Instructions to use kh38/my-cool-model1126 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kh38/my-cool-model1126 with Transformers:

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

pipe = pipeline("text-generation", model="kh38/my-cool-model1126")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kh38/my-cool-model1126")
model = AutoModelForCausalLM.from_pretrained("kh38/my-cool-model1126", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kh38/my-cool-model1126 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kh38/my-cool-model1126"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kh38/my-cool-model1126",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kh38/my-cool-model1126

SGLang

How to use kh38/my-cool-model1126 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 "kh38/my-cool-model1126" \
    --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": "kh38/my-cool-model1126",
		"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 "kh38/my-cool-model1126" \
        --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": "kh38/my-cool-model1126",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kh38/my-cool-model1126 with Docker Model Runner:
```
docker model run hf.co/kh38/my-cool-model1126
```

final_merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

../evol_merge_storage/input_models/Meta-Llama-3-8B-Instruct_fictional_mathqa_Spanish_v1_2935777833
../evol_merge_storage/input_models/Llama-3.1-Swallow-8B-v0.2_4249862252

Configuration

The following YAML configuration was used to produce this model:

dtype: bfloat16
merge_method: linear
parameters:
  int8_mask: 1.0
  normalize: 1.0
slices:
- sources:
  - layer_range: [0, 4]
    model: ../evol_merge_storage/input_models/Llama-3.1-Swallow-8B-v0.2_4249862252
    parameters:
      weight: 0.6682912881042561
  - layer_range: [0, 4]
    model: ../evol_merge_storage/input_models/Meta-Llama-3-8B-Instruct_fictional_mathqa_Spanish_v1_2935777833
    parameters:
      weight: 0.8169238866732543
- sources:
  - layer_range: [4, 8]
    model: ../evol_merge_storage/input_models/Llama-3.1-Swallow-8B-v0.2_4249862252
    parameters:
      weight: 0.824383032378547
  - layer_range: [4, 8]
    model: ../evol_merge_storage/input_models/Meta-Llama-3-8B-Instruct_fictional_mathqa_Spanish_v1_2935777833
    parameters:
      weight: 0.585658209873855
- sources:
  - layer_range: [8, 12]
    model: ../evol_merge_storage/input_models/Llama-3.1-Swallow-8B-v0.2_4249862252
    parameters:
      weight: 0.27646115516439407
  - layer_range: [8, 12]
    model: ../evol_merge_storage/input_models/Meta-Llama-3-8B-Instruct_fictional_mathqa_Spanish_v1_2935777833
    parameters:
      weight: 0.6421834326611193
- sources:
  - layer_range: [12, 16]
    model: ../evol_merge_storage/input_models/Llama-3.1-Swallow-8B-v0.2_4249862252
    parameters:
      weight: 0.19263623796034313
  - layer_range: [12, 16]
    model: ../evol_merge_storage/input_models/Meta-Llama-3-8B-Instruct_fictional_mathqa_Spanish_v1_2935777833
    parameters:
      weight: 0.28408471038937055
- sources:
  - layer_range: [16, 20]
    model: ../evol_merge_storage/input_models/Llama-3.1-Swallow-8B-v0.2_4249862252
    parameters:
      weight: 0.5452257394072989
  - layer_range: [16, 20]
    model: ../evol_merge_storage/input_models/Meta-Llama-3-8B-Instruct_fictional_mathqa_Spanish_v1_2935777833
    parameters:
      weight: 0.5345283738895676
- sources:
  - layer_range: [20, 24]
    model: ../evol_merge_storage/input_models/Llama-3.1-Swallow-8B-v0.2_4249862252
    parameters:
      weight: 0.6694408493851071
  - layer_range: [20, 24]
    model: ../evol_merge_storage/input_models/Meta-Llama-3-8B-Instruct_fictional_mathqa_Spanish_v1_2935777833
    parameters:
      weight: 0.36909260818773304
- sources:
  - layer_range: [24, 28]
    model: ../evol_merge_storage/input_models/Llama-3.1-Swallow-8B-v0.2_4249862252
    parameters:
      weight: 0.5611229475708517
  - layer_range: [24, 28]
    model: ../evol_merge_storage/input_models/Meta-Llama-3-8B-Instruct_fictional_mathqa_Spanish_v1_2935777833
    parameters:
      weight: 0.1981276090509695
- sources:
  - layer_range: [28, 32]
    model: ../evol_merge_storage/input_models/Llama-3.1-Swallow-8B-v0.2_4249862252
    parameters:
      weight: 0.6876393865290468
  - layer_range: [28, 32]
    model: ../evol_merge_storage/input_models/Meta-Llama-3-8B-Instruct_fictional_mathqa_Spanish_v1_2935777833
    parameters:
      weight: 0.15713286244650526

Downloads last month: 9

Safetensors

Model size

8B params

Tensor type

BF16

Paper for kh38/my-cool-model1126

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Paper • 2203.05482 • Published Mar 10, 2022 • 9