Instructions to use CharlesLi/llama_2_llama_2_code_math_1_full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CharlesLi/llama_2_llama_2_code_math_1_full with Transformers:

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

pipe = pipeline("text-generation", model="CharlesLi/llama_2_llama_2_code_math_1_full")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CharlesLi/llama_2_llama_2_code_math_1_full")
model = AutoModelForCausalLM.from_pretrained("CharlesLi/llama_2_llama_2_code_math_1_full", device_map="auto")
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 CharlesLi/llama_2_llama_2_code_math_1_full with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CharlesLi/llama_2_llama_2_code_math_1_full"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CharlesLi/llama_2_llama_2_code_math_1_full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CharlesLi/llama_2_llama_2_code_math_1_full

SGLang

How to use CharlesLi/llama_2_llama_2_code_math_1_full 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 "CharlesLi/llama_2_llama_2_code_math_1_full" \
    --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": "CharlesLi/llama_2_llama_2_code_math_1_full",
		"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 "CharlesLi/llama_2_llama_2_code_math_1_full" \
        --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": "CharlesLi/llama_2_llama_2_code_math_1_full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CharlesLi/llama_2_llama_2_code_math_1_full with Docker Model Runner:
```
docker model run hf.co/CharlesLi/llama_2_llama_2_code_math_1_full
```

CharlesLi commited on Jan 20, 2025

Commit

866b4cc

verified ·

1 Parent(s): b530858

Model save

Browse files

Files changed (9) hide show

README.md +0 -6
all_results.json +2 -2
config.json +1 -1
model-00001-of-00003.safetensors +1 -1
model-00002-of-00003.safetensors +1 -1
model-00003-of-00003.safetensors +1 -1
runs/Jan20_07-29-52_dgx-a100-12/events.out.tfevents.1737354615.dgx-a100-12.1090407.0 +3 -0
train_results.json +2 -2
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -3,10 +3,6 @@ library_name: transformers
 license: llama2
 base_model: meta-llama/Llama-2-7b-chat-hf
 tags:
-- alignment-handbook
-- trl
-- sft
-- generated_from_trainer
 - trl
 - sft
 - alignment-handbook
@@ -24,8 +20,6 @@ should probably proofread and complete it, then remove this comment. -->
 # llama_2_llama_2_code_math_1_full
 This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the generator dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.8354
 ## Model description

 license: llama2
 base_model: meta-llama/Llama-2-7b-chat-hf
 tags:
 - trl
 - sft
 - alignment-handbook
 # llama_2_llama_2_code_math_1_full
 This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the generator dataset.
 ## Model description

all_results.json CHANGED Viewed

@@ -6,8 +6,8 @@
     "eval_samples_per_second": 5.723,
     "eval_steps_per_second": 1.431,
     "total_flos": 575794053120.0,
-    "train_loss": 1.0956947803497314,
-    "train_runtime": 34.0419,
     "train_samples": 980,
     "train_samples_per_second": 5.258,
     "train_steps_per_second": 0.176

     "eval_samples_per_second": 5.723,
     "eval_steps_per_second": 1.431,
     "total_flos": 575794053120.0,
+    "train_loss": 1.0960698922475178,
+    "train_runtime": 34.0457,
     "train_samples": 980,
     "train_samples_per_second": 5.258,
     "train_steps_per_second": 0.176

config.json CHANGED Viewed

@@ -24,6 +24,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": true,
   "vocab_size": 32000
 }

   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
+  "use_cache": false,
   "vocab_size": 32000
 }

model-00001-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:668b741f618b824309ca2979b545587be37bb45370e4a19da6d0d30d141db4e3
 size 4938985352

 version https://git-lfs.github.com/spec/v1
+oid sha256:819e163277818f837be67b0ca5371f67f9bdc40c72cbbef488f5f1587ac10438
 size 4938985352

model-00002-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fe54da6c852dc98f43958707f3bffe27ff31791bad102a4433b02c577c35107
 size 4947390880

 version https://git-lfs.github.com/spec/v1
+oid sha256:cbd9eb9b978034b2c156bd0c0e7f1358c875906789ae33b6ac99655aa3d4bc10
 size 4947390880

model-00003-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe270ea436a36ce500feaca503a60f3654ad5c09f5687d80205db9bbcd34fbc1
 size 3590488816

 version https://git-lfs.github.com/spec/v1
+oid sha256:b9d05e0b592d83ab2e12e42ff5cdfd298aec89600228285aadd93b9f807feb33
 size 3590488816

runs/Jan20_07-29-52_dgx-a100-12/events.out.tfevents.1737354615.dgx-a100-12.1090407.0 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:751257edbb4f51b06990d4dc61eb41795e4e249caab07f034b22caa7d7a3f942
+size 6232

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 575794053120.0,
-    "train_loss": 1.0956947803497314,
-    "train_runtime": 34.0419,
     "train_samples": 980,
     "train_samples_per_second": 5.258,
     "train_steps_per_second": 0.176

 {
     "epoch": 1.0,
     "total_flos": 575794053120.0,
+    "train_loss": 1.0960698922475178,
+    "train_runtime": 34.0457,
     "train_samples": 980,
     "train_samples_per_second": 5.258,
     "train_steps_per_second": 0.176

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b09a603c768db55c439e659e341ce1c028c855d6514c6d1bb80f5b485e048008
 size 7032

 version https://git-lfs.github.com/spec/v1
+oid sha256:164efc751f2409ac9ed9b510aa917133c06dea1384c94c3842604d6ce9cbe0c1
 size 7032