Text Generation
Transformers
Safetensors
English
llama
continual-pretraining
sft
135m
single-gpu
l20
data-curation
text-generation-inference
Instructions to use AliceYin/l20-edu-135m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AliceYin/l20-edu-135m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AliceYin/l20-edu-135m")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("AliceYin/l20-edu-135m") model = AutoModelForCausalLM.from_pretrained("AliceYin/l20-edu-135m", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use AliceYin/l20-edu-135m with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AliceYin/l20-edu-135m" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AliceYin/l20-edu-135m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/AliceYin/l20-edu-135m
- SGLang
How to use AliceYin/l20-edu-135m 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 "AliceYin/l20-edu-135m" \ --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": "AliceYin/l20-edu-135m", "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 "AliceYin/l20-edu-135m" \ --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": "AliceYin/l20-edu-135m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use AliceYin/l20-edu-135m with Docker Model Runner:
docker model run hf.co/AliceYin/l20-edu-135m
Upload Stage 4 evaluation artifacts
Browse files- .gitattributes +1 -0
- eval_results/stage4-release/sft_eval/stage4-base/runs__l20-edu-135m-stage4-hq-crossdedup-8k__step-002500/samples_arc_challenge_2026-06-15T20-41-45.707017.jsonl +0 -0
- eval_results/stage4-release/sft_eval/stage4-base/runs__l20-edu-135m-stage4-hq-crossdedup-8k__step-002500/samples_arc_easy_2026-06-15T20-41-45.707017.jsonl +0 -0
- eval_results/stage4-release/sft_eval/stage4-base/runs__l20-edu-135m-stage4-hq-crossdedup-8k__step-002500/samples_hellaswag_2026-06-15T20-41-45.707017.jsonl +3 -0
- eval_results/stage4-release/sft_eval/stage4-base/runs__l20-edu-135m-stage4-hq-crossdedup-8k__step-002500/samples_piqa_2026-06-15T20-41-45.707017.jsonl +0 -0
- eval_results/stage4-release/sft_eval/stage4-base/runs__l20-edu-135m-stage4-hq-crossdedup-8k__step-002500/samples_winogrande_2026-06-15T20-41-45.707017.jsonl +0 -0
.gitattributes
CHANGED
|
@@ -40,3 +40,4 @@ docs/assets/training_curves.png filter=lfs diff=lfs merge=lfs -text
|
|
| 40 |
eval_results/step-001850_sota/__home__hhai__l20-pretrain__runs__l20-edu-135m-stage2-math-code-textbook-replay-8k__step-001850/samples_gsm8k_2026-06-10T07-04-18.519095.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 41 |
eval_results/step-001850_sota/__home__hhai__l20-pretrain__runs__l20-edu-135m-stage2-math-code-textbook-replay-8k__step-001850/samples_hellaswag_2026-06-10T07-04-18.519095.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 42 |
eval_results/step-001850_sota/__home__hhai__l20-pretrain__runs__l20-edu-135m-stage2-math-code-textbook-replay-8k__step-001850/samples_mmlu_professional_law_2026-06-10T07-04-18.519095.jsonl filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 40 |
eval_results/step-001850_sota/__home__hhai__l20-pretrain__runs__l20-edu-135m-stage2-math-code-textbook-replay-8k__step-001850/samples_gsm8k_2026-06-10T07-04-18.519095.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 41 |
eval_results/step-001850_sota/__home__hhai__l20-pretrain__runs__l20-edu-135m-stage2-math-code-textbook-replay-8k__step-001850/samples_hellaswag_2026-06-10T07-04-18.519095.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 42 |
eval_results/step-001850_sota/__home__hhai__l20-pretrain__runs__l20-edu-135m-stage2-math-code-textbook-replay-8k__step-001850/samples_mmlu_professional_law_2026-06-10T07-04-18.519095.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
eval_results/stage4-release/sft_eval/stage4-base/runs__l20-edu-135m-stage4-hq-crossdedup-8k__step-002500/samples_hellaswag_2026-06-15T20-41-45.707017.jsonl filter=lfs diff=lfs merge=lfs -text
|
eval_results/stage4-release/sft_eval/stage4-base/runs__l20-edu-135m-stage4-hq-crossdedup-8k__step-002500/samples_arc_challenge_2026-06-15T20-41-45.707017.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results/stage4-release/sft_eval/stage4-base/runs__l20-edu-135m-stage4-hq-crossdedup-8k__step-002500/samples_arc_easy_2026-06-15T20-41-45.707017.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results/stage4-release/sft_eval/stage4-base/runs__l20-edu-135m-stage4-hq-crossdedup-8k__step-002500/samples_hellaswag_2026-06-15T20-41-45.707017.jsonl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9659be0674167fe7d01c0983c7abe0bc475d95c60a10cc94eb281e7dfa15fefb
|
| 3 |
+
size 16711680
|
eval_results/stage4-release/sft_eval/stage4-base/runs__l20-edu-135m-stage4-hq-crossdedup-8k__step-002500/samples_piqa_2026-06-15T20-41-45.707017.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results/stage4-release/sft_eval/stage4-base/runs__l20-edu-135m-stage4-hq-crossdedup-8k__step-002500/samples_winogrande_2026-06-15T20-41-45.707017.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|