Instructions to use Plaban81/codegen-int4-GPTQ-python-code with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Plaban81/codegen-int4-GPTQ-python-code with Transformers:

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

pipe = pipeline("text-generation", model="Plaban81/codegen-int4-GPTQ-python-code")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Plaban81/codegen-int4-GPTQ-python-code")
model = AutoModelForCausalLM.from_pretrained("Plaban81/codegen-int4-GPTQ-python-code")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Plaban81/codegen-int4-GPTQ-python-code with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Plaban81/codegen-int4-GPTQ-python-code"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Plaban81/codegen-int4-GPTQ-python-code",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Plaban81/codegen-int4-GPTQ-python-code

SGLang

How to use Plaban81/codegen-int4-GPTQ-python-code 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 "Plaban81/codegen-int4-GPTQ-python-code" \
    --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": "Plaban81/codegen-int4-GPTQ-python-code",
		"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 "Plaban81/codegen-int4-GPTQ-python-code" \
        --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": "Plaban81/codegen-int4-GPTQ-python-code",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Plaban81/codegen-int4-GPTQ-python-code with Docker Model Runner:
```
docker model run hf.co/Plaban81/codegen-int4-GPTQ-python-code
```

Plaban81 commited on Oct 26, 2023

Commit

edc03c8

1 Parent(s): 37411f5

Upload LlamaForCausalLM

Browse files

Files changed (3) hide show

config.json +49 -0
generation_config.json +7 -0
pytorch_model.bin +3 -0

config.json ADDED Viewed

	@@ -0,0 +1,49 @@

+{
+  "_name_or_path": "edumunozsala/llama-2-7b-int4-python-code-20k",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "batch_size": 1,
+    "bits": 4,
+    "block_name_to_quantize": "model.layers",
+    "damp_percent": 0.1,
+    "dataset": "c4",
+    "desc_act": false,
+    "disable_exllama": false,
+    "group_size": 128,
+    "max_input_length": null,
+    "model_seqlen": 4096,
+    "module_name_preceding_first_block": [
+      "model.embed_tokens"
+    ],
+    "pad_token_id": null,
+    "quant_method": "gptq",
+    "sym": true,
+    "tokenizer": null,
+    "true_sequential": true,
+    "use_cuda_fp16": true
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.34.1"
+}

pytorch_model.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a2005b86b4a899ccd54d4a5f651294f2c3e3372eacc7854a5ca62aff842234e1
+size 3896979412