Instructions to use LLM360/CrystalChat-7B-Web2Code with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LLM360/CrystalChat-7B-Web2Code with Transformers:

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

pipe = pipeline("text-generation", model="LLM360/CrystalChat-7B-Web2Code", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("LLM360/CrystalChat-7B-Web2Code", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use LLM360/CrystalChat-7B-Web2Code with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LLM360/CrystalChat-7B-Web2Code"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LLM360/CrystalChat-7B-Web2Code",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/LLM360/CrystalChat-7B-Web2Code

SGLang

How to use LLM360/CrystalChat-7B-Web2Code 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 "LLM360/CrystalChat-7B-Web2Code" \
    --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": "LLM360/CrystalChat-7B-Web2Code",
		"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 "LLM360/CrystalChat-7B-Web2Code" \
        --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": "LLM360/CrystalChat-7B-Web2Code",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use LLM360/CrystalChat-7B-Web2Code with Docker Model Runner:
```
docker model run hf.co/LLM360/CrystalChat-7B-Web2Code
```

CrystalChat-7B-Web2Code / config.json

qazimbhat1

Add initial model files

acbaabd almost 2 years ago

raw

history blame contribute delete

1.59 kB

	{
	"_name_or_path": "LLM360/CrystalChat",
	"activation_function": "swiglu",
	"architectures": [
	"LlavaCrystalForCausalLM"
	],
	"attn_pdrop": 0.0,
	"auto_map": {
	"AutoConfig": "LLM360/CrystalChat--configuration_crystalcoder.CrystalCoderConfig",
	"AutoModel": "LLM360/CrystalChat--modeling_crystalcoder.CrystalCoderModel",
	"AutoModelForCausalLM": "LLM360/CrystalChat--modeling_crystalcoder.CrystalCoderLMHeadModel"
	},
	"bos_token_id": 1,
	"embd_pdrop": 0.0,
	"eos_token_id": 2,
	"freeze_mm_mlp_adapter": false,
	"image_aspect_ratio": "pad",
	"initializer_range": 0.02,
	"layer_norm_epsilon": 1e-05,
	"mm_hidden_size": 1024,
	"mm_projector_lr": null,
	"mm_projector_type": "mlp2x_gelu",
	"mm_use_im_patch_token": false,
	"mm_use_im_start_end": false,
	"mm_vision_select_feature": "patch",
	"mm_vision_select_layer": -2,
	"mm_vision_tower": "openai/clip-vit-large-patch14-336",
	"model_type": "llava_crystal",
	"mup_embeddings_scale": 14.6,
	"mup_output_alpha": 2.22,
	"mup_scale_qk_dot_by_d": true,
	"mup_width_scale": 0.0625,
	"n_embd": 4096,
	"n_head": 32,
	"n_inner": 10922,
	"n_layer": 32,
	"n_positions": 2048,
	"position_embedding_type": "rotary",
	"reorder_and_upcast_attn": false,
	"resid_pdrop": 0.0,
	"rotary_dim": 32,
	"scale_attn_by_inverse_layer_idx": false,
	"scale_attn_weights": true,
	"tokenizer_model_max_length": 2048,
	"tokenizer_padding_side": "right",
	"torch_dtype": "bfloat16",
	"transformers_version": "4.31.0",
	"tune_mm_mlp_adapter": false,
	"use_cache": true,
	"use_mm_proj": true,
	"vocab_size": 32032
	}