Instructions to use Jashan887/90_Yarn_LongMemory with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jashan887/90_Yarn_LongMemory with Transformers:

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

pipe = pipeline("text-generation", model="Jashan887/90_Yarn_LongMemory", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Jashan887/90_Yarn_LongMemory", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Jashan887/90_Yarn_LongMemory", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Jashan887/90_Yarn_LongMemory with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jashan887/90_Yarn_LongMemory"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jashan887/90_Yarn_LongMemory",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Jashan887/90_Yarn_LongMemory

SGLang

How to use Jashan887/90_Yarn_LongMemory 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 "Jashan887/90_Yarn_LongMemory" \
    --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": "Jashan887/90_Yarn_LongMemory",
		"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 "Jashan887/90_Yarn_LongMemory" \
        --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": "Jashan887/90_Yarn_LongMemory",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Jashan887/90_Yarn_LongMemory with Docker Model Runner:
```
docker model run hf.co/Jashan887/90_Yarn_LongMemory
```

90_Yarn_LongMemory / config.json

Jashan887

Upload folder using huggingface_hub

657cc77 verified 25 days ago

raw

history blame contribute delete

975 Bytes

	{
	"_name_or_path": "/fsx/proj-trlx/conceptofmind/scaled-rope-private/save_model/final/yarn-llama-2-7b-3e-5-64k-600steps-32scale",
	"architectures": [
	"LlamaForCausalLM"
	],
	"auto_map": {
	"AutoConfig": "configuration_llama.LlamaConfig",
	"AutoModelForCausalLM": "modeling_llama_together_yarn.LlamaForCausalLM"
	},
	"bos_token_id": 1,
	"eos_token_id": 2,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 11008,
	"max_position_embeddings": 131072,
	"model_type": "llama",
	"num_attention_heads": 32,
	"num_hidden_layers": 32,
	"num_key_value_heads": 32,
	"pad_token_id": 0,
	"pretraining_tp": 1,
	"rms_norm_eps": 1e-05,
	"rope_scaling": {
	"factor": 32.0,
	"original_max_position_embeddings": 4096,
	"type": "yarn",
	"finetuned": true
	},
	"tie_word_embeddings": false,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.32.0.dev0",
	"use_cache": true,
	"vocab_size": 32000
	}