Instructions to use TehVenom/DiffMerge_Pygmalion_Main-onto-V8P4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TehVenom/DiffMerge_Pygmalion_Main-onto-V8P4 with Transformers:

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

pipe = pipeline("text-generation", model="TehVenom/DiffMerge_Pygmalion_Main-onto-V8P4")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TehVenom/DiffMerge_Pygmalion_Main-onto-V8P4")
model = AutoModelForCausalLM.from_pretrained("TehVenom/DiffMerge_Pygmalion_Main-onto-V8P4")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TehVenom/DiffMerge_Pygmalion_Main-onto-V8P4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TehVenom/DiffMerge_Pygmalion_Main-onto-V8P4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TehVenom/DiffMerge_Pygmalion_Main-onto-V8P4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TehVenom/DiffMerge_Pygmalion_Main-onto-V8P4

SGLang

How to use TehVenom/DiffMerge_Pygmalion_Main-onto-V8P4 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 "TehVenom/DiffMerge_Pygmalion_Main-onto-V8P4" \
    --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": "TehVenom/DiffMerge_Pygmalion_Main-onto-V8P4",
		"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 "TehVenom/DiffMerge_Pygmalion_Main-onto-V8P4" \
        --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": "TehVenom/DiffMerge_Pygmalion_Main-onto-V8P4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TehVenom/DiffMerge_Pygmalion_Main-onto-V8P4 with Docker Model Runner:
```
docker model run hf.co/TehVenom/DiffMerge_Pygmalion_Main-onto-V8P4
```

DiffMerge_Pygmalion_Main-onto-V8P4 / config.json

TehVenom

Upload 11 files

7dd875a about 3 years ago

raw

history blame contribute delete

1.33 kB

	{
	"_name_or_path": "TehVenom_DiffMerge_Pygmalion_Main-onto-V8P4",
	"activation_function": "gelu_new",
	"architectures": [
	"GPTJForCausalLM"
	],
	"attn_pdrop": 0.0,
	"badwordsids": [
	[
	10619,
	62,
	19238,
	62,
	35,
	12576,
	7730
	]
	],
	"bos_token_id": 50256,
	"embd_pdrop": 0.0,
	"eos_token_id": 50256,
	"gradient_checkpointing": false,
	"initializer_range": 0.02,
	"layer_norm_epsilon": 1e-05,
	"model_type": "gptj",
	"n_embd": 4096,
	"n_head": 16,
	"n_inner": null,
	"n_layer": 28,
	"n_positions": 2048,
	"resid_pdrop": 0.0,
	"rotary_dim": 64,
	"scale_attn_weights": true,
	"summary_activation": null,
	"summary_first_dropout": 0.1,
	"summary_proj_to_labels": true,
	"summary_type": "cls_index",
	"summary_use_proj": true,
	"task_specific_params": {
	"text-generation": {
	"do_sample": true,
	"max_length": 50,
	"temperature": 0.5
	}
	},
	"tie_word_embeddings": false,
	"tokenizer_class": "GPT2Tokenizer",
	"torch_dtype": "float16",
	"transformers_version": "4.25.0.dev0",
	"use_cache": true,
	"vocab_size": 50400,
	"welcome": "You are currently running a Diff Mix of the two models Pygmalion/pygmalion-6b (Main build) and Pygmalion/pygmalion-6b-dev (V8P4 build), using the following formula:\n((Main - V8p4) + V8P4)"
	}