Instructions to use flytech/togetherchat-dev-7b-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use flytech/togetherchat-dev-7b-v2 with Transformers:

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

pipe = pipeline("text-generation", model="flytech/togetherchat-dev-7b-v2", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("flytech/togetherchat-dev-7b-v2", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("flytech/togetherchat-dev-7b-v2", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use flytech/togetherchat-dev-7b-v2 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-v2"
# 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-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/flytech/togetherchat-dev-7b-v2

SGLang

How to use flytech/togetherchat-dev-7b-v2 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-v2" \
    --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-v2",
		"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-v2" \
        --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-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use flytech/togetherchat-dev-7b-v2 with Docker Model Runner:
```
docker model run hf.co/flytech/togetherchat-dev-7b-v2
```

flytech commited on Oct 9, 2023

Commit

10cd9fc

1 Parent(s): 5316dfc

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -8

README.md CHANGED Viewed

@@ -20,11 +20,11 @@ This model is a fine-tuned version of [togethercomputer/LLaMA-2-7B-32K](https://
 Model can be used for text-to-code generation and for further fine-tuning,
 Colab notebook example (on free T4 GPU) soon!
-Datasets used:
-evol-codealpaca-80k - 10000 entries
-codealpaca-20k - 10000 entries
-open-platypus - 5000 entries
 ## Intended uses & limitations
@@ -35,10 +35,6 @@ you need to fine-tune it for your specific task.
 See 'Metrics'
-## Training procedure
-Soon! (leave a like / sign of life to let me know you need one)
 ### Training hyperparameters
 The following hyperparameters were used during training:

 Model can be used for text-to-code generation and for further fine-tuning,
 Colab notebook example (on free T4 GPU) soon!
+## Datasets used:
+- evol-codealpaca-80k - 10000 entries
+- codealpaca-20k - 10000 entries
+- open-platypus - 5000 entries
 ## Intended uses & limitations
 See 'Metrics'
 ### Training hyperparameters
 The following hyperparameters were used during training: