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

Libraries

How to use izzcw/crafting_sft_fail_new_mem with Transformers:

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

pipe = pipeline("text-generation", model="izzcw/crafting_sft_fail_new_mem")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("izzcw/crafting_sft_fail_new_mem")
model = AutoModelForCausalLM.from_pretrained("izzcw/crafting_sft_fail_new_mem")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use izzcw/crafting_sft_fail_new_mem with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "izzcw/crafting_sft_fail_new_mem"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "izzcw/crafting_sft_fail_new_mem",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/izzcw/crafting_sft_fail_new_mem

SGLang

How to use izzcw/crafting_sft_fail_new_mem 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 "izzcw/crafting_sft_fail_new_mem" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "izzcw/crafting_sft_fail_new_mem",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "izzcw/crafting_sft_fail_new_mem" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "izzcw/crafting_sft_fail_new_mem",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

crafting_sft_fail_new_mem

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the identity and the crafting_sft_fail_new_mem datasets. It achieves the following results on the evaluation set:

Loss: 0.3208

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: 1e-05
train_batch_size: 1
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 16
total_train_batch_size: 128
total_eval_batch_size: 16
optimizer: Use 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: 0.1
num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.5341	0.0323	50	0.4793
0.5261	0.0646	100	0.4858
0.5103	0.0969	150	0.4932
0.5236	0.1291	200	0.4820
0.524	0.1614	250	0.4623
0.5107	0.1937	300	0.4454
0.4723	0.2260	350	0.4380
0.4771	0.2583	400	0.4323
0.4835	0.2906	450	0.4249
0.455	0.3229	500	0.4205
0.4724	0.3552	550	0.4145
0.4579	0.3874	600	0.4005
0.4691	0.4197	650	0.4049
0.4405	0.4520	700	0.3883
0.4443	0.4843	750	0.3845
0.4348	0.5166	800	0.3788
0.4153	0.5489	850	0.3675
0.4123	0.5812	900	0.3647
0.3943	0.6134	950	0.3590
0.4059	0.6457	1000	0.3495
0.3778	0.6780	1050	0.3437
0.3734	0.7103	1100	0.3430
0.3762	0.7426	1150	0.3367
0.3576	0.7749	1200	0.3327
0.3794	0.8072	1250	0.3295
0.3695	0.8395	1300	0.3265
0.3571	0.8717	1350	0.3233
0.3655	0.9040	1400	0.3225
0.3801	0.9363	1450	0.3211
0.3704	0.9686	1500	0.3209

Framework versions

Transformers 4.49.0
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0

Downloads last month: 2

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for izzcw/crafting_sft_fail_new_mem

Base model

meta-llama/Llama-3.1-8B

Finetuned

meta-llama/Llama-3.1-8B-Instruct

Finetuned

(2824)

this model