Instructions to use PanzerBread/PromptCoT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PanzerBread/PromptCoT with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "PanzerBread/PromptCoT")

Transformers

How to use PanzerBread/PromptCoT with Transformers:

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

pipe = pipeline("text-generation", model="PanzerBread/PromptCoT")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("PanzerBread/PromptCoT", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PanzerBread/PromptCoT with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/PanzerBread/PromptCoT

SGLang

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

Unsloth Studio

How to use PanzerBread/PromptCoT with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for PanzerBread/PromptCoT to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for PanzerBread/PromptCoT to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for PanzerBread/PromptCoT to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="PanzerBread/PromptCoT",
    max_seq_length=2048,
)

Docker Model Runner
How to use PanzerBread/PromptCoT with Docker Model Runner:
```
docker model run hf.co/PanzerBread/PromptCoT
```

PanzerBread commited on Nov 22, 2025

Commit

640197a

verified ·

1 Parent(s): 115861d

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (2) hide show

adapter_config.json +11 -8
adapter_model.safetensors +2 -2

adapter_config.json CHANGED Viewed

@@ -7,7 +7,7 @@
     "parent_library": "transformers.models.qwen2.modeling_qwen2",
     "unsloth_fixed": true
   },
-  "base_model_name_or_path": "unsloth/deepseek-r1-distill-qwen-14b-unsloth-bnb-4bit",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
@@ -20,12 +20,15 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
   "lora_bias": false,
   "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
-  "modules_to_save": null,
   "peft_type": "LORA",
   "peft_version": "0.18.0",
   "qalora_group_size": 16,
@@ -33,13 +36,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "up_proj",
     "q_proj",
-    "down_proj",
-    "o_proj",
     "k_proj",
-    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

     "parent_library": "transformers.models.qwen2.modeling_qwen2",
     "unsloth_fixed": true
   },
+  "base_model_name_or_path": "unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
+  "lora_alpha": 64,
   "lora_bias": false,
   "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "lm_head",
+    "embed_tokens"
+  ],
   "peft_type": "LORA",
   "peft_version": "0.18.0",
   "qalora_group_size": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "q_proj",
+    "up_proj",
+    "v_proj",
     "k_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
   ],
   "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:d275d291fe0ca22d878c478f3e5377858b8c8bf773e904f4f5713226db78f4e5
-size 1101095848

 version https://git-lfs.github.com/spec/v1
+oid sha256:52551d2295543ded415868f8d7c12aff0d3cc111c026b1acc66dc18d2029ab29
+size 2825965440