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 Sep 11, 2023

Commit

0f3638b

1 Parent(s): 269a4f3

Model save

Browse files

Files changed (4) hide show

README.md +52 -0
adapter_model.safetensors +1 -1
events.out.tfevents.1694360236.ef7f542c87ff.1166609.0 +2 -2
events.out.tfevents.1694360236.ef7f542c87ff.1166609.1 +2 -2

README.md CHANGED Viewed

@@ -1,3 +1,55 @@
 ---
 license: llama2
 ---

 ---
 license: llama2
+base_model: togethercomputer/LLaMA-2-7B-32K
+tags:
+- generated_from_trainer
+model-index:
+- name: togetherchat-dev-7b-v2
+  results: []
 ---
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+# togetherchat-dev-7b-v2
+This model is a fine-tuned version of [togethercomputer/LLaMA-2-7B-32K](https://huggingface.co/togethercomputer/LLaMA-2-7B-32K) on an unknown dataset.
+## Model description
+More information needed
+## Intended uses & limitations
+More information needed
+## Training and evaluation data
+More information needed
+## Training procedure
+### Training hyperparameters
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 10
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 40
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+### Training results
+### Framework versions
+- Transformers 4.33.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.13.3

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6e4bd22e52def8ccccc94ff33374f3ae64db15fa712a0c31f0d43fb6dd41fd6
 size 40036040

 version https://git-lfs.github.com/spec/v1
+oid sha256:5193a596d4e5ef6d9d756afedfd1d59d1f5160bb0ede9da1b031a7d54a0ccdf1
 size 40036040

events.out.tfevents.1694360236.ef7f542c87ff.1166609.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e3ab42d2ae876a0a6f2e69a6c29ed60b27662c1bcd2465f9cb929309dacd688
-size 7325

 version https://git-lfs.github.com/spec/v1
+oid sha256:61d5bbff09d5c5be77a3ec684b97811b71fea357d0ee07aaee86fab18680e2de
+size 7679

events.out.tfevents.1694360236.ef7f542c87ff.1166609.1 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87df27190f8f576084c776f7b802bf8bd7c8a4f02aa67812b622c5d56ade6d1f
-size 7325

 version https://git-lfs.github.com/spec/v1
+oid sha256:e5fd8fcc261d625277c577be78eaa776b74068373217f5089f38fbdb9a4be904
+size 7679