Instructions to use WebOrganizer/LM-1b_1x-DCLMFasttext with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WebOrganizer/LM-1b_1x-DCLMFasttext with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="WebOrganizer/LM-1b_1x-DCLMFasttext")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("WebOrganizer/LM-1b_1x-DCLMFasttext", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use WebOrganizer/LM-1b_1x-DCLMFasttext with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WebOrganizer/LM-1b_1x-DCLMFasttext"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WebOrganizer/LM-1b_1x-DCLMFasttext",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/WebOrganizer/LM-1b_1x-DCLMFasttext

SGLang

How to use WebOrganizer/LM-1b_1x-DCLMFasttext 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 "WebOrganizer/LM-1b_1x-DCLMFasttext" \
    --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": "WebOrganizer/LM-1b_1x-DCLMFasttext",
		"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 "WebOrganizer/LM-1b_1x-DCLMFasttext" \
        --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": "WebOrganizer/LM-1b_1x-DCLMFasttext",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use WebOrganizer/LM-1b_1x-DCLMFasttext with Docker Model Runner:
```
docker model run hf.co/WebOrganizer/LM-1b_1x-DCLMFasttext
```

LM-1b_1x-DCLMFasttext / config.json

princeton-nlp

Upload folder using huggingface_hub

fc4aea2 verified about 1 year ago

raw

history blame contribute delete

832 Bytes

	{
	"apply_qk_norm": true,
	"architectures": [
	"OpenLMForCausalLM"
	],
	"attn_activation": null,
	"attn_name": "torch_attn",
	"attn_seq_scalar": null,
	"attn_seq_scalar_alpha": null,
	"dim": 2048,
	"ffn_type": "swiglu_torch",
	"model": "open_lm_1b_swiglutorch",
	"model_type": "openlm",
	"moe_capacity_factor": 1.25,
	"moe_expert_model_parallelism": false,
	"moe_freq": 0,
	"moe_loss_weight": 0.1,
	"moe_num_experts": null,
	"moe_top_k": 2,
	"moe_weight_parallelism": false,
	"n_heads": 16,
	"n_layers": 24,
	"norm_eps": 1e-05,
	"norm_type": "gain_only_lp_layer_norm",
	"params": null,
	"positional_embedding_type": "rotary",
	"post_embed_norm": false,
	"qk_norm": true,
	"seq_len": 2048,
	"torch_dtype": "float32",
	"transformers_version": "4.40.2",
	"vocab_size": 50432,
	"weight_tying": false
	}