Text Generation
Transformers
Safetensors
Sanskrit
sansar
sanskrit
devanagari
slp1
causal-lm
base-model
custom_code
Eval Results (legacy)
Instructions to use MuseMesh/sansar-60m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MuseMesh/sansar-60m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MuseMesh/sansar-60m", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("MuseMesh/sansar-60m", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use MuseMesh/sansar-60m with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MuseMesh/sansar-60m" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MuseMesh/sansar-60m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MuseMesh/sansar-60m
- SGLang
How to use MuseMesh/sansar-60m 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 "MuseMesh/sansar-60m" \ --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": "MuseMesh/sansar-60m", "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 "MuseMesh/sansar-60m" \ --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": "MuseMesh/sansar-60m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MuseMesh/sansar-60m with Docker Model Runner:
docker model run hf.co/MuseMesh/sansar-60m
Download config.json from MuseMesh/sansar-60m: direct link, hf CLI and curl.
- Browser
- Download file 784 Bytes
-
https://huggingface.co/MuseMesh/sansar-60m/resolve/main/config.json
- Command line
-
hf download hf://MuseMesh/sansar-60m/config.json
-
curl -L -o config.json https://huggingface.co/MuseMesh/sansar-60m/resolve/main/config.json
784 Bytes
| { | |
| "architectures": [ | |
| "SansarForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_sansar.SansarConfig", | |
| "AutoModelForCausalLM": "modeling_sansar.SansarForCausalLM" | |
| }, | |
| "bias": false, | |
| "block_size": 512, | |
| "bos_token_id": 1, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 2, | |
| "initializer_range": 0.02, | |
| "layer_norm_eps": 1e-05, | |
| "logit_cap": 0.0, | |
| "mlp_ratio": 4, | |
| "model_type": "sansar", | |
| "n_embd": 768, | |
| "n_head": 12, | |
| "n_layer": 8, | |
| "pad_token_id": 2, | |
| "qk_norm": false, | |
| "relu_sq": false, | |
| "rope": false, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "5.18.0", | |
| "untied_head": false, | |
| "use_cache": false, | |
| "value_embed": false, | |
| "value_embed_layers": "", | |
| "vocab_size": 8000 | |
| } | |