Instructions to use EmbeddedLLM/Mistral-7B-Merge-14-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EmbeddedLLM/Mistral-7B-Merge-14-v0 with Transformers:

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

pipe = pipeline("text-generation", model="EmbeddedLLM/Mistral-7B-Merge-14-v0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EmbeddedLLM/Mistral-7B-Merge-14-v0")
model = AutoModelForCausalLM.from_pretrained("EmbeddedLLM/Mistral-7B-Merge-14-v0", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use EmbeddedLLM/Mistral-7B-Merge-14-v0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EmbeddedLLM/Mistral-7B-Merge-14-v0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EmbeddedLLM/Mistral-7B-Merge-14-v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/EmbeddedLLM/Mistral-7B-Merge-14-v0

SGLang

How to use EmbeddedLLM/Mistral-7B-Merge-14-v0 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 "EmbeddedLLM/Mistral-7B-Merge-14-v0" \
    --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": "EmbeddedLLM/Mistral-7B-Merge-14-v0",
		"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 "EmbeddedLLM/Mistral-7B-Merge-14-v0" \
        --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": "EmbeddedLLM/Mistral-7B-Merge-14-v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use EmbeddedLLM/Mistral-7B-Merge-14-v0 with Docker Model Runner:
```
docker model run hf.co/EmbeddedLLM/Mistral-7B-Merge-14-v0
```

thesunday commited on Dec 18, 2023

Commit

aaddbb1

1 Parent(s): 2275d8b

Update model card

Browse files

Files changed (1) hide show

README.md +95 -0

README.md CHANGED Viewed

@@ -1,3 +1,98 @@
 ---
 license: apache-2.0
 ---

 ---
 license: apache-2.0
+language:
+- en
 ---
+# Model Description
+This is an experiment to test merging 14 models using DARE TIES 🦙
+The result is a base model that performs quite well but requires some further instruction fine-tuning.
+The 14 models are as follows:
+1. [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
+2. [ehartford/dolphin-2.2.1-mistral-7b](https://huggingface.co/ehartford/dolphin-2.2.1-mistral-7b)
+3. [SciPhi/SciPhi-Mistral-7B-32k](https://huggingface.co/SciPhi/SciPhi-Mistral-7B-32k)
+4. [ehartford/samantha-1.2-mistral-7b](https://huggingface.co/ehartford/samantha-1.2-mistral-7b)
+5. [Arc53/docsgpt-7b-mistral](https://huggingface.co/Arc53/docsgpt-7b-mistral)
+6. [berkeley-nest/Starling-LM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha)
+7. [Q-bert/MetaMath-Cybertron-Starling](https://huggingface.co/Q-bert/MetaMath-Cybertron-Starling)
+8. [Open-Orca/Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca)
+9. [v1olet/v1olet_marcoroni-go-bruins-merge-7B](https://huggingface.co/v1olet/v1olet_marcoroni-go-bruins-merge-7B)
+10. [beowolx/MistralHermes-CodePro-7B-v1](https://huggingface.co/beowolx/MistralHermes-CodePro-7B-v1)
+11. [TIGER-Lab/MAmmoTH-7B-Mistral](https://huggingface.co/TIGER-Lab/MAmmoTH-7B-Mistral)
+12. [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B)
+13. [Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp](https://huggingface.co/Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp)
+14. [mlabonne/NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B)
+- base model: [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
+The yaml config file for this model is here:
+```yaml
+models:
+  - model: /media/data5/hf_models/Mistral-7B-v0.1
+    # no parameters necessary for base model
+  - model: /media/data5/hf_models/dolphin-2.2.1-mistral-7b
+    parameters:
+      weight: 0.08
+      density: 0.4
+  - model: /media/data5/hf_models/SciPhi-Mistral-7B-32k
+    parameters:
+      weight: 0.08
+      density: 0.4
+  - model: /media/data5/hf_models/samantha-1.2-mistral-7b
+    parameters:
+      weight: 0.08
+      density: 0.4
+  - model: /media/data5/hf_models/docsgpt-7b-mistral
+    parameters:
+      weight: 0.08
+      density: 0.4
+  - model: /media/data5/hf_models/Starling-LM-7B-alpha
+    parameters:
+      weight: 0.08
+      density: 0.4
+  - model: /media/data5/hf_models/MetaMath-Cybertron-Starling
+    parameters:
+      weight: 0.08
+      density: 0.4
+  - model: /media/data5/hf_models/Mistral-7B-OpenOrca
+    parameters:
+      weight: 0.08
+      density: 0.4
+  - model: /media/data5/hf_models/v1olet_marcoroni-go-bruins-merge-7B
+    parameters:
+      weight: 0.08
+      density: 0.4
+  - model: /media/data5/hf_models/MistralHermes-CodePro-7B-v1
+    parameters:
+      weight: 0.08
+      density: 0.4
+  - model: /media/data5/hf_models/MAmmoTH-7B-Mistral
+    parameters:
+      weight: 0.08
+      density: 0.4
+  - model: /media/data5/hf_models/OpenHermes-2.5-Mistral-7B
+    parameters:
+      weight: 0.08
+      density: 0.4
+  - model: /media/data5/hf_models/OpenHermes-2.5-neural-chat-v3-3-Slerp
+    parameters:
+      weight: 0.08
+      density: 0.4
+  - model: /media/data5/hf_models/NeuralHermes-2.5-Mistral-7B
+    parameters:
+      weight: 0.08
+      density: 0.4
+  - model: /media/data5/hf_models/Mistral-7B-Instruct-v0.2
+    parameters:
+      weight: 0.08
+      density: 0.5
+merge_method: dare_ties
+base_model: /media/data5/hf_models/Mistral-7B-v0.1
+parameters:
+  int8_mask: true
+dtype: bfloat16
+```