Instructions to use tabeehive/tabeehive-ft-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tabeehive/tabeehive-ft-2 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("TheBloke/Mistral-7B-Instruct-v0.2-GPTQ")
model = PeftModel.from_pretrained(base_model, "tabeehive/tabeehive-ft-2")

Transformers

How to use tabeehive/tabeehive-ft-2 with Transformers:

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

pipe = pipeline("text-generation", model="tabeehive/tabeehive-ft-2")
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("tabeehive/tabeehive-ft-2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tabeehive/tabeehive-ft-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tabeehive/tabeehive-ft-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tabeehive/tabeehive-ft-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tabeehive/tabeehive-ft-2

SGLang

How to use tabeehive/tabeehive-ft-2 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 "tabeehive/tabeehive-ft-2" \
    --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": "tabeehive/tabeehive-ft-2",
		"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 "tabeehive/tabeehive-ft-2" \
        --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": "tabeehive/tabeehive-ft-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tabeehive/tabeehive-ft-2 with Docker Model Runner:
```
docker model run hf.co/tabeehive/tabeehive-ft-2
```

tabeehive commited on Jun 27, 2025

Commit

0b4d016

verified ·

1 Parent(s): 7506b14

tabeehive/tabeehive-ft-4

Browse files

Files changed (3) hide show

README.md +13 -8
adapter_model.safetensors +1 -1
training_args.bin +2 -2

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2134
 ## Model description
@@ -44,24 +44,29 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
-- num_epochs: 5
 - mixed_precision_training: Native AMP
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.3419        | 1.0   | 4    | 2.0782          |
-| 1.9259        | 2.0   | 8    | 1.7029          |
-| 1.6054        | 3.0   | 12   | 1.4563          |
-| 1.3916        | 4.0   | 16   | 1.2880          |
-| 1.2566        | 5.0   | 20   | 1.2134          |
 ### Framework versions
 - PEFT 0.15.2
 - Transformers 4.52.4
-- Pytorch 2.7.1+cu126
 - Datasets 2.14.4
 - Tokenizers 0.21.1

 This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.4065
 ## Model description
 - optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| 2.3409        | 1.0   | 4    | 2.0695          |
+| 1.9045        | 2.0   | 8    | 1.6551          |
+| 1.5367        | 3.0   | 12   | 1.3351          |
+| 1.225         | 4.0   | 16   | 1.0331          |
+| 0.9373        | 5.0   | 20   | 0.7792          |
+| 0.7175        | 6.0   | 24   | 0.6143          |
+| 0.5782        | 7.0   | 28   | 0.5108          |
+| 0.4913        | 8.0   | 32   | 0.4461          |
+| 0.4395        | 9.0   | 36   | 0.4166          |
+| 0.4178        | 10.0  | 40   | 0.4065          |
 ### Framework versions
 - PEFT 0.15.2
 - Transformers 4.52.4
+- Pytorch 2.6.0+cu124
 - Datasets 2.14.4
 - Tokenizers 0.21.1

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0604d0dc209cfb23836411c6ae29f4ea41d879ff111655cdce515cd72e0b4a86
 size 8397056

 version https://git-lfs.github.com/spec/v1
+oid sha256:18ea7d02129722ddf2e35b59cf8d5b0a7fc7f1687530ed7182ef1bdd63892597
 size 8397056

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09dff82ade94585ab7b38f83aaf60588ebf48191d549572ef45679a5e3c51869
-size 5649

 version https://git-lfs.github.com/spec/v1
+oid sha256:5ad28866a34f556e9187e66e45900e2d1411da84947b16773e70266038fbe637
+size 5240