Instructions to use AlSamCur123/ElmerContinuedFine with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AlSamCur123/ElmerContinuedFine with Transformers:

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

pipe = pipeline("text-generation", model="AlSamCur123/ElmerContinuedFine")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AlSamCur123/ElmerContinuedFine")
model = AutoModelForCausalLM.from_pretrained("AlSamCur123/ElmerContinuedFine")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AlSamCur123/ElmerContinuedFine with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AlSamCur123/ElmerContinuedFine"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AlSamCur123/ElmerContinuedFine",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AlSamCur123/ElmerContinuedFine

SGLang

How to use AlSamCur123/ElmerContinuedFine 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 "AlSamCur123/ElmerContinuedFine" \
    --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": "AlSamCur123/ElmerContinuedFine",
		"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 "AlSamCur123/ElmerContinuedFine" \
        --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": "AlSamCur123/ElmerContinuedFine",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use AlSamCur123/ElmerContinuedFine 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 AlSamCur123/ElmerContinuedFine 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 AlSamCur123/ElmerContinuedFine to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AlSamCur123/ElmerContinuedFine to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="AlSamCur123/ElmerContinuedFine",
    max_seq_length=2048,
)

Docker Model Runner
How to use AlSamCur123/ElmerContinuedFine with Docker Model Runner:
```
docker model run hf.co/AlSamCur123/ElmerContinuedFine
```

AlSamCur123 commited on Dec 12, 2024

Commit

02b086b

verified ·

1 Parent(s): 596f059

Trained with Unsloth

Browse files

Files changed (11) hide show

config.json +3 -3
generation_config.json +1 -1
model-00001-of-00009.safetensors +2 -2
model-00002-of-00009.safetensors +2 -2
model-00003-of-00009.safetensors +2 -2
model-00004-of-00009.safetensors +2 -2
model-00005-of-00009.safetensors +2 -2
model-00006-of-00009.safetensors +2 -2
model-00007-of-00009.safetensors +2 -2
model-00008-of-00009.safetensors +2 -2
model-00009-of-00009.safetensors +1 -1

@@ -28,9 +28,9 @@
   },
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.46.2",
-  "unsloth_version": "2024.11.10",
   "use_cache": false,
   "vocab_size": 32000
 }

   },
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "unsloth_version": "2024.12.4",
   "use_cache": false,
   "vocab_size": 32000
 }

@@ -6,5 +6,5 @@
   "pad_token_id": 0,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.46.2"
 }

   "pad_token_id": 0,
   "temperature": 0.6,
   "top_p": 0.9,
+  "transformers_version": "4.46.3"
 }

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:408d62d5444159d488c1f5a74fd1620790f84180a5942931e05895a7fb30ee62
-size 4978265728

 version https://git-lfs.github.com/spec/v1
+oid sha256:86cf6eb172f4c8809e1e20c3588234f0f57755a66834fce47fcf0b916bbe897c
+size 4978265800

 version https://git-lfs.github.com/spec/v1
+oid sha256:864da33438cbacc0113b7db5445d45ba2eb0c848e9bde2474d5edea137f9f91d
+size 4970422232

 version https://git-lfs.github.com/spec/v1
+oid sha256:3af5b00d98de48aea9abce72879ba4e6cc22dc8c5f25f06092dda8897518e9bf
+size 4970422256

 version https://git-lfs.github.com/spec/v1
+oid sha256:3a4343e2e7e61c0bc0e32c95dea37de585afeae286e9e44c36247e8571827fea
+size 4933701504

 version https://git-lfs.github.com/spec/v1
+oid sha256:f92bfad5faa702d1c2b9ee7ff39a44e1f2f53bab86ab672db948070bc72b1b60
+size 4933722216

 version https://git-lfs.github.com/spec/v1
+oid sha256:1b39c5c0032e8c0ee133cda164b2693b34df5b4f83544677a6bef17b31b996fb
+size 4933722208

 version https://git-lfs.github.com/spec/v1
+oid sha256:d6c7bec00657003175173c18c315fe8b4fa4f2aa5d586285b41e5568f7095439
+size 4970432584

 version https://git-lfs.github.com/spec/v1
+oid sha256:46912948f2e47ef9345027837ebd1fff61bd962c0dd5d957e885199abc8b2f39
 size 327680128