Instructions to use smcleish/clrs_llama_3_8b_100k_finetune_with_traces with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use smcleish/clrs_llama_3_8b_100k_finetune_with_traces with Transformers:

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

pipe = pipeline("text-generation", model="smcleish/clrs_llama_3_8b_100k_finetune_with_traces")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("smcleish/clrs_llama_3_8b_100k_finetune_with_traces")
model = AutoModelForCausalLM.from_pretrained("smcleish/clrs_llama_3_8b_100k_finetune_with_traces")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use smcleish/clrs_llama_3_8b_100k_finetune_with_traces with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "smcleish/clrs_llama_3_8b_100k_finetune_with_traces"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "smcleish/clrs_llama_3_8b_100k_finetune_with_traces",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/smcleish/clrs_llama_3_8b_100k_finetune_with_traces

SGLang

How to use smcleish/clrs_llama_3_8b_100k_finetune_with_traces 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 "smcleish/clrs_llama_3_8b_100k_finetune_with_traces" \
    --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": "smcleish/clrs_llama_3_8b_100k_finetune_with_traces",
		"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 "smcleish/clrs_llama_3_8b_100k_finetune_with_traces" \
        --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": "smcleish/clrs_llama_3_8b_100k_finetune_with_traces",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use smcleish/clrs_llama_3_8b_100k_finetune_with_traces with Docker Model Runner:
```
docker model run hf.co/smcleish/clrs_llama_3_8b_100k_finetune_with_traces
```

Model Details

meta-llama/Meta-Llama-3-8B model finetuned on 100,000 CLRS-Text examples.

Training Details

Learning Rate: 1e-4, 150 warmup steps then cosine decayed to 5e-06 using AdamW optimiser
Batch size: 128
Loss taken over answer only, not on question.

Downloads last month: 5

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for smcleish/clrs_llama_3_8b_100k_finetune_with_traces

Base model

meta-llama/Meta-Llama-3-8B

Finetuned

(606)

this model