Instructions to use krytonguard/peft-starcoder-lora-a100 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use krytonguard/peft-starcoder-lora-a100 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("bigcode/starcoderbase-1b")
model = PeftModel.from_pretrained(base_model, "krytonguard/peft-starcoder-lora-a100")

Transformers

How to use krytonguard/peft-starcoder-lora-a100 with Transformers:

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

pipe = pipeline("text-generation", model="krytonguard/peft-starcoder-lora-a100")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("krytonguard/peft-starcoder-lora-a100", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use krytonguard/peft-starcoder-lora-a100 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "krytonguard/peft-starcoder-lora-a100"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "krytonguard/peft-starcoder-lora-a100",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/krytonguard/peft-starcoder-lora-a100

SGLang

How to use krytonguard/peft-starcoder-lora-a100 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 "krytonguard/peft-starcoder-lora-a100" \
    --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": "krytonguard/peft-starcoder-lora-a100",
		"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 "krytonguard/peft-starcoder-lora-a100" \
        --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": "krytonguard/peft-starcoder-lora-a100",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use krytonguard/peft-starcoder-lora-a100 with Docker Model Runner:
```
docker model run hf.co/krytonguard/peft-starcoder-lora-a100
```

krytonguard commited on Mar 7

Commit

2a8ef5c

verified ·

1 Parent(s): 64e8fa0

Training in progress, step 100

Browse files

Files changed (3) hide show

adapter_config.json +4 -4
adapter_model.safetensors +2 -2
training_args.bin +2 -2

adapter_config.json CHANGED Viewed

@@ -3,7 +3,7 @@
   "alpha_pattern": {},
   "arrow_config": null,
   "auto_mapping": null,
-  "base_model_name_or_path": "bigcode/starcoderbase-3b",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
@@ -23,16 +23,16 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "peft_version": "0.18.0",
   "qalora_group_size": 16,
   "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_attn",
     "c_proj",
     "c_fc",
-    "c_attn"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

   "alpha_pattern": {},
   "arrow_config": null,
   "auto_mapping": null,
+  "base_model_name_or_path": "bigcode/starcoderbase-1b",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
+  "peft_version": "0.18.1",
   "qalora_group_size": 16,
   "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "c_proj",
     "c_fc",
+    "c_attn",
+    "q_attn"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8f0fa23724611f80e334a1429603527d15928dd1a9f8742919dca6dc79554f9
-size 45748400

 version https://git-lfs.github.com/spec/v1
+oid sha256:4acfeb4cc9cda09a3acc118e7f81ec7eaeffa9c5836edfa49f09d13bff373a38
+size 22241240

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78ee86147e50110f6d17c09ddb931a96a8767e71126cc66d08be84c5b877af8f
-size 5905

 version https://git-lfs.github.com/spec/v1
+oid sha256:4264536d71111fb254fb1bba3ec36537bfc6b612b8c2d34a93e2e2871df79690
+size 5201