Instructions to use codead6/interview_help_quantized_8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use codead6/interview_help_quantized_8bit with Transformers:

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

pipe = pipeline("text-generation", model="codead6/interview_help_quantized_8bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("codead6/interview_help_quantized_8bit")
model = AutoModelForCausalLM.from_pretrained("codead6/interview_help_quantized_8bit")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use codead6/interview_help_quantized_8bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "codead6/interview_help_quantized_8bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "codead6/interview_help_quantized_8bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/codead6/interview_help_quantized_8bit

SGLang

How to use codead6/interview_help_quantized_8bit 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 "codead6/interview_help_quantized_8bit" \
    --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": "codead6/interview_help_quantized_8bit",
		"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 "codead6/interview_help_quantized_8bit" \
        --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": "codead6/interview_help_quantized_8bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use codead6/interview_help_quantized_8bit with Docker Model Runner:
```
docker model run hf.co/codead6/interview_help_quantized_8bit
```

interview_help_quantized_8bit / config.json

codead6

Upload RwkvForCausalLM

cf92f87 verified over 1 year ago

Raw

History Blame Contribute Delete

977 Bytes

	{
	"_name_or_path": "beomi/KoAlpaca-KoRWKV-6B",
	"architectures": [
	"RwkvForCausalLM"
	],
	"attention_hidden_size": 4096,
	"bos_token_id": 0,
	"context_length": 2048,
	"eos_token_id": 0,
	"hidden_size": 4096,
	"intermediate_size": 16384,
	"layer_norm_epsilon": 1e-05,
	"model_type": "rwkv",
	"num_hidden_layers": 28,
	"quantization_config": {
	"_load_in_4bit": false,
	"_load_in_8bit": true,
	"bnb_4bit_compute_dtype": "float32",
	"bnb_4bit_quant_storage": "uint8",
	"bnb_4bit_quant_type": "fp4",
	"bnb_4bit_use_double_quant": false,
	"llm_int8_enable_fp32_cpu_offload": false,
	"llm_int8_has_fp16_weight": false,
	"llm_int8_skip_modules": null,
	"llm_int8_threshold": 6.0,
	"load_in_4bit": false,
	"load_in_8bit": true,
	"quant_method": "bitsandbytes"
	},
	"rescale_every": 6,
	"tie_word_embeddings": false,
	"torch_dtype": "float16",
	"transformers_version": "4.46.2",
	"use_cache": true,
	"vocab_size": 52000
	}