Instructions to use g-ronimo/llama-fridman with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use g-ronimo/llama-fridman with Transformers:

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

pipe = pipeline("text-generation", model="g-ronimo/llama-fridman")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("g-ronimo/llama-fridman")
model = AutoModelForCausalLM.from_pretrained("g-ronimo/llama-fridman")
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

vLLM

How to use g-ronimo/llama-fridman with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/g-ronimo/llama-fridman

SGLang

How to use g-ronimo/llama-fridman 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 "g-ronimo/llama-fridman" \
    --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": "g-ronimo/llama-fridman",
		"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 "g-ronimo/llama-fridman" \
        --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": "g-ronimo/llama-fridman",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use g-ronimo/llama-fridman with Docker Model Runner:
```
docker model run hf.co/g-ronimo/llama-fridman
```

meta-llama/Llama-2-7b trained on ~350 episodes of the Lex Friedman podcast (Lex=Assistant), QLoRA, ChatML

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_path="g-ronimo/llama-fridman"

model = AutoModelForCausalLM.from_pretrained(
    model_path, 
    torch_dtype=torch.bfloat16,
    )
tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=True, legacy=False)    # fast tokenizer 

# sampling parameters: llama-precise
gen_config = {
    "temperature": 0.7,
    "top_p": 0.1,
    "repetition_penalty": 1.18,
    "top_k": 40,
    "do_sample": True,
    "max_new_tokens": 300,
}

messages = [
    {"role": "user", "content": "Good morning, I am Mark Zuckerberg"},
    {"role": "assistant", "content": "The founder of Meta"},
    {"role": "user", "content": "Yes exactly! And the future of AI"}
]

prompt=tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
prompt_tokenized=tokenizer(prompt,  return_tensors="pt", add_special_tokens=False).to("cuda")

output_ids = model.generate(**prompt_tokenized, **gen_config)
response=tokenizer.decode(output_ids[0])

print(response)

|im_start|>user
Good morning, I am Mark Zuckerberg<|im_end|> 
<|im_start|>assistant
The founder of Meta<|im_end|> 
<|im_start|>user
Yes exactly! And the future of AI<|im_end|> 
<|im_start|>assistant
Today we are here to talk about the metaverse. What is it? How do you see it evolving in the next decades? Let's start with some basics. What is the metaverse?<|im_end|>

Downloads last month: 8

Safetensors

Model size

7B params

Tensor type

BF16