Instructions to use Jcfunk/Ternary-Bonsai-8B-Code-SFT-checkpoints with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jcfunk/Ternary-Bonsai-8B-Code-SFT-checkpoints with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Jcfunk/Ternary-Bonsai-8B-unpacked")
model = PeftModel.from_pretrained(base_model, "Jcfunk/Ternary-Bonsai-8B-Code-SFT-checkpoints")

Transformers

How to use Jcfunk/Ternary-Bonsai-8B-Code-SFT-checkpoints with Transformers:

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

pipe = pipeline("text-generation", model="Jcfunk/Ternary-Bonsai-8B-Code-SFT-checkpoints")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Jcfunk/Ternary-Bonsai-8B-Code-SFT-checkpoints", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Jcfunk/Ternary-Bonsai-8B-Code-SFT-checkpoints with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jcfunk/Ternary-Bonsai-8B-Code-SFT-checkpoints"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jcfunk/Ternary-Bonsai-8B-Code-SFT-checkpoints",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Jcfunk/Ternary-Bonsai-8B-Code-SFT-checkpoints

SGLang

How to use Jcfunk/Ternary-Bonsai-8B-Code-SFT-checkpoints 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 "Jcfunk/Ternary-Bonsai-8B-Code-SFT-checkpoints" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jcfunk/Ternary-Bonsai-8B-Code-SFT-checkpoints",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Jcfunk/Ternary-Bonsai-8B-Code-SFT-checkpoints" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jcfunk/Ternary-Bonsai-8B-Code-SFT-checkpoints",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use Jcfunk/Ternary-Bonsai-8B-Code-SFT-checkpoints with Docker Model Runner:
```
docker model run hf.co/Jcfunk/Ternary-Bonsai-8B-Code-SFT-checkpoints
```

Jcfunk commited on Jun 10

Commit

d44c752

verified ·

1 Parent(s): 6b5f753

Checkpoint step 400

Browse files

Files changed (2) hide show

step_400/adapter_config.json +4 -4
step_400/adapter_model.safetensors +1 -1

step_400/adapter_config.json CHANGED Viewed

@@ -34,12 +34,12 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "down_proj",
-    "gate_proj",
     "q_proj",
-    "up_proj",
     "v_proj",
-    "o_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

   "revision": null,
   "target_modules": [
     "k_proj",
     "q_proj",
+    "down_proj",
     "v_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

step_400/adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1293b59b1e323fdd6e724ec65edb5c2aaea6a81d49cee182ad13ce15d004abcc
 size 349243752

 version https://git-lfs.github.com/spec/v1
+oid sha256:464daf7ada82d3e90cd2894ac55603ea6404a600674c3bf4d57c4fa35ce472ae
 size 349243752