Instructions to use Finisha-F-scratch/Pikyname with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Finisha-F-scratch/Pikyname with Transformers:

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

pipe = pipeline("text-generation", model="Finisha-F-scratch/Pikyname")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Finisha-F-scratch/Pikyname")
model = AutoModelForCausalLM.from_pretrained("Finisha-F-scratch/Pikyname", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Finisha-F-scratch/Pikyname with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Finisha-F-scratch/Pikyname

SGLang

How to use Finisha-F-scratch/Pikyname 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 "Finisha-F-scratch/Pikyname" \
    --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": "Finisha-F-scratch/Pikyname",
		"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 "Finisha-F-scratch/Pikyname" \
        --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": "Finisha-F-scratch/Pikyname",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Finisha-F-scratch/Pikyname with Docker Model Runner:
```
docker model run hf.co/Finisha-F-scratch/Pikyname
```

Clemylia commited on Mar 22

Commit

11bed05

verified ·

1 Parent(s): 3e45a5c

Training in progress, step 70

Browse files

Files changed (4) hide show

README.md +48 -5
config.json +1 -1
model.safetensors +2 -2
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -1,11 +1,54 @@
 ---
 library_name: transformers
 tags:
-- name
-- pseudo
-- small
-- ever
 model-index:
 - name: small-ever
   results: []
----

 ---
 library_name: transformers
 tags:
+- generated_from_trainer
 model-index:
 - name: small-ever
   results: []
+---
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+# small-ever
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+## Model description
+More information needed
+## Intended uses & limitations
+More information needed
+## Training and evaluation data
+More information needed
+## Training procedure
+### Training hyperparameters
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+### Training results
+### Framework versions
+- Transformers 5.0.0
+- Pytorch 2.10.0+cpu
+- Datasets 4.0.0
+- Tokenizers 0.22.2

config.json CHANGED Viewed

@@ -7,7 +7,7 @@
   "bos_token_id": 2,
   "dtype": "float32",
   "eos_token_id": 1,
-  "head_dim": 2,
   "hidden_act": "gelu_pytorch_tanh",
   "hidden_size": 2,
   "initializer_range": 0.02,

   "bos_token_id": 2,
   "dtype": "float32",
   "eos_token_id": 1,
+  "head_dim": 1,
   "hidden_act": "gelu_pytorch_tanh",
   "hidden_size": 2,
   "initializer_range": 0.02,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60208e07b1b4ef04557d436dacad54246c2dcaf431c07d02c368415d25528f4b
-size 1624

 version https://git-lfs.github.com/spec/v1
+oid sha256:54f00b8a1fdcfac29e1e60f6195f019c8ef3ffff1703f73d3e8202428cc679c3
+size 1592

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5903013123572beac04c00c9c94a45c9cbc5c287505a735b4e6d0e1828d6b9ab
 size 5201

 version https://git-lfs.github.com/spec/v1
+oid sha256:9c08e0357a4d36f66cb9d6565f81a05d140784e3962a131a3e62c16184d940eb
 size 5201