Instructions to use flytech/togetherchat-dev-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use flytech/togetherchat-dev-7b with Transformers:

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

pipe = pipeline("text-generation", model="flytech/togetherchat-dev-7b", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("flytech/togetherchat-dev-7b", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("flytech/togetherchat-dev-7b", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use flytech/togetherchat-dev-7b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/flytech/togetherchat-dev-7b

SGLang

How to use flytech/togetherchat-dev-7b 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 "flytech/togetherchat-dev-7b" \
    --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": "flytech/togetherchat-dev-7b",
		"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 "flytech/togetherchat-dev-7b" \
        --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": "flytech/togetherchat-dev-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use flytech/togetherchat-dev-7b with Docker Model Runner:
```
docker model run hf.co/flytech/togetherchat-dev-7b
```

togetherchat-dev-7b / last-checkpoint /trainer_state.json

flytech

Training in progress, step 240, checkpoint

cabc880 almost 3 years ago

Raw

History Blame

1.49 kB

	{
	"best_metric": null,
	"best_model_checkpoint": null,
	"epoch": 0.7111111111111111,
	"eval_steps": 60,
	"global_step": 240,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"epoch": 0.18,
	"learning_rate": 0.0002,
	"loss": 1.293,
	"step": 60
	},
	{
	"epoch": 0.18,
	"eval_runtime": 313.4076,
	"eval_samples_per_second": 1.914,
	"eval_steps_per_second": 0.239,
	"step": 60
	},
	{
	"epoch": 0.36,
	"learning_rate": 0.0002,
	"loss": 0.6736,
	"step": 120
	},
	{
	"epoch": 0.36,
	"eval_runtime": 313.3616,
	"eval_samples_per_second": 1.915,
	"eval_steps_per_second": 0.239,
	"step": 120
	},
	{
	"epoch": 0.53,
	"learning_rate": 0.0002,
	"loss": 0.6332,
	"step": 180
	},
	{
	"epoch": 0.53,
	"eval_runtime": 313.7062,
	"eval_samples_per_second": 1.913,
	"eval_steps_per_second": 0.239,
	"step": 180
	},
	{
	"epoch": 0.71,
	"learning_rate": 0.0002,
	"loss": 0.6116,
	"step": 240
	},
	{
	"epoch": 0.71,
	"eval_runtime": 313.0801,
	"eval_samples_per_second": 1.916,
	"eval_steps_per_second": 0.24,
	"step": 240
	}
	],
	"logging_steps": 60,
	"max_steps": 1011,
	"num_train_epochs": 3,
	"save_steps": 60,
	"total_flos": 3.986425972260864e+16,
	"trial_name": null,
	"trial_params": null
	}