Instructions to use impactframes/molmo-7B-D-bnb-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use impactframes/molmo-7B-D-bnb-4bit with Transformers:

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

pipe = pipeline("text-generation", model="impactframes/molmo-7B-D-bnb-4bit", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("impactframes/molmo-7B-D-bnb-4bit", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use impactframes/molmo-7B-D-bnb-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "impactframes/molmo-7B-D-bnb-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "impactframes/molmo-7B-D-bnb-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/impactframes/molmo-7B-D-bnb-4bit

SGLang

How to use impactframes/molmo-7B-D-bnb-4bit 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 "impactframes/molmo-7B-D-bnb-4bit" \
    --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": "impactframes/molmo-7B-D-bnb-4bit",
		"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 "impactframes/molmo-7B-D-bnb-4bit" \
        --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": "impactframes/molmo-7B-D-bnb-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use impactframes/molmo-7B-D-bnb-4bit with Docker Model Runner:
```
docker model run hf.co/impactframes/molmo-7B-D-bnb-4bit
```

molmo-7B-D-bnb-4bit / config.json

impactframes

Duplicate from cyan2k/molmo-7B-D-bnb-4bit

4f123fd verified over 1 year ago

raw

history blame contribute delete

1.34 kB

	{
	"_name_or_path": "cyan2k/molmo-7B-D-bnb-4bit",
	"architectures": [
	"MolmoForCausalLM"
	],
	"attention_layer_norm": false,
	"auto_map": {
	"AutoConfig": "config_molmo.MolmoConfig",
	"AutoModelForCausalLM": "modeling_molmo.MolmoForCausalLM"
	},
	"clip_qkv": null,
	"embedding_size": 152064,
	"hidden_size": 3584,
	"initializer_range": 0.02,
	"intermediate_size": 37888,
	"layer_norm_eps": 1e-06,
	"layer_norm_type": "rms",
	"max_position_embeddings": 4096,
	"model_type": "molmo",
	"norm_after": false,
	"num_attention_heads": 28,
	"num_hidden_layers": 28,
	"num_key_value_heads": 4,
	"qkv_bias": true,
	"quantization_config": {
	"_load_in_4bit": true,
	"_load_in_8bit": false,
	"bnb_4bit_compute_dtype": "float32",
	"bnb_4bit_quant_storage": "uint8",
	"bnb_4bit_quant_type": "fp4",
	"bnb_4bit_use_double_quant": true,
	"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": true,
	"load_in_8bit": false,
	"quant_method": "bitsandbytes"
	},
	"rope_theta": 1000000.0,
	"tie_word_embeddings": false,
	"torch_dtype": "float32",
	"transformers_version": "4.44.0",
	"use_cache": true,
	"use_position_ids": true,
	"vocab_size": 152064,
	"weight_tying": false
	}