Instructions to use codegood/DistHermYam-7B-ties-bnb-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use codegood/DistHermYam-7B-ties-bnb-4bit with Transformers:

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

pipe = pipeline("text-generation", model="codegood/DistHermYam-7B-ties-bnb-4bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("codegood/DistHermYam-7B-ties-bnb-4bit")
model = AutoModelForCausalLM.from_pretrained("codegood/DistHermYam-7B-ties-bnb-4bit")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use codegood/DistHermYam-7B-ties-bnb-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "codegood/DistHermYam-7B-ties-bnb-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "codegood/DistHermYam-7B-ties-bnb-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/codegood/DistHermYam-7B-ties-bnb-4bit

SGLang

How to use codegood/DistHermYam-7B-ties-bnb-4bit 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 "codegood/DistHermYam-7B-ties-bnb-4bit" \
    --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": "codegood/DistHermYam-7B-ties-bnb-4bit",
		"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 "codegood/DistHermYam-7B-ties-bnb-4bit" \
        --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": "codegood/DistHermYam-7B-ties-bnb-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use codegood/DistHermYam-7B-ties-bnb-4bit 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 codegood/DistHermYam-7B-ties-bnb-4bit 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 codegood/DistHermYam-7B-ties-bnb-4bit to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for codegood/DistHermYam-7B-ties-bnb-4bit to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="codegood/DistHermYam-7B-ties-bnb-4bit",
    max_seq_length=2048,
)

Docker Model Runner
How to use codegood/DistHermYam-7B-ties-bnb-4bit with Docker Model Runner:
```
docker model run hf.co/codegood/DistHermYam-7B-ties-bnb-4bit
```

codegood commited on Apr 2, 2024

Commit

6df6cb8

verified ·

1 Parent(s): b18d01d

Trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (3) hide show

config.json +4 -4
generation_config.json +1 -1
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "codegood/DistHermYam-7B-ties-bnb-4bit",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -15,7 +15,7 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
-  "pretraining_tp": 1,
   "quantization_config": {
     "bnb_4bit_compute_dtype": "float16",
     "bnb_4bit_quant_type": "nf4",
@@ -33,8 +33,8 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.39.1",
   "unsloth_version": "2024.3",
-  "use_cache": false,
   "vocab_size": 32000
 }

 {
+  "_name_or_path": "codegood/DistHermYam-7B-ties",
   "architectures": [
     "MistralForCausalLM"
   ],
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
+  "pad_token_id": 2,
   "quantization_config": {
     "bnb_4bit_compute_dtype": "float16",
     "bnb_4bit_quant_type": "nf4",
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
+  "transformers_version": "4.39.3",
   "unsloth_version": "2024.3",
+  "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json CHANGED Viewed

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.39.1"
 }

   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "transformers_version": "4.39.3"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8b6316e4a0406f91b3cc0e4a0b642de0eddbce74696ce110e97d3ef30aebb89
-size 4125687614

 version https://git-lfs.github.com/spec/v1
+oid sha256:b1a2e85d1f1ca182ad051e6daa7a6c74d116385c2a34a8ea526e7fb38c1da4fc
+size 4125687616