Instructions to use terry69/feedback_p0.1_seed42_level2_syntaxmixbatch16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use terry69/feedback_p0.1_seed42_level2_syntaxmixbatch16 with Transformers:

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

pipe = pipeline("text-generation", model="terry69/feedback_p0.1_seed42_level2_syntaxmixbatch16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("terry69/feedback_p0.1_seed42_level2_syntaxmixbatch16")
model = AutoModelForCausalLM.from_pretrained("terry69/feedback_p0.1_seed42_level2_syntaxmixbatch16")
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 terry69/feedback_p0.1_seed42_level2_syntaxmixbatch16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "terry69/feedback_p0.1_seed42_level2_syntaxmixbatch16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "terry69/feedback_p0.1_seed42_level2_syntaxmixbatch16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/terry69/feedback_p0.1_seed42_level2_syntaxmixbatch16

SGLang

How to use terry69/feedback_p0.1_seed42_level2_syntaxmixbatch16 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 "terry69/feedback_p0.1_seed42_level2_syntaxmixbatch16" \
    --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": "terry69/feedback_p0.1_seed42_level2_syntaxmixbatch16",
		"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 "terry69/feedback_p0.1_seed42_level2_syntaxmixbatch16" \
        --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": "terry69/feedback_p0.1_seed42_level2_syntaxmixbatch16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use terry69/feedback_p0.1_seed42_level2_syntaxmixbatch16 with Docker Model Runner:
```
docker model run hf.co/terry69/feedback_p0.1_seed42_level2_syntaxmixbatch16
```

terry69 commited on Sep 17, 2024

Commit

dc035c3

verified ·

1 Parent(s): ba537a8

End of training

Browse files

Files changed (5) hide show

README.md +7 -1
all_results.json +4 -0
config.json +1 -1
eval_results.json +3 -4
runs/Sep17_05-11-37_COE-CS-sv003/events.out.tfevents.1726567067.COE-CS-sv003.3171136.1 +3 -0

README.md CHANGED Viewed

@@ -3,9 +3,15 @@ library_name: transformers
 license: apache-2.0
 base_model: mistralai/Mistral-7B-Instruct-v0.2
 tags:
 - trl
 - sft
 - generated_from_trainer
 model-index:
 - name: feedback_p0.1_seed42_level2_syntaxmixbatch16
   results: []
@@ -16,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 # feedback_p0.1_seed42_level2_syntaxmixbatch16
-This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset.
 ## Model description

 license: apache-2.0
 base_model: mistralai/Mistral-7B-Instruct-v0.2
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- preference-data
 model-index:
 - name: feedback_p0.1_seed42_level2_syntaxmixbatch16
   results: []
 # feedback_p0.1_seed42_level2_syntaxmixbatch16
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the preference-data dataset.
 ## Model description

all_results.json CHANGED Viewed

@@ -1,5 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 194513700126720.0,
     "train_loss": 0.5105859521772428,
     "train_runtime": 16588.6757,

 {
     "epoch": 1.0,
+    "eval_runtime": 3.1544,
+    "eval_samples": 10,
+    "eval_samples_per_second": 3.17,
+    "eval_steps_per_second": 0.951,
     "total_flos": 194513700126720.0,
     "train_loss": 0.5105859521772428,
     "train_runtime": 16588.6757,

config.json CHANGED Viewed

@@ -22,6 +22,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": false,
   "vocab_size": 32000
 }

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

eval_results.json CHANGED Viewed

@@ -1,8 +1,7 @@
 {
     "epoch": 1.0,
-    "eval_loss": 0.3188657760620117,
-    "eval_runtime": 1.3214,
     "eval_samples": 10,
-    "eval_samples_per_second": 1.514,
-    "eval_steps_per_second": 0.757
 }

 {
     "epoch": 1.0,
+    "eval_runtime": 3.1544,
     "eval_samples": 10,
+    "eval_samples_per_second": 3.17,
+    "eval_steps_per_second": 0.951
 }

runs/Sep17_05-11-37_COE-CS-sv003/events.out.tfevents.1726567067.COE-CS-sv003.3171136.1 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:6b4577cb17050d958cc2e45de555c829ae1908fe8a0c929890d08f8f9d675731
+size 311