Text Generation
Transformers
Safetensors
English
shivik_code
code
causal-lm
shivik
conversational
custom_code
Instructions to use theaicompany02/Shivik-Code-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use theaicompany02/Shivik-Code-1B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="theaicompany02/Shivik-Code-1B", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("theaicompany02/Shivik-Code-1B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use theaicompany02/Shivik-Code-1B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "theaicompany02/Shivik-Code-1B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "theaicompany02/Shivik-Code-1B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/theaicompany02/Shivik-Code-1B
- SGLang
How to use theaicompany02/Shivik-Code-1B 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 "theaicompany02/Shivik-Code-1B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "theaicompany02/Shivik-Code-1B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "theaicompany02/Shivik-Code-1B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "theaicompany02/Shivik-Code-1B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use theaicompany02/Shivik-Code-1B with Docker Model Runner:
docker model run hf.co/theaicompany02/Shivik-Code-1B
Download config.json from theaicompany02/Shivik-Code-1B: direct link, hf CLI and curl.
- Browser
- Download file 2.79 kB
-
https://huggingface.co/theaicompany02/Shivik-Code-1B/resolve/main/config.json
- Command line
-
hf download hf://theaicompany02/Shivik-Code-1B/config.json
-
curl -L -o config.json https://huggingface.co/theaicompany02/Shivik-Code-1B/resolve/main/config.json
2.79 kB
| { | |
| "vocab_size": 128279, | |
| "max_position_embeddings": 131072, | |
| "hidden_size": 2048, | |
| "intermediate_size": 8192, | |
| "num_hidden_layers": 16, | |
| "num_attention_heads": 32, | |
| "num_key_value_heads": 8, | |
| "hidden_act": "silu", | |
| "initializer_range": 0.02, | |
| "rms_norm_eps": 1e-05, | |
| "use_cache": true, | |
| "rope_theta": 500000.0, | |
| "rope_scaling": { | |
| "factor": 32.0, | |
| "high_freq_factor": 4.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_type": "llama3" | |
| }, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "mlp_bias": false, | |
| "head_dim": 64, | |
| "return_dict": true, | |
| "output_hidden_states": false, | |
| "torchscript": false, | |
| "dtype": "bfloat16", | |
| "pruned_heads": {}, | |
| "tie_word_embeddings": true, | |
| "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": [ | |
| "ShivikCodeForCausalLM" | |
| ], | |
| "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": 128000, | |
| "pad_token_id": null, | |
| "eos_token_id": [ | |
| 128001, | |
| 128008, | |
| 128009 | |
| ], | |
| "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, | |
| "transformers_version": "4.57.6", | |
| "model_type": "shivik_code", | |
| "tf_legacy_loss": false, | |
| "use_bfloat16": false, | |
| "output_attentions": false, | |
| "auto_map": { | |
| "AutoConfig": "configuration_shivik_code.ShivikCodeConfig", | |
| "AutoModelForCausalLM": "modeling_shivik_code.ShivikCodeForCausalLM" | |
| }, | |
| "_shivik_code_version": "1.0", | |
| "_tool_tokens": { | |
| "tool_call_start": 128256, | |
| "tool_call_end": 128257, | |
| "tool_result_start": 128258, | |
| "tool_result_end": 128259 | |
| }, | |
| "_reasoning_tokens": { | |
| "think_start": 128260, | |
| "think_end": 128261, | |
| "plan_start": 128266, | |
| "plan_end": 128267 | |
| }, | |
| "_fim_tokens": { | |
| "fim_prefix": 128276, | |
| "fim_suffix": 128277, | |
| "fim_middle": 128278 | |
| } | |
| } |