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 +18 -0
- stage1b-hrm-fastcap-repeat/all_config.yaml +46 -0
- stage1b-hrm-fastcap-repeat/carry_epoch_1.0.pt +3 -0
- stage1b-hrm-fastcap-repeat/carry_epoch_1.1.pt +3 -0
- stage1b-hrm-fastcap-repeat/carry_epoch_1.2.pt +3 -0
- stage1b-hrm-fastcap-repeat/carry_epoch_1.3.pt +3 -0
- stage1b-hrm-fastcap-repeat/carry_epoch_1.4.pt +3 -0
- stage1b-hrm-fastcap-repeat/carry_epoch_1.5.pt +3 -0
- stage1b-hrm-fastcap-repeat/carry_epoch_1.6.pt +3 -0
- stage1b-hrm-fastcap-repeat/carry_epoch_1.7.pt +3 -0
- stage1b-hrm-fastcap-repeat/carry_step_310000.0.pt +3 -0
- stage1b-hrm-fastcap-repeat/carry_step_310000.1.pt +3 -0
- stage1b-hrm-fastcap-repeat/carry_step_310000.2.pt +3 -0
- stage1b-hrm-fastcap-repeat/carry_step_310000.3.pt +3 -0
- stage1b-hrm-fastcap-repeat/carry_step_310000.4.pt +3 -0
- stage1b-hrm-fastcap-repeat/carry_step_310000.5.pt +3 -0
- stage1b-hrm-fastcap-repeat/carry_step_310000.6.pt +3 -0
- stage1b-hrm-fastcap-repeat/carry_step_310000.7.pt +3 -0
- stage1b-hrm-fastcap-repeat/epoch_1_info.json +8 -0
- stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/.metadata +3 -0
- stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/__0_0.distcp +3 -0
- stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/__1_0.distcp +3 -0
- stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/__2_0.distcp +3 -0
- stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/__3_0.distcp +3 -0
- stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/__4_0.distcp +3 -0
- stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/__5_0.distcp +3 -0
- stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/__6_0.distcp +3 -0
- stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/__7_0.distcp +3 -0
- stage1b-hrm-fastcap-repeat/fsdp2_step_310000/.metadata +3 -0
- stage1b-hrm-fastcap-repeat/fsdp2_step_310000/__0_0.distcp +3 -0
- stage1b-hrm-fastcap-repeat/fsdp2_step_310000/__1_0.distcp +3 -0
- stage1b-hrm-fastcap-repeat/fsdp2_step_310000/__2_0.distcp +3 -0
- stage1b-hrm-fastcap-repeat/fsdp2_step_310000/__3_0.distcp +3 -0
- stage1b-hrm-fastcap-repeat/fsdp2_step_310000/__4_0.distcp +3 -0
- stage1b-hrm-fastcap-repeat/fsdp2_step_310000/__5_0.distcp +3 -0
- stage1b-hrm-fastcap-repeat/fsdp2_step_310000/__6_0.distcp +3 -0
- stage1b-hrm-fastcap-repeat/fsdp2_step_310000/__7_0.distcp +3 -0
- stage1b-hrm-fastcap-repeat/latest_checkpoint.txt +1 -0
- stage1b-hrm-fastcap-repeat/step_310000_info.json +8 -0
- stage1b-hrm-fastcap-repeat/train_metadata.yaml +13 -0
- stage1b-hrm-fastcap-repeat/upload_manifest.json +10 -0
.gitattributes
CHANGED
|
@@ -393,3 +393,21 @@ stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__4_0.distcp filter=lfs
|
|
| 393 |
stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 394 |
stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 395 |
stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 393 |
stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 394 |
stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 395 |
stage1b-hrm-fastcap-repeat-step310000/fsdp2_step_310000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 396 |
+
stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 397 |
+
stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 398 |
+
stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 399 |
+
stage1b-hrm-fastcap-repeat/fsdp2_step_310000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 400 |
+
stage1b-hrm-fastcap-repeat/fsdp2_step_310000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 401 |
+
stage1b-hrm-fastcap-repeat/fsdp2_step_310000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 402 |
+
stage1b-hrm-fastcap-repeat/fsdp2_step_310000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 403 |
+
stage1b-hrm-fastcap-repeat/fsdp2_step_310000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 404 |
+
stage1b-hrm-fastcap-repeat/fsdp2_step_310000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 405 |
+
stage1b-hrm-fastcap-repeat/fsdp2_step_310000/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 406 |
+
stage1b-hrm-fastcap-repeat/fsdp2_step_310000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 407 |
+
stage1b-hrm-fastcap-repeat/fsdp2_step_310000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 408 |
+
stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 409 |
+
stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 410 |
+
stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 411 |
+
stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 412 |
+
stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 413 |
+
stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/.metadata filter=lfs diff=lfs merge=lfs -text
|
stage1b-hrm-fastcap-repeat/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-stage1b-hrm-fastcap-repeat-gbs180
|
| 24 |
+
checkpoint_step_interval: 10000
|
| 25 |
+
data:
|
| 26 |
+
path: /home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_fastcap_stage1_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-stage4-korean-tool-finance-gbs180
|
| 39 |
+
resume_step: null
|
| 40 |
+
resume_step_offset: 237192
|
| 41 |
+
run_name: KoHRM-Text-1.4B-stage1b-hrm-fastcap-repeat
|
| 42 |
+
seed: 0
|
| 43 |
+
skip_batches: 0
|
| 44 |
+
total_steps_override: 465000
|
| 45 |
+
weight_decay: 0.1
|
| 46 |
+
weights_only_resume_from_ema: false
|
stage1b-hrm-fastcap-repeat/carry_epoch_1.0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e3b089e35eacca121e8bc850c0fc138c4ef45a63cf9e370e2f852d6245db36b
|
| 3 |
+
size 1309
|
stage1b-hrm-fastcap-repeat/carry_epoch_1.1.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66952aadc5b6f1d9d38cd436e6dba2c3b6a487138c6960beb815672ddf699495
|
| 3 |
+
size 1309
|
stage1b-hrm-fastcap-repeat/carry_epoch_1.2.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a7da182d5d1dfe900b2018b6e4fe6d318c69f791b7a3c94c1727e2112a5f57d
|
| 3 |
+
size 1309
|
stage1b-hrm-fastcap-repeat/carry_epoch_1.3.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45156a7f9cef48f22d7a3c46c59d92394c3da40b2b596f2681cecece9156177e
|
| 3 |
+
size 1309
|
stage1b-hrm-fastcap-repeat/carry_epoch_1.4.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34356bd35b48ac6ce98742241b2c0e1c96147c36743415c7b0e432ae28f8bfc8
|
| 3 |
+
size 1309
|
stage1b-hrm-fastcap-repeat/carry_epoch_1.5.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f5934083e16382c0d96bab003d7f577ced0da026175aff5a4ad2aaf31c603f6
|
| 3 |
+
size 1309
|
stage1b-hrm-fastcap-repeat/carry_epoch_1.6.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93480251cc3a3285f6cea88b5f8b7c6d46672f04cacd0623127885ff4469e7d8
|
| 3 |
+
size 1309
|
stage1b-hrm-fastcap-repeat/carry_epoch_1.7.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2de90149405f8416a3f1c4bb6b69b52843f8a2f835c1b874bd13c13129fc3f5
|
| 3 |
+
size 1309
|
stage1b-hrm-fastcap-repeat/carry_step_310000.0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e6d6f28ef3c85f170b821a8767935e58dee86a2861d5ccf97421a7ff530eb4b
|
| 3 |
+
size 1333
|
stage1b-hrm-fastcap-repeat/carry_step_310000.1.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:961afdf1cfe288c54600418f32c68b17341d65472b99342bdadc9505ebe73f5c
|
| 3 |
+
size 1333
|
stage1b-hrm-fastcap-repeat/carry_step_310000.2.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f1b1677e0e606f834986ce943044ae4a7c157ba9b721046a078f16e4a31819c
|
| 3 |
+
size 1333
|
stage1b-hrm-fastcap-repeat/carry_step_310000.3.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04e9e45713d5396e7b8c4df99a38cf9ee0290c9d93b2a1c019e2ae771861ad5f
|
| 3 |
+
size 1333
|
stage1b-hrm-fastcap-repeat/carry_step_310000.4.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:484b0bb1fcf296ecfd97a36aadeaf0746bdd34aa1f7c38776d0ca0becbc8594e
|
| 3 |
+
size 1333
|
stage1b-hrm-fastcap-repeat/carry_step_310000.5.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51a245d840aa3f7386d63d6051ffd28408590768700733b22b820245a99b2ed0
|
| 3 |
+
size 1333
|
stage1b-hrm-fastcap-repeat/carry_step_310000.6.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e61153399ebbdef42ea372998b32bb44bd6954ef9afbcb98c0d5ce805ad836ef
|
| 3 |
+
size 1333
|
stage1b-hrm-fastcap-repeat/carry_step_310000.7.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfeb840a1a8e588689c4d2b23f8e26ff99090b842561849c046b0ed6ebebe58d
|
| 3 |
+
size 1333
|
stage1b-hrm-fastcap-repeat/epoch_1_info.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"tag": "epoch_1",
|
| 3 |
+
"global_step": 317814,
|
| 4 |
+
"stage_start_step": 237192,
|
| 5 |
+
"skip_batches_hint": 80622,
|
| 6 |
+
"data_path": "/home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_fastcap_stage1_v1",
|
| 7 |
+
"global_batch_size": 180224
|
| 8 |
+
}
|
stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/.metadata
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a7edad27130db89f41b6740f96963466679ce333b2516fc36fa50bf096ce95b
|
