Instructions to use DiscoResearch/mixtral-7b-8expert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DiscoResearch/mixtral-7b-8expert with Transformers:

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

pipe = pipeline("text-generation", model="DiscoResearch/mixtral-7b-8expert", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("DiscoResearch/mixtral-7b-8expert", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("DiscoResearch/mixtral-7b-8expert", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DiscoResearch/mixtral-7b-8expert with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DiscoResearch/mixtral-7b-8expert"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DiscoResearch/mixtral-7b-8expert",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DiscoResearch/mixtral-7b-8expert

SGLang

How to use DiscoResearch/mixtral-7b-8expert 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 "DiscoResearch/mixtral-7b-8expert" \
    --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": "DiscoResearch/mixtral-7b-8expert",
		"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 "DiscoResearch/mixtral-7b-8expert" \
        --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": "DiscoResearch/mixtral-7b-8expert",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DiscoResearch/mixtral-7b-8expert with Docker Model Runner:
```
docker model run hf.co/DiscoResearch/mixtral-7b-8expert
```

bjoernp commited on Dec 9, 2023

Commit

3ba003a

1 Parent(s): b694477

Update modeling_moe_mistral.py (#1)

Browse files

- Update modeling_moe_mistral.py (36895657ceb8b36d400804a084468668deee6686)

Files changed (1) hide show

modeling_moe_mistral.py +3 -4

modeling_moe_mistral.py CHANGED Viewed

@@ -196,9 +196,7 @@ class FeedForward(nn.Module):
         )
     def forward(self, x):
-        device = x.device
-        x = x.to(self.w1.weight.device)
-        return self.w2(F.silu(self.w1(x)) * self.w3(x)).to(device)
 class MoE(nn.Module):
@@ -217,8 +215,9 @@ class MoE(nn.Module):
         orig_shape = x.shape
         x = x.view(-1, x.shape[-1])
-        scores = self.gate(x).softmax(dim=-1)
         expert_weights, expert_indices = torch.topk(scores, self.num_experts_per_token, dim=-1)
         flat_expert_indices = expert_indices.view(-1)
         x = x.repeat_interleave(self.num_experts_per_token, dim=0)

         )
     def forward(self, x):
+        return self.w2(F.silu(self.w1(x)) * self.w3(x))
 class MoE(nn.Module):
         orig_shape = x.shape
         x = x.view(-1, x.shape[-1])
+        scores = self.gate(x)
         expert_weights, expert_indices = torch.topk(scores, self.num_experts_per_token, dim=-1)
+        expert_weights = expert_weights.softmax(dim=-1)
         flat_expert_indices = expert_indices.view(-1)
         x = x.repeat_interleave(self.num_experts_per_token, dim=0)