Instructions to use donoway/GSM8K-Binary_Llama-3.2-1B-rtd7v6w7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use donoway/GSM8K-Binary_Llama-3.2-1B-rtd7v6w7 with Transformers:

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

pipe = pipeline("text-generation", model="donoway/GSM8K-Binary_Llama-3.2-1B-rtd7v6w7")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("donoway/GSM8K-Binary_Llama-3.2-1B-rtd7v6w7")
model = AutoModelForCausalLM.from_pretrained("donoway/GSM8K-Binary_Llama-3.2-1B-rtd7v6w7")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use donoway/GSM8K-Binary_Llama-3.2-1B-rtd7v6w7 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "donoway/GSM8K-Binary_Llama-3.2-1B-rtd7v6w7"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "donoway/GSM8K-Binary_Llama-3.2-1B-rtd7v6w7",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/donoway/GSM8K-Binary_Llama-3.2-1B-rtd7v6w7

SGLang

How to use donoway/GSM8K-Binary_Llama-3.2-1B-rtd7v6w7 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 "donoway/GSM8K-Binary_Llama-3.2-1B-rtd7v6w7" \
    --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": "donoway/GSM8K-Binary_Llama-3.2-1B-rtd7v6w7",
		"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 "donoway/GSM8K-Binary_Llama-3.2-1B-rtd7v6w7" \
        --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": "donoway/GSM8K-Binary_Llama-3.2-1B-rtd7v6w7",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use donoway/GSM8K-Binary_Llama-3.2-1B-rtd7v6w7 with Docker Model Runner:
```
docker model run hf.co/donoway/GSM8K-Binary_Llama-3.2-1B-rtd7v6w7
```

GSM8K-Binary_Llama-3.2-1B-rtd7v6w7

This model is a fine-tuned version of meta-llama/Llama-3.2-1B on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.8309
Model Preparation Time: 0.0055
Mdl: 2966.8667
Accumulated Loss: 2056.4753
Correct Preds: 1984.0
Total Preds: 2475.0
Accuracy: 0.8016
Correct Gen Preds: 1758.0
Gen Accuracy: 0.7103
Correct Gen Preds 34192: 869.0
Correct Preds 34192: 1016.0
Total Labels 34192: 1196.0
Accuracy 34192: 0.8495
Gen Accuracy 34192: 0.7266
Correct Gen Preds 41568: 881.0
Correct Preds 41568: 968.0
Total Labels 41568: 1267.0
Accuracy 41568: 0.7640
Gen Accuracy 41568: 0.6953