| 3 |
+
size 983807
|
stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/__0_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d413d24e3c76814f951f54203d57319f007e79688dc9bbe1c1326846ead5a128
|
| 3 |
+
size 2769065329
|
stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/__1_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2984cacac3c25ab4122009c39436bbfbdc73fdbc968318c6f19def494635bb27
|
| 3 |
+
size 2769090643
|
stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/__2_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee4f27df2c6f930fb19b6bb4020864d72786bba311a11ebd9b3a59bf5d8a417a
|
| 3 |
+
size 2769090643
|
stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/__3_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc5742b4a425579fb2a9a3f7935d2a2261b1c0ed26b04c8c100d9c6f18a540e5
|
| 3 |
+
size 2769090643
|
stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/__4_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c88e528c61c0e1b6d6399dd240e7c94d1f2d007ebf21ae0d997eae4327b2b2f9
|
| 3 |
+
size 2769090643
|
stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/__5_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f581017776a382b84e8a7f8bde2959c37a5e00365061a19d3bea2f00f2a17cf
|
| 3 |
+
size 2769090643
|
stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/__6_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1892e229bedb649918f12a2f2faed3e382ad0e411286b7ff378038da1638d810
|
| 3 |
+
size 2769091588
|
stage1b-hrm-fastcap-repeat/fsdp2_epoch_1/__7_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdabe76b43aca364d1c21b9c73d9dbf9150c97aa9073c3aa978421b808912507
|
| 3 |
+
size 2769098756
|
stage1b-hrm-fastcap-repeat/fsdp2_step_310000/.metadata
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fbbe207316b429606282cd0e35fbe10ee0f1854b8b919723ce269b3345ff238
|
| 3 |
+
size 983811
|
stage1b-hrm-fastcap-repeat/fsdp2_step_310000/__0_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41d0384aca1d1d1caf7a6658c040186a240ae300cb357c646510879fb6c5592a
|
| 3 |
+
size 2769065329
|
stage1b-hrm-fastcap-repeat/fsdp2_step_310000/__1_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:354292e75c135070dd9f17c867da8d343e5b15b87ae8750b89eda6ac7adfb994
|
| 3 |
+
size 2769090643
|
stage1b-hrm-fastcap-repeat/fsdp2_step_310000/__2_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18c51635eb8a273f44df62eef622a1d830e5f2e5f805144ebee6336995acf5fd
|
| 3 |
+
size 2769090643
|
stage1b-hrm-fastcap-repeat/fsdp2_step_310000/__3_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca83306d419a74817d148e04ce0cde017369af7839880eabf3cc30474ecf2a13
|
| 3 |
+
size 2769090643
|
stage1b-hrm-fastcap-repeat/fsdp2_step_310000/__4_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54d30a28b480ebc594ba75a4cb0c3e99e5b298807ef0b6db097a40e489d0c5d5
|
| 3 |
+
size 2769090643
|
stage1b-hrm-fastcap-repeat/fsdp2_step_310000/__5_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af9f32b32e0d5994796774a324aef243c83e57d866bf00e2212ef3153dfd9769
|
| 3 |
+
size 2769090643
|
stage1b-hrm-fastcap-repeat/fsdp2_step_310000/__6_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d919fe36972816fcafd57d0cdde1a3c8de4d98577c17a893b4ea205cc99a6b78
|
| 3 |
+
size 2769091588
|
stage1b-hrm-fastcap-repeat/fsdp2_step_310000/__7_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac024a9fee171e2a82f369e32236ecf1acef89838b3f29ca4f4b8401470c74aa
|
| 3 |
+
size 2769098756
|
stage1b-hrm-fastcap-repeat/latest_checkpoint.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
epoch_1
|
stage1b-hrm-fastcap-repeat/step_310000_info.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"tag": "step_310000",
|
| 3 |
+
"global_step": 310000,
|
| 4 |
+
"stage_start_step": 237192,
|
| 5 |
+
"skip_batches_hint": 72808,
|
| 6 |
+
"data_path": "/home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_fastcap_stage1_v1",
|
| 7 |
+
"global_batch_size": 180224
|
| 8 |
+
}
|
stage1b-hrm-fastcap-repeat/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: 14554291763
|
| 13 |
+
vocab_size: 131072
|
stage1b-hrm-fastcap-repeat/upload_manifest.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"source": "/home/work/.data/hrm_text_checkpoints/KoHRM-Text-1.4B-stage1b-hrm-fastcap-repeat-gbs180",
|
| 3 |
+
"stage": "stage1b-hrm-fastcap-repeat",
|
| 4 |
+
"keep_last": 2,
|
| 5 |
+
"tags": [
|
| 6 |
+
"step_310000",
|
| 7 |
+
"epoch_1"
|
| 8 |
+
],
|
| 9 |
+
"created_at": "2026-05-27T05:18:32Z"
|
| 10 |
+
}
|