Text Generation
PEFT
Safetensors
Transformers
lora
promptcot
chain-of-thought
mathematical-reasoning
unsloth
Instructions to use PanzerBread/PromptCoT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
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")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("PanzerBread/PromptCoT", device_map="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 Desktop
- Docker Model Runner
How to use PanzerBread/PromptCoT with Docker Model Runner:
docker model run hf.co/PanzerBread/PromptCoT
Upload folder using huggingface_hub
Browse files- coding-0.2/p/latest/README.md +4 -8
- coding-0.2/p/latest/checkpoint-15/adapter_config.json +5 -5
- coding-0.2/p/latest/checkpoint-15/base_adapter/adapter_config.json +5 -5
- coding-0.2/p/latest/checkpoint-15/base_adapter/adapter_model.safetensors +1 -1
- coding-0.2/p/latest/checkpoint-15/optimizer.pt +1 -1
- coding-0.2/p/latest/checkpoint-15/training_args.bin +1 -1
coding-0.2/p/latest/README.md
CHANGED
|
@@ -1,19 +1,16 @@
|
|
| 1 |
---
|
| 2 |
base_model: unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit
|
| 3 |
-
library_name:
|
| 4 |
-
model_name: iter-
|
| 5 |
tags:
|
| 6 |
-
-
|
| 7 |
-
- lora
|
| 8 |
- sft
|
| 9 |
-
- transformers
|
| 10 |
- trl
|
| 11 |
- unsloth
|
| 12 |
licence: license
|
| 13 |
-
pipeline_tag: text-generation
|
| 14 |
---
|
| 15 |
|
| 16 |
-
# Model Card for iter-
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit](https://huggingface.co/unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit).
|
| 19 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
|
@@ -38,7 +35,6 @@ This model was trained with SFT.
|
|
| 38 |
|
| 39 |
### Framework versions
|
| 40 |
|
| 41 |
-
- PEFT 0.18.0
|
| 42 |
- TRL: 0.23.0
|
| 43 |
- Transformers: 4.57.1
|
| 44 |
- Pytorch: 2.9.0
|
|
|
|
| 1 |
---
|
| 2 |
base_model: unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: iter-4
|
| 5 |
tags:
|
| 6 |
+
- generated_from_trainer
|
|
|
|
| 7 |
- sft
|
|
|
|
| 8 |
- trl
|
| 9 |
- unsloth
|
| 10 |
licence: license
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
+
# Model Card for iter-4
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit](https://huggingface.co/unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit).
|
| 16 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
|
|
|
| 35 |
|
| 36 |
### Framework versions
|
| 37 |
|
|
|
|
| 38 |
- TRL: 0.23.0
|
| 39 |
- Transformers: 4.57.1
|
| 40 |
- Pytorch: 2.9.0
|
coding-0.2/p/latest/checkpoint-15/adapter_config.json
CHANGED
|
@@ -33,13 +33,13 @@
|
|
| 33 |
"rank_pattern": {},
|
| 34 |
"revision": null,
|
| 35 |
"target_modules": [
|
| 36 |
-
"
|
| 37 |
-
"gate_proj",
|
| 38 |
-
"o_proj",
|
| 39 |
"down_proj",
|
| 40 |
-
"
|
| 41 |
"k_proj",
|
| 42 |
-
"
|
|
|
|
|
|
|
| 43 |
],
|
| 44 |
"target_parameters": null,
|
| 45 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 33 |
"rank_pattern": {},
|
| 34 |
"revision": null,
|
| 35 |
"target_modules": [
|
| 36 |
+
"up_proj",
|
|
|
|
|
|
|
| 37 |
"down_proj",
|
| 38 |
+
"gate_proj",
|
| 39 |
"k_proj",
|
| 40 |
+
"q_proj",
|
| 41 |
+
"v_proj",
|
| 42 |
+
"o_proj"
|
| 43 |
],
|
| 44 |
"target_parameters": null,
|
| 45 |
"task_type": "CAUSAL_LM",
|
coding-0.2/p/latest/checkpoint-15/base_adapter/adapter_config.json
CHANGED
|
@@ -33,13 +33,13 @@
|
|
| 33 |
"rank_pattern": {},
|
| 34 |
"revision": null,
|
| 35 |
"target_modules": [
|
| 36 |
-
"
|
| 37 |
-
"gate_proj",
|
| 38 |
-
"o_proj",
|
| 39 |
"down_proj",
|
| 40 |
-
"
|
| 41 |
"k_proj",
|
| 42 |
-
"
|
|
|
|
|
|
|
| 43 |
],
|
| 44 |
"target_parameters": null,
|
| 45 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 33 |
"rank_pattern": {},
|
| 34 |
"revision": null,
|
| 35 |
"target_modules": [
|
| 36 |
+
"up_proj",
|
|
|
|
|
|
|
| 37 |
"down_proj",
|
| 38 |
+
"gate_proj",
|
| 39 |
"k_proj",
|
| 40 |
+
"q_proj",
|
| 41 |
+
"v_proj",
|
| 42 |
+
"o_proj"
|
| 43 |
],
|
| 44 |
"target_parameters": null,
|
| 45 |
"task_type": "CAUSAL_LM",
|
coding-0.2/p/latest/checkpoint-15/base_adapter/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 645975704
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e13d77666cde3be5553e4374a99bbb6da79ac806c123c5dc3f2c0728109cd1b6
|
| 3 |
size 645975704
|
coding-0.2/p/latest/checkpoint-15/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 328468869
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:554519fec21b50fdaf46aa0fe08d2db8000a8c953da52e227616003a522d61cf
|
| 3 |
size 328468869
|
coding-0.2/p/latest/checkpoint-15/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6225
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce87e7ba68f7bae04e1f54d1eaf3eec80d67754740de7a5d4280edd907f4b5db
|
| 3 |
size 6225
|