Instructions to use GRKTheGreat/ForgeLM-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GRKTheGreat/ForgeLM-v1 with Transformers:

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

pipe = pipeline("text-generation", model="GRKTheGreat/ForgeLM-v1", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import ForgeLM
model = ForgeLM.from_pretrained("GRKTheGreat/ForgeLM-v1", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use GRKTheGreat/ForgeLM-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/GRKTheGreat/ForgeLM-v1

SGLang

How to use GRKTheGreat/ForgeLM-v1 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 "GRKTheGreat/ForgeLM-v1" \
    --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": "GRKTheGreat/ForgeLM-v1",
		"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 "GRKTheGreat/ForgeLM-v1" \
        --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": "GRKTheGreat/ForgeLM-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use GRKTheGreat/ForgeLM-v1 with Docker Model Runner:
```
docker model run hf.co/GRKTheGreat/ForgeLM-v1
```

ForgeLM-v1 / config.json

GRKTheGreat

Upload ForgeLM v1 — training-free KeyStack port of Qwen2.5-Coder-1.5B

72c2207 verified 5 days ago

Raw

History Blame Contribute Delete

1.09 kB

	{
	"architectures": [
	"ForgeLM"
	],
	"model_type": "forgelm",
	"base_model": "Qwen/Qwen2.5-Coder-1.5B-Instruct",
	"vocab_size": 151936,
	"hidden_size": 1536,
	"num_hidden_layers": 28,
	"num_attention_heads": 12,
	"num_key_value_heads": 2,
	"intermediate_size": 8960,
	"hidden_act": "silu",
	"max_position_embeddings": 32768,
	"rms_norm_eps": 1e-06,
	"rope_theta": 1000000.0,
	"tie_word_embeddings": false,
	"torch_dtype": "bfloat16",
	"use_cache": true,
	"attention_bias": true,
	"bias": true,
	"attention_type": "mla",
	"kv_compression_dim": 512,
	"ffn_type": "moe",
	"moe_num_experts": 4,
	"moe_top_k": 4,
	"moe_shared_expert": true,
	"moe_expert_size": 1792,
	"keystack_features": [
	"mla",
	"moe",
	"mrl",
	"quarot",
	"value_residual",
	"rotorquant",
	"mtp",
	"airllm"
	],
	"keystack_cosine_similarity": 1.0,
	"training_required": false,
	"vibe_coded": true,
	"vibe_coded_by": "Devin Desktop (Cognition)",
	"auto_map": {
	"AutoModelForCausalLM": "modeling_forgelm.ForgeLMForCausalLM"
	},
	"transformers_version": "4.51.3"
	}