Instructions to use hinny-coder/quant-hinny-coder-6.7b-java with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hinny-coder/quant-hinny-coder-6.7b-java with Transformers:

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

pipe = pipeline("text-generation", model="hinny-coder/quant-hinny-coder-6.7b-java")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hinny-coder/quant-hinny-coder-6.7b-java")
model = AutoModelForCausalLM.from_pretrained("hinny-coder/quant-hinny-coder-6.7b-java")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hinny-coder/quant-hinny-coder-6.7b-java with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hinny-coder/quant-hinny-coder-6.7b-java"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hinny-coder/quant-hinny-coder-6.7b-java",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/hinny-coder/quant-hinny-coder-6.7b-java

SGLang

How to use hinny-coder/quant-hinny-coder-6.7b-java 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 "hinny-coder/quant-hinny-coder-6.7b-java" \
    --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": "hinny-coder/quant-hinny-coder-6.7b-java",
		"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 "hinny-coder/quant-hinny-coder-6.7b-java" \
        --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": "hinny-coder/quant-hinny-coder-6.7b-java",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hinny-coder/quant-hinny-coder-6.7b-java with Docker Model Runner:
```
docker model run hf.co/hinny-coder/quant-hinny-coder-6.7b-java
```

zhaospei commited on Apr 7, 2024

Commit

4be4e53

verified ·

1 Parent(s): 9c69fb4

Update config.json

Browse files

Files changed (1) hide show

config.json +12 -10

config.json CHANGED Viewed

@@ -18,16 +18,18 @@
   "num_key_value_heads": 32,
   "pretraining_tp": 1,
   "quantization_config": {
-    "backend": "llm-awq",
-    "bits": 4,
-    "do_fuse": false,
-    "fuse_max_seq_len": null,
-    "group_size": 128,
-    "modules_to_fuse": null,
-    "modules_to_not_convert": null,
-    "quant_method": "awq",
-    "version": "gemm",
-    "zero_point": true
   },
   "rms_norm_eps": 1e-06,
   "rope_scaling": {

   "num_key_value_heads": 32,
   "pretraining_tp": 1,
   "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
   },
   "rms_norm_eps": 1e-06,
   "rope_scaling": {