |
+
size 1333
|
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/.metadata
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:139fe7898d021b4570d46c29c37125e987d0deea3b078e307dc3159070470725
|
| 3 |
+
size 983815
|
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__0_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9402ef8f3950c9820c5cc0a1c31c3bc3dd31fa4fde24eec4f48f9a2cc3537f54
|
| 3 |
+
size 2769065329
|
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__1_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7cd34d8ec137c9870cb076731761ea9c1a256d2bbba9ee9d0906503df0075518
|
| 3 |
+
size 2769090643
|
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__2_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fbc69cb22b0e18cc10b8d06a9be3b072c64c27b535b9b7d16d2438d895dfecda
|
| 3 |
+
size 2769090643
|
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__3_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0308a2f49b13ded4b7f7e99fed3745f55c2d77e78ebf3087e3632abcbd8ae514
|
| 3 |
+
size 2769090643
|
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__4_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fee568c4a579bc5e68c7b5c298c7a4c18a31859471ecd95873acdc1083a9086d
|
| 3 |
+
size 2769090643
|
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__5_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b796bdf82e8036db5a1f646b9e1767b0cd6c7cdf1318c6a6c2f7c7a8968eff70
|
| 3 |
+
size 2769090643
|
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__6_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fac67a69b14369d248d6fda6951a54eb6df68784a31aa9eac532c13516ea309a
|
| 3 |
+
size 2769091588
|
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__7_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97ae880ece3774b4b300a974e7b27cd9dd805e8d56d354fa3d46e2b08f66945e
|
| 3 |
+
size 2769098756
|
stage2c-hrm-full-nocap-repeat2-step580000/latest_checkpoint.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
step_580000
|
stage2c-hrm-full-nocap-repeat2-step580000/step_580000_info.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"tag": "step_580000",
|
| 3 |
+
"global_step": 580000,
|
| 4 |
+
"stage_start_step": 550699,
|
| 5 |
+
"skip_batches_hint": 29301,
|
| 6 |
+
"data_path": "/home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_full_nocap_v1",
|
| 7 |
+
"global_batch_size": 180224
|
| 8 |
+
}
|
stage2c-hrm-full-nocap-repeat2-step580000/train_metadata.yaml
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
max_seq_len: 4096
|
| 2 |
+
tokenizer_info:
|
| 3 |
+
boq: <|im_start|>
|
| 4 |
+
condition_mapping:
|
| 5 |
+
cot: <|object_ref_end|>
|
| 6 |
+
direct: <|object_ref_start|>
|
| 7 |
+
noisy: <|quad_start|>
|
| 8 |
+
synth: <|quad_end|>
|
| 9 |
+
eoa: <|box_end|>
|
| 10 |
+
eoq: <|im_end|>
|
| 11 |
+
tokenizer_path: /home/work/.data/huggingface/trained_tokenizers/hrm-ko-terminal-131k-v1/tokenizer.json
|
| 12 |
+
total_length: 14553653061
|
| 13 |
+
vocab_size: 131072
|
stage2c-hrm-full-nocap-repeat2-step580000/upload_manifest.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
stage2c-hrm-full-nocap-repeat2 step_580000 raw resume checkpoint
|