Text Generation
Transformers
Safetensors
English
pruned_flex_olmo
custom_code
math
pruned
distilled
mixture-of-experts
Instructions to use hbfreed/flex-math-5504 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hbfreed/flex-math-5504 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="hbfreed/flex-math-5504", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("hbfreed/flex-math-5504", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use hbfreed/flex-math-5504 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "hbfreed/flex-math-5504" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hbfreed/flex-math-5504", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/hbfreed/flex-math-5504
- SGLang
How to use hbfreed/flex-math-5504 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 "hbfreed/flex-math-5504" \ --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": "hbfreed/flex-math-5504", "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 "hbfreed/flex-math-5504" \ --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": "hbfreed/flex-math-5504", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use hbfreed/flex-math-5504 with Docker Model Runner:
docker model run hf.co/hbfreed/flex-math-5504
| { | |
| "return_dict": true, | |
| "output_hidden_states": false, | |
| "torchscript": false, | |
| "dtype": "float32", | |
| "pruned_heads": {}, | |
| "tie_word_embeddings": false, | |
| "chunk_size_feed_forward": 0, | |
| "is_encoder_decoder": false, | |
| "is_decoder": false, | |
| "cross_attention_hidden_size": null, | |
| "add_cross_attention": false, | |
| "tie_encoder_decoder": false, | |
| "architectures": [ | |
| "FlexOlmoForCausalLM" | |
| ], | |
| "finetuning_task": null, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "task_specific_params": null, | |
| "problem_type": null, | |
| "tokenizer_class": null, | |
| "prefix": null, | |
| "bos_token_id": null, | |
| "pad_token_id": 100277, | |
| "eos_token_id": 100257, | |
| "sep_token_id": null, | |
| "decoder_start_token_id": null, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "num_beams": 1, | |
| "temperature": 1.0, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "typical_p": 1.0, | |
| "repetition_penalty": 1.0, | |
| "length_penalty": 1.0, | |
| "no_repeat_ngram_size": 0, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "bad_words_ids": null, | |
| "num_return_sequences": 1, | |
| "output_scores": false, | |
| "return_dict_in_generate": false, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "remove_invalid_values": false, | |
| "exponential_decay_length_penalty": null, | |
| "suppress_tokens": null, | |
| "begin_suppress_tokens": null, | |
| "num_beam_groups": 1, | |
| "diversity_penalty": 0.0, | |
| "_name_or_path": "allenai/Flex-math-2x7B-1T", | |
| "transformers_version": "4.57.6", | |
| "clip_qkv": null, | |
| "model_type": "pruned_flex_olmo", | |
| "tf_legacy_loss": false, | |
| "use_bfloat16": false, | |
| "vocab_size": 100352, | |
| "max_position_embeddings": 4096, | |
| "hidden_size": 4096, | |
| "intermediate_size": 11008, | |
| "num_hidden_layers": 32, | |
| "num_attention_heads": 32, | |
| "num_key_value_heads": 32, | |
| "hidden_act": "silu", | |
| "initializer_range": 0.02, | |
| "rms_norm_eps": 1e-06, | |
| "use_cache": true, | |
| "rope_theta": 500000, | |
| "rope_scaling": null, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "num_experts_per_tok": 2, | |
| "num_experts": 2, | |
| "output_router_logits": false, | |
| "router_aux_loss_coef": 0.01, | |
| "norm_topk_prob": false, | |
| "output_attentions": false, | |
| "expert_1_intermediate_size": 5504, | |
| "auto_map": { | |
| "AutoConfig": "configuration_pruned_flex_olmo.PrunedFlexOlmoConfig", | |
| "AutoModelForCausalLM": "modeling_pruned_flex_olmo.PrunedFlexOlmoForCausalLM" | |
| }, | |
| "_pruning_metadata": { | |
| "base_model": "allenai/Flex-math-2x7B-1T", | |
| "importance_type": "math" | |
| } | |
| } |