Instructions to use Harley-ml/Dillion-1.2M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Harley-ml/Dillion-1.2M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Harley-ml/Dillion-1.2M")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Harley-ml/Dillion-1.2M") model = AutoModelForCausalLM.from_pretrained("Harley-ml/Dillion-1.2M") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Harley-ml/Dillion-1.2M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Harley-ml/Dillion-1.2M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Harley-ml/Dillion-1.2M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Harley-ml/Dillion-1.2M
- SGLang
How to use Harley-ml/Dillion-1.2M 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 "Harley-ml/Dillion-1.2M" \ --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": "Harley-ml/Dillion-1.2M", "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 "Harley-ml/Dillion-1.2M" \ --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": "Harley-ml/Dillion-1.2M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Harley-ml/Dillion-1.2M with Docker Model Runner:
docker model run hf.co/Harley-ml/Dillion-1.2M
Create benchmarks.txt
Browse files- benchmarks.txt +87 -0
benchmarks.txt
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
| Tasks |Version|Filter|n-shot| Metric | | Value | |Stde|
|
| 2 |
+
|------------------------------------------------------------|------:|------|-----:|---------------|---|-------:|---|----|
|
| 3 |
+
|arc_challenge | 1|none | 0|acc |↑ | 0.1817|± |0.01|
|
| 4 |
+
| | |none | 0|acc_norm |↑ | 0.2244|± |0.01|
|
| 5 |
+
|arc_easy | 1|none | 0|acc |↑ | 0.3144|± |0.00|
|
| 6 |
+
| | |none | 0|acc_norm |↑ | 0.3136|± |0.00|
|
| 7 |
+
|blimp | 2|none | |acc |↑ | 0.6294|± |0.00|
|
| 8 |
+
| - blimp_adjunct_island | 1|none | 0|acc |↑ | 0.5970|± |0.01|
|
| 9 |
+
| - blimp_anaphor_gender_agreement | 1|none | 0|acc |↑ | 0.2480|± |0.01|
|
| 10 |
+
| - blimp_anaphor_number_agreement | 1|none | 0|acc |↑ | 0.5930|± |0.01|
|
| 11 |
+
| - blimp_animate_subject_passive | 1|none | 0|acc |↑ | 0.6450|± |0.01|
|
| 12 |
+
| - blimp_animate_subject_trans | 1|none | 0|acc |↑ | 0.7630|± |0.01|
|
| 13 |
+
| - blimp_causative | 1|none | 0|acc |↑ | 0.5490|± |0.01|
|
| 14 |
+
| - blimp_complex_NP_island | 1|none | 0|acc |↑ | 0.5290|± |0.01|
|
| 15 |
+
| - blimp_coordinate_structure_constraint_complex_left_branch| 1|none | 0|acc |↑ | 0.3190|± |0.01|
|
| 16 |
+
| - blimp_coordinate_structure_constraint_object_extraction | 1|none | 0|acc |↑ | 0.6490|± |0.01|
|
| 17 |
+
| - blimp_determiner_noun_agreement_1 | 1|none | 0|acc |↑ | 0.8720|± |0.01|
|
| 18 |
+
| - blimp_determiner_noun_agreement_2 | 1|none | 0|acc |↑ | 0.8800|± |0.01|
|
| 19 |
+
