Instructions to use pkarypis/llama2-lima with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pkarypis/llama2-lima with Transformers:

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

pipe = pipeline("text-generation", model="pkarypis/llama2-lima")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pkarypis/llama2-lima")
model = AutoModelForCausalLM.from_pretrained("pkarypis/llama2-lima")
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 pkarypis/llama2-lima with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pkarypis/llama2-lima"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pkarypis/llama2-lima",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pkarypis/llama2-lima

SGLang

How to use pkarypis/llama2-lima 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 "pkarypis/llama2-lima" \
    --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": "pkarypis/llama2-lima",
		"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 "pkarypis/llama2-lima" \
        --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": "pkarypis/llama2-lima",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pkarypis/llama2-lima with Docker Model Runner:
```
docker model run hf.co/pkarypis/llama2-lima
```

pkarypis commited on Apr 26, 2024

Commit

a4c2cfd

verified ·

1 Parent(s): 9db510a

End of training

Browse files

Files changed (5) hide show

README.md +6 -2
all_results.json +5 -0
config.json +1 -1
eval_results.json +8 -0
runs/Apr26_14-38-49_aga39/events.out.tfevents.1714161024.aga39.1452190.1 +3 -0

README.md CHANGED Viewed

@@ -2,11 +2,15 @@
 license: llama2
 base_model: meta-llama/Llama-2-7b-hf
 tags:
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
 model-index:
 - name: llama2-lima
   results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 # llama2-lima
-This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the generator dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.5297

 license: llama2
 base_model: meta-llama/Llama-2-7b-hf
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
+- GAIR/lima
 model-index:
 - name: llama2-lima
   results: []
 # llama2-lima
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the GAIR/lima dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.5297

all_results.json CHANGED Viewed

@@ -1,5 +1,10 @@
 {
     "epoch": 10.0,
     "train_loss": 1.0364325324694315,
     "train_runtime": 358.0118,
     "train_samples": 1030,

 {
     "epoch": 10.0,
+    "eval_loss": 2.5297091007232666,
+    "eval_runtime": 2.0612,
+    "eval_samples": 300,
+    "eval_samples_per_second": 5.822,
+    "eval_steps_per_second": 0.485,
     "train_loss": 1.0364325324694315,
     "train_runtime": 358.0118,
     "train_samples": 1030,

config.json CHANGED Viewed

@@ -23,6 +23,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.38.2",
-  "use_cache": false,
   "vocab_size": 32000
 }

   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.38.2",
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+    "epoch": 10.0,
+    "eval_loss": 2.5297091007232666,
+    "eval_runtime": 2.0612,
+    "eval_samples": 300,
+    "eval_samples_per_second": 5.822,
+    "eval_steps_per_second": 0.485
+}

runs/Apr26_14-38-49_aga39/events.out.tfevents.1714161024.aga39.1452190.1 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e03c81f39ac13323386f8483663135a7d9c911388c47193b5c91590d5c67c805
+size 354