openai/gsm8k
Benchmark • Updated • 17.6k • 1.24M • 2.08k
How to use ITLL/LFM3-1.7B-RD-Coder-SLERP with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="ITLL/LFM3-1.7B-RD-Coder-SLERP", trust_remote_code=True) # pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ITLL/LFM3-1.7B-RD-Coder-SLERP", trust_remote_code=True, device_map="auto")How to use ITLL/LFM3-1.7B-RD-Coder-SLERP with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ITLL/LFM3-1.7B-RD-Coder-SLERP"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "ITLL/LFM3-1.7B-RD-Coder-SLERP",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/ITLL/LFM3-1.7B-RD-Coder-SLERP
How to use ITLL/LFM3-1.7B-RD-Coder-SLERP with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "ITLL/LFM3-1.7B-RD-Coder-SLERP" \
--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": "ITLL/LFM3-1.7B-RD-Coder-SLERP",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'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 "ITLL/LFM3-1.7B-RD-Coder-SLERP" \
--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": "ITLL/LFM3-1.7B-RD-Coder-SLERP",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use ITLL/LFM3-1.7B-RD-Coder-SLERP with Docker Model Runner:
docker model run hf.co/ITLL/LFM3-1.7B-RD-Coder-SLERP
This is a merge of pre-trained language models created using mergekit.
This model was merged using the SLERP merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: cybertruck32489/LFM3-1.7B-RD-v2
- model: ITLL/LFM-3-Coder-Claude-Distill
merge_method: slerp
base_model: cybertruck32489/LFM3-1.7B-RD-v2
parameters:
t: 0.5
dtype: bfloat16
out_dtype: bfloat16