| - blimp_determiner_noun_agreement_irregular_1 | 1|none | 0|acc |↑ | 0.7290|± |0.01|
|
| 20 |
+
| - blimp_determiner_noun_agreement_irregular_2 | 1|none | 0|acc |↑ | 0.8230|± |0.01|
|
| 21 |
+
| - blimp_determiner_noun_agreement_with_adj_2 | 1|none | 0|acc |↑ | 0.7780|± |0.01|
|
| 22 |
+
| - blimp_determiner_noun_agreement_with_adj_irregular_1 | 1|none | 0|acc |↑ | 0.6510|± |0.01|
|
| 23 |
+
| - blimp_determiner_noun_agreement_with_adj_irregular_2 | 1|none | 0|acc |↑ | 0.7550|± |0.01|
|
| 24 |
+
| - blimp_determiner_noun_agreement_with_adjective_1 | 1|none | 0|acc |↑ | 0.8110|± |0.01|
|
| 25 |
+
| - blimp_distractor_agreement_relational_noun | 1|none | 0|acc |↑ | 0.4350|± |0.01|
|
| 26 |
+
| - blimp_distractor_agreement_relative_clause | 1|none | 0|acc |↑ | 0.3030|± |0.01|
|
| 27 |
+
| - blimp_drop_argument | 1|none | 0|acc |↑ | 0.7290|± |0.01|
|
| 28 |
+
| - blimp_ellipsis_n_bar_1 | 1|none | 0|acc |↑ | 0.4440|± |0.01|
|
| 29 |
+
| - blimp_ellipsis_n_bar_2 | 1|none | 0|acc |↑ | 0.7500|± |0.01|
|
| 30 |
+
| - blimp_existential_there_object_raising | 1|none | 0|acc |↑ | 0.7660|± |0.01|
|
| 31 |
+
| - blimp_existential_there_quantifiers_1 | 1|none | 0|acc |↑ | 0.9390|± |0.00|
|
| 32 |
+
| - blimp_existential_there_quantifiers_2 | 1|none | 0|acc |↑ | 0.4420|± |0.01|
|
| 33 |
+
| - blimp_existential_there_subject_raising | 1|none | 0|acc |↑ | 0.7570|± |0.01|
|
| 34 |
+
| - blimp_expletive_it_object_raising | 1|none | 0|acc |↑ | 0.6800|± |0.01|
|
| 35 |
+
| - blimp_inchoative | 1|none | 0|acc |↑ | 0.4160|± |0.01|
|
| 36 |
+
| - blimp_intransitive | 1|none | 0|acc |↑ | 0.5920|± |0.01|
|
| 37 |
+
| - blimp_irregular_past_participle_adjectives | 1|none | 0|acc |↑ | 0.8590|± |0.01|
|
| 38 |
+
| - blimp_irregular_past_participle_verbs | 1|none | 0|acc |↑ | 0.6770|± |0.01|
|
| 39 |
+
| - blimp_irregular_plural_subject_verb_agreement_1 | 1|none | 0|acc |↑ | 0.7190|± |0.01|
|
| 40 |
+
| - blimp_irregular_plural_subject_verb_agreement_2 | 1|none | 0|acc |↑ | 0.8020|± |0.01|
|
| 41 |
+
| - blimp_left_branch_island_echo_question | 1|none | 0|acc |↑ | 0.4720|± |0.01|
|
| 42 |
+
| - blimp_left_branch_island_simple_question | 1|none | 0|acc |↑ | 0.3430|± |0.01|
|
| 43 |
+
| - blimp_matrix_question_npi_licensor_present | 1|none | 0|acc |↑ | 0.0370|± |0.00|
|
| 44 |
+
| - blimp_npi_present_1 | 1|none | 0|acc |↑ | 0.5970|± |0.01|
|
| 45 |
+
| - blimp_npi_present_2 | 1|none | 0|acc |↑ | 0.4770|± |0.01|
|
| 46 |
+
| - blimp_only_npi_licensor_present | 1|none | 0|acc |↑ | 0.5170|± |0.01|
|
| 47 |
+
| - blimp_only_npi_scope | 1|none | 0|acc |↑ | 0.4840|± |0.01|
|
| 48 |
+
| - blimp_passive_1 | 1|none | 0|acc |↑ | 0.8170|± |0.01|
|
| 49 |
+
| - blimp_passive_2 | 1|none | 0|acc |↑ | 0.7790|± |0.01|
|
| 50 |
+
| - blimp_principle_A_c_command | 1|none | 0|acc |↑ | 0.7350|± |0.01|
