Instructions to use Jolly-Q/Reflection-Llama-3.1-70B_BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jolly-Q/Reflection-Llama-3.1-70B_BF16 with Transformers:

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

pipe = pipeline("text-generation", model="Jolly-Q/Reflection-Llama-3.1-70B_BF16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Jolly-Q/Reflection-Llama-3.1-70B_BF16")
model = AutoModelForCausalLM.from_pretrained("Jolly-Q/Reflection-Llama-3.1-70B_BF16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Jolly-Q/Reflection-Llama-3.1-70B_BF16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jolly-Q/Reflection-Llama-3.1-70B_BF16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jolly-Q/Reflection-Llama-3.1-70B_BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Jolly-Q/Reflection-Llama-3.1-70B_BF16

SGLang

How to use Jolly-Q/Reflection-Llama-3.1-70B_BF16 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 "Jolly-Q/Reflection-Llama-3.1-70B_BF16" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jolly-Q/Reflection-Llama-3.1-70B_BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Jolly-Q/Reflection-Llama-3.1-70B_BF16" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jolly-Q/Reflection-Llama-3.1-70B_BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Jolly-Q/Reflection-Llama-3.1-70B_BF16 with Docker Model Runner:
```
docker model run hf.co/Jolly-Q/Reflection-Llama-3.1-70B_BF16
```

schonsense commited on Feb 10

Commit

34eaea8

verified ·

1 Parent(s): 0381a5f

Update README.md

Browse files

Files changed (1) hide show

README.md +56 -54

README.md CHANGED Viewed

@@ -1,54 +1,56 @@
----
-base_model:
-- mattshumer/Reflection-Llama-3.1-70B
-library_name: transformers
-tags:
-- mergekit
-- merge
----
-# reflection_bf16
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
-## Merge Details
-### Merge Method
-This model was merged using the Passthrough merge method using [mattshumer/Reflection-Llama-3.1-70B](https://huggingface.co/mattshumer/Reflection-Llama-3.1-70B) as a base.
-### Models Merged
-The following models were included in the merge:
-### Configuration
-The following YAML configuration was used to produce this model:
-```yaml
-models:
-  - model: mattshumer/Reflection-Llama-3.1-70B
-merge_method: passthrough
-base_model: mattshumer/Reflection-Llama-3.1-70B
-parameters:
-  normalize: false
-  int8_mask: true
-  rescale: false
-dtype: float32
-out_dtype: bfloat16
-chat_template: llama3
-tokenizer:
-  source: union
-  pad_to_multiple_of: 8
-```

+---
+base_model:
+- mattshumer/Reflection-Llama-3.1-70B
+library_name: transformers
+tags:
+- mergekit
+- merge
+---
+# reflection_bf16
+Conversion from FP32 to BF16
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+## Merge Details
+### Merge Method
+This model was merged using the Passthrough merge method using [mattshumer/Reflection-Llama-3.1-70B](https://huggingface.co/mattshumer/Reflection-Llama-3.1-70B) as a base.
+### Models Merged
+The following models were included in the merge:
+### Configuration
+The following YAML configuration was used to produce this model:
+```yaml
+models:
+  - model: mattshumer/Reflection-Llama-3.1-70B
+merge_method: passthrough
+base_model: mattshumer/Reflection-Llama-3.1-70B
+parameters:
+  normalize: false
+  int8_mask: true
+  rescale: false
+dtype: float32
+out_dtype: bfloat16
+chat_template: llama3
+tokenizer:
+  source: union
+  pad_to_multiple_of: 8
+```