Instructions to use CodingWarrior33/tryModel-mpt1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CodingWarrior33/tryModel-mpt1 with Transformers:

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

pipe = pipeline("text-generation", model="CodingWarrior33/tryModel-mpt1", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CodingWarrior33/tryModel-mpt1", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("CodingWarrior33/tryModel-mpt1", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use CodingWarrior33/tryModel-mpt1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CodingWarrior33/tryModel-mpt1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CodingWarrior33/tryModel-mpt1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CodingWarrior33/tryModel-mpt1

SGLang

How to use CodingWarrior33/tryModel-mpt1 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 "CodingWarrior33/tryModel-mpt1" \
    --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": "CodingWarrior33/tryModel-mpt1",
		"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 "CodingWarrior33/tryModel-mpt1" \
        --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": "CodingWarrior33/tryModel-mpt1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CodingWarrior33/tryModel-mpt1 with Docker Model Runner:
```
docker model run hf.co/CodingWarrior33/tryModel-mpt1
```

CodingWarrior33 commited on Dec 11, 2023

Commit

0a99a18

1 Parent(s): ebd4f35

Upload MptForCausalLM

Browse files

Files changed (3) hide show

config.json +46 -0
generation_config.json +6 -0
pytorch_model.bin +3 -0

config.json ADDED Viewed

	@@ -0,0 +1,46 @@

+{
+  "_name_or_path": "mosaicml/mpt-7b",
+  "architectures": [
+    "MptForCausalLM"
+  ],
+  "attn_config": {
+    "model_type": ""
+  },
+  "auto_map": {
+    "AutoConfig": "mosaicml/mpt-7b--configuration_mpt.MPTConfig",
+    "AutoModelForCausalLM": "mosaicml/mpt-7b--modeling_mpt.MPTForCausalLM"
+  },
+  "d_model": 4096,
+  "emb_pdrop": 0,
+  "embedding_fraction": 1.0,
+  "expansion_ratio": 4,
+  "init_config": {
+    "emb_init_std": null,
+    "emb_init_uniform_lim": null,
+    "fan_mode": "fan_in",
+    "init_div_is_residual": true,
+    "init_gain": 0,
+    "init_nonlinearity": "relu",
+    "init_std": 0.02,
+    "name": "kaiming_normal_",
+    "verbose": 0
+  },
+  "init_device": "cpu",
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "learned_pos_emb": true,
+  "logit_scale": null,
+  "max_seq_len": 2048,
+  "model_type": "mpt",
+  "n_heads": 32,
+  "n_layers": 32,
+  "no_bias": true,
+  "norm_type": "low_precision_layernorm",
+  "resid_pdrop": 0,
+  "tokenizer_name": "EleutherAI/gpt-neox-20b",
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.1",
+  "use_cache": false,
+  "verbose": 0,
+  "vocab_size": 50432
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "eos_token_id": 0,
+  "transformers_version": "4.34.1",
+  "use_cache": false
+}

pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:62f6551bf22c180ff199f45ab3ac77aed8709aec0742ce0e390984e053b35d3d
+size 13298640518