|
| 51 |
+
| - blimp_principle_A_case_1 | 1|none | 0|acc |↑ | 1.0000|± | |
|
| 52 |
+
| - blimp_principle_A_case_2 | 1|none | 0|acc |↑ | 0.8370|± |0.01|
|
| 53 |
+
| - blimp_principle_A_domain_1 | 1|none | 0|acc |↑ | 0.9880|± |0.00|
|
| 54 |
+
| - blimp_principle_A_domain_2 | 1|none | 0|acc |↑ | 0.5750|± |0.01|
|
| 55 |
+
| - blimp_principle_A_domain_3 | 1|none | 0|acc |↑ | 0.4810|± |0.01|
|
| 56 |
+
| - blimp_principle_A_reconstruction | 1|none | 0|acc |↑ | 0.5350|± |0.01|
|
| 57 |
+
| - blimp_regular_plural_subject_verb_agreement_1 | 1|none | 0|acc |↑ | 0.7110|± |0.01|
|
| 58 |
+
| - blimp_regular_plural_subject_verb_agreement_2 | 1|none | 0|acc |↑ | 0.7870|± |0.01|
|
| 59 |
+
| - blimp_sentential_negation_npi_licensor_present | 1|none | 0|acc |↑ | 0.9970|± |0.00|
|
| 60 |
+
| - blimp_sentential_negation_npi_scope | 1|none | 0|acc |↑ | 0.4500|± |0.01|
|
| 61 |
+
| - blimp_sentential_subject_island | 1|none | 0|acc |↑ | 0.3070|± |0.01|
|
| 62 |
+
| - blimp_superlative_quantifiers_1 | 1|none | 0|acc |↑ | 0.5800|± |0.01|
|
| 63 |
+
| - blimp_superlative_quantifiers_2 | 1|none | 0|acc |↑ | 0.3040|± |0.01|
|
| 64 |
+
| - blimp_tough_vs_raising_1 | 1|none | 0|acc |↑ | 0.4480|± |0.01|
|
| 65 |
+
| - blimp_tough_vs_raising_2 | 1|none | 0|acc |↑ | 0.6910|± |0.01|
|
| 66 |
+
| - blimp_transitive | 1|none | 0|acc |↑ | 0.7500|± |0.01|
|
| 67 |
+
| - blimp_wh_island | 1|none | 0|acc |↑ | 0.3930|± |0.01|
|
| 68 |
+
| - blimp_wh_questions_object_gap | 1|none | 0|acc |↑ | 0.5950|± |0.01|
|
| 69 |
+
| - blimp_wh_questions_subject_gap | 1|none | 0|acc |↑ | 0.8910|± |0.00|
|
| 70 |
+
| - blimp_wh_questions_subject_gap_long_distance | 1|none | 0|acc |↑ | 0.9390|± |0.00|
|
| 71 |
+
| - blimp_wh_vs_that_no_gap | 1|none | 0|acc |↑ | 0.9700|± |0.00|
|
| 72 |
+
| - blimp_wh_vs_that_no_gap_long_distance | 1|none | 0|acc |↑ | 0.9800|± |0.00|
|
| 73 |
+
| - blimp_wh_vs_that_with_gap | 1|none | 0|acc |↑ | 0.1260|± |0.01|
|
| 74 |
+
| - blimp_wh_vs_that_with_gap_long_distance | 1|none | 0|acc |↑ | 0.0780|± |0.00|
|
| 75 |
+
|hellaswag | 1|none | 0|acc |↑ | 0.2605|± |0.00|
|
| 76 |
+
| | |none | 0|acc_norm |↑ | 0.2676|± |0.00|
|
| 77 |
+
|piqa | 1|none | 0|acc |↑ | 0.5446|± |0.01|
|
| 78 |
+
| | |none | 0|acc_norm |↑ | 0.5310|± |0.01|
|
| 79 |
+
|swag | 1|none | 0|acc |↑ | 0.2851|± |0.00|
|
| 80 |
+
| | |none | 0|acc_norm |↑ | 0.3036|± |0.00|
|
| 81 |
+
|wikitext | 2|none | 0|bits_per_byte |↓ | 1.6161|± | N|
|
| 82 |
+
| | |none | 0|byte_perplexity|↓ | 3.0655|± | N|
|
| 83 |
+
| | |none | 0|word_perplexity|↓ |399.5047|± | N|
|
| 84 |
+
|
| 85 |
+
|Groups|Version|Filter|n-shot|Metric| |Value | |Stderr|
|
| 86 |
+
|------|------:|------|------|------|---|-----:|---|-----:|
|
| 87 |
+
|blimp | 2|none | |acc |↑ |0.6294|± |0.0016|
|