Instructions to use Ba2han/experimental2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ba2han/experimental2 with Transformers:

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

pipe = pipeline("text-generation", model="Ba2han/experimental2", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ba2han/experimental2", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Ba2han/experimental2", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Ba2han/experimental2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ba2han/experimental2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ba2han/experimental2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Ba2han/experimental2

SGLang

How to use Ba2han/experimental2 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 "Ba2han/experimental2" \
    --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": "Ba2han/experimental2",
		"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 "Ba2han/experimental2" \
        --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": "Ba2han/experimental2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use Ba2han/experimental2 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 Ba2han/experimental2 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 Ba2han/experimental2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Ba2han/experimental2 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Ba2han/experimental2",
    max_seq_length=2048,
)

Docker Model Runner
How to use Ba2han/experimental2 with Docker Model Runner:
```
docker model run hf.co/Ba2han/experimental2
```

Ba2han commited on 27 days ago

Commit

0b71d48

verified ·

1 Parent(s): e79d758

Training in progress, step 390

Browse files

Files changed (4) hide show

README.md +1 -1
config.json +4 -4
model.safetensors +2 -2
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -27,7 +27,7 @@ print(output["generated_text"])
 ## Training procedure
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/batuhan409/huggingface/runs/dd1eu3b5)
 This model was trained with SFT.

 ## Training procedure
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/batuhan409/huggingface/runs/gcmu9feu)
 This model was trained with SFT.

config.json CHANGED Viewed

@@ -75,10 +75,10 @@
   "num_hidden_layers": 48,
   "num_key_value_heads": 4,
   "pad_token_id": 50034,
-  "resid_lambda_end": 1.05,
-  "resid_lambda_init": 1.15,
   "resid_lambda_init_end": 1.05,
   "resid_lambda_init_start": 1.15,
   "resid_scalar_lr_mult": 0.01,
   "resid_scalar_weight_decay": 0.05,
   "rms_norm_eps": 1e-06,
@@ -96,9 +96,9 @@
   "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 50048,
-  "x0_lambda_end": 0.0,
-  "x0_lambda_init": 0.02,
   "x0_lambda_init_end": 0.05,
   "x0_lambda_init_start": 0.2,
   "x0_scalar_weight_decay": 0.0
 }

   "num_hidden_layers": 48,
   "num_key_value_heads": 4,
   "pad_token_id": 50034,
   "resid_lambda_init_end": 1.05,
   "resid_lambda_init_start": 1.15,
+  "resid_lambda_max": 1.25,
+  "resid_lambda_min": 0.75,
   "resid_scalar_lr_mult": 0.01,
   "resid_scalar_weight_decay": 0.05,
   "rms_norm_eps": 1e-06,
   "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 50048,
   "x0_lambda_init_end": 0.05,
   "x0_lambda_init_start": 0.2,
+  "x0_mix_max": 0.3,
+  "x0_scalar_lr_mult": 0.01,
   "x0_scalar_weight_decay": 0.0
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f53d74af2b3082df05a025c64c68722ca660725afe94f4ae6de06107074aea1
-size 1151039640

 version https://git-lfs.github.com/spec/v1
+oid sha256:dd7e6a063adf275be5a5eecef05d85e520e1bffac9fb3d5baee4b2ac72ebae57
+size 1151039648

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b350586eae4abc083bd0fbabe256a8a042109d3a895c5dbd482bedadc195db10
 size 5777

 version https://git-lfs.github.com/spec/v1
+oid sha256:49fa95ecdb125dba941409b1921c0141f8cdfb3fd3d0645b173ea1d009eba909
 size 5777