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 32
eval_batch_size: 64
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.01
num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	Mdl	Accumulated Loss	Correct Preds	Total Preds	Accuracy	Correct Gen Preds	Gen Accuracy	Correct Gen Preds 34192	Correct Preds 34192	Total Labels 34192	Accuracy 34192	Gen Accuracy 34192	Correct Gen Preds 41568	Correct Preds 41568	Total Labels 41568	Accuracy 41568	Gen Accuracy 41568
No log	0	0	1.4656	0.0055	5233.1723	3627.3586	1196.0	2475.0	0.4832	1204.0	0.4865	1196.0	1196.0	1196.0	1.0	1.0	0.0	0.0	1267.0	0.0	0.0
0.7154	1.0	25	0.6989	0.0055	2495.4759	1729.7321	1514.0	2475.0	0.6117	949.0	0.3834	661.0	1174.0	1196.0	0.9816	0.5527	280.0	340.0	1267.0	0.2684	0.2210
0.9619	2.0	50	0.7183	0.0055	2564.7178	1777.7269	1557.0	2475.0	0.6291	23.0	0.0093	0.0	338.0	1196.0	0.2826	0.0	15.0	1219.0	1267.0	0.9621	0.0118
0.7749	3.0	75	0.5842	0.0055	2086.0604	1445.9469	1857.0	2475.0	0.7503	260.0	0.1051	0.0	718.0	1196.0	0.6003	0.0	252.0	1139.0	1267.0	0.8990	0.1989
0.3418	4.0	100	1.0916	0.0055	3897.6253	2701.6280	1690.0	2475.0	0.6828	379.0	0.1531	272.0	1174.0	1196.0	0.9816	0.2274	99.0	516.0	1267.0	0.4073	0.0781
0.5389	5.0	125	0.7000	0.0055	2499.5846	1732.5800	1936.0	2475.0	0.7822	353.0	0.1426	115.0	1040.0	1196.0	0.8696	0.0962	231.0	896.0	1267.0	0.7072	0.1823
0.4228	6.0	150	0.8309	0.0055	2966.8667	2056.4753	1984.0	2475.0	0.8016	1758.0	0.7103	869.0	1016.0	1196.0	0.8495	0.7266	881.0	968.0	1267.0	0.7640	0.6953
0.0038	7.0	175	1.0896	0.0055	3890.7175	2696.8399	1907.0	2475.0	0.7705	1087.0	0.4392	596.0	1096.0	1196.0	0.9164	0.4983	484.0	811.0	1267.0	0.6401	0.3820
0.0096	8.0	200	1.1357	0.0055	4055.3565	2810.9589	1951.0	2475.0	0.7883	1898.0	0.7669	963.0	987.0	1196.0	0.8253	0.8052	927.0	964.0	1267.0	0.7609	0.7316
0.3927	9.0	225	1.4010	0.0055	5002.5226	3467.4844	1976.0	2475.0	0.7984	1937.0	0.7826	1017.0	1046.0	1196.0	0.8746	0.8503	913.0	930.0	1267.0	0.7340	0.7206
0.0001	10.0	250	1.2540	0.0055	4477.7630	3103.7488	1983.0	2475.0	0.8012	1946.0	0.7863	964.0	993.0	1196.0	0.8303	0.8060	975.0	990.0	1267.0	0.7814	0.7695
0.3922	11.0	275	1.3906	0.0055	4965.3047	3441.6870	1964.0	2475.0	0.7935	1932.0	0.7806	1029.0	1047.0	1196.0	0.8754	0.8604	896.0	917.0	1267.0	0.7238	0.7072
0.0	12.0	300	1.4206	0.0055	5072.5476	3516.0220	1966.0	2475.0	0.7943	1947.0	0.7867	1030.0	1046.0	1196.0	0.8746	0.8612	910.0	920.0	1267.0	0.7261	0.7182
0.3921	13.0	325	1.4252	0.0055	5089.0899	3527.4883	1967.0	2475.0	0.7947	1954.0	0.7895	1029.0	1041.0	1196.0	0.8704	0.8604	918.0	926.0	1267.0	0.7309	0.7245
0.0	14.0	350	1.4296	0.0055	5104.8061	3538.3819	1968.0	2475.0	0.7952	1956.0	0.7903	1027.0	1040.0	1196.0	0.8696	0.8587	922.0	928.0	1267.0	0.7324	0.7277
0.3921	15.0	375	1.4327	0.0055	5115.6967	3545.9308	1973.0	2475.0	0.7972	1964.0	0.7935	1029.0	1040.0	1196.0	0.8696	0.8604	928.0	933.0	1267.0	0.7364	0.7324
0.3921	16.0	400	1.4372	0.0055	5131.6445	3556.9849	1972.0	2475.0	0.7968	1961.0	0.7923	1028.0	1039.0	1196.0	0.8687	0.8595	926.0	933.0	1267.0	0.7364	0.7309
0.0	17.0	425	1.4412	0.0055	5146.1676	3567.0516	1972.0	2475.0	0.7968	1961.0	0.7923	1027.0	1038.0	1196.0	0.8679	0.8587	927.0	934.0	1267.0	0.7372	0.7316
0.7841	18.0	450	1.4461	0.0055	5163.7167	3579.2156	1970.0	2475.0	0.7960	1962.0	0.7927	1026.0	1037.0	1196.0	0.8671	0.8579	929.0	933.0	1267.0	0.7364	0.7332
0.0	19.0	475	1.4499	0.0055	5177.0033	3588.4253	1972.0	2475.0	0.7968	1966.0	0.7943	1027.0	1036.0	1196.0	0.8662	0.8587	932.0	936.0	1267.0	0.7388	0.7356
0.0	20.0	500	1.4508	0.0055	5180.3062	3590.7146	1971.0	2475.0	0.7964	1964.0	0.7935	1025.0	1035.0	1196.0	0.8654	0.8570	932.0	936.0	1267.0	0.7388	0.7356
0.3921	21.0	525	1.4534	0.0055	5189.7817	3597.2826	1974.0	2475.0	0.7976	1969.0	0.7956	1029.0	1038.0	1196.0	0.8679	0.8604	933.0	936.0	1267.0	0.7388	0.7364
0.0	22.0	550	1.4580	0.0055	5206.0889	3608.5858	1971.0	2475.0	0.7964	1964.0	0.7935	1028.0	1038.0	1196.0	0.8679	0.8595	929.0	933.0	1267.0	0.7364	0.7332
0.0	23.0	575	1.4600	0.0055	5213.0440	3613.4067	1975.0	2475.0	0.7980	1968.0	0.7952	1027.0	1037.0	1196.0	0.8671	0.8587	934.0	938.0	1267.0	0.7403	0.7372
0.0	24.0	600	1.4608	0.0055	5216.0428	3615.4854	1975.0	2475.0	0.7980	1970.0	0.7960	1027.0	1036.0	1196.0	0.8662	0.8587	936.0	939.0	1267.0	0.7411	0.7388
0.0	25.0	625	1.4642	0.0055	5228.0668	3623.8198	1973.0	2475.0	0.7972	1967.0	0.7947	1028.0	1037.0	1196.0	0.8671	0.8595	932.0	936.0	1267.0	0.7388	0.7356
0.0	26.0	650	1.4671	0.0055	5238.4672	3631.0288	1973.0	2475.0	0.7972	1969.0	0.7956	1025.0	1034.0	1196.0	0.8645	0.8570	937.0	939.0	1267.0	0.7411	0.7395

Framework versions

Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 3.5.0
Tokenizers 0.21.1

Downloads last month: 1

Safetensors

Model size

1B params

Tensor type

BF16

Model tree for donoway/GSM8K-Binary_Llama-3.2-1B-rtd7v6w7

Base model

meta-llama/Llama-3.2-1B

Finetuned

(915)

this model