Instructions to use terry69/feedback_p0.05_seed42_level2_raredirtybatch16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use terry69/feedback_p0.05_seed42_level2_raredirtybatch16 with Transformers:

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

pipe = pipeline("text-generation", model="terry69/feedback_p0.05_seed42_level2_raredirtybatch16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("terry69/feedback_p0.05_seed42_level2_raredirtybatch16")
model = AutoModelForCausalLM.from_pretrained("terry69/feedback_p0.05_seed42_level2_raredirtybatch16")
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_p0.05_seed42_level2_raredirtybatch16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "terry69/feedback_p0.05_seed42_level2_raredirtybatch16"
# 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_p0.05_seed42_level2_raredirtybatch16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/terry69/feedback_p0.05_seed42_level2_raredirtybatch16

SGLang

How to use terry69/feedback_p0.05_seed42_level2_raredirtybatch16 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_p0.05_seed42_level2_raredirtybatch16" \
    --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_p0.05_seed42_level2_raredirtybatch16",
		"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_p0.05_seed42_level2_raredirtybatch16" \
        --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_p0.05_seed42_level2_raredirtybatch16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use terry69/feedback_p0.05_seed42_level2_raredirtybatch16 with Docker Model Runner:
```
docker model run hf.co/terry69/feedback_p0.05_seed42_level2_raredirtybatch16
```

terry69 commited on Sep 22, 2024

Commit

1c895b4

verified ·

1 Parent(s): 861af76

Model save

Browse files

Files changed (7) hide show

README.md +2 -7
all_results.json +4 -4
config.json +1 -1
runs/Sep22_05-05-45_COE-CS-sv003/events.out.tfevents.1726981611.COE-CS-sv003.654422.0 +3 -0
train_results.json +4 -4
trainer_state.json +4 -4
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -3,15 +3,10 @@ library_name: transformers
 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_p0.05_seed42_level2_raredirtybatch16
   results: []
@@ -22,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 # feedback_p0.05_seed42_level2_raredirtybatch16
-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

 license: apache-2.0
 base_model: mistralai/Mistral-7B-Instruct-v0.2
 tags:
 - trl
 - sft
+- alignment-handbook
 - generated_from_trainer
 model-index:
 - name: feedback_p0.05_seed42_level2_raredirtybatch16
   results: []
 # feedback_p0.05_seed42_level2_raredirtybatch16
+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

all_results.json CHANGED Viewed

@@ -5,9 +5,9 @@
     "eval_samples_per_second": 3.147,
     "eval_steps_per_second": 0.944,
     "total_flos": 195037149265920.0,
-    "train_loss": 0.5025508344909291,
-    "train_runtime": 16743.285,
     "train_samples": 98952,
-    "train_samples_per_second": 1.78,
-    "train_steps_per_second": 0.111
 }

     "eval_samples_per_second": 3.147,
     "eval_steps_per_second": 0.944,
     "total_flos": 195037149265920.0,
+    "train_loss": 0.0,
+    "train_runtime": 0.0084,
     "train_samples": 98952,
+    "train_samples_per_second": 3568486.833,
+    "train_steps_per_second": 223052.876
 }

config.json CHANGED Viewed

@@ -22,6 +22,6 @@
   "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
 }

runs/Sep22_05-05-45_COE-CS-sv003/events.out.tfevents.1726981611.COE-CS-sv003.654422.0 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:bcb8cba0f3e68f5c8d82f578f9e4b396ce245c9a910d6407b49d6537c02fdad6
+size 5624

train_results.json CHANGED Viewed

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 195037149265920.0,
-    "train_loss": 0.5025508344909291,
-    "train_runtime": 16743.285,
     "train_samples": 98952,
-    "train_samples_per_second": 1.78,
-    "train_steps_per_second": 0.111
 }

 {
     "epoch": 1.0,
     "total_flos": 195037149265920.0,
+    "train_loss": 0.0,
+    "train_runtime": 0.0084,
     "train_samples": 98952,
+    "train_samples_per_second": 3568486.833,
+    "train_steps_per_second": 223052.876
 }

trainer_state.json CHANGED Viewed

@@ -2630,10 +2630,10 @@
       "epoch": 1.0,
       "step": 1863,
       "total_flos": 195037149265920.0,
-      "train_loss": 0.5025508344909291,
-      "train_runtime": 16743.285,
-      "train_samples_per_second": 1.78,
-      "train_steps_per_second": 0.111
     }
   ],
   "logging_steps": 5,

       "epoch": 1.0,
       "step": 1863,
       "total_flos": 195037149265920.0,
+      "train_loss": 0.0,
+      "train_runtime": 0.0084,
+      "train_samples_per_second": 3568486.833,
+      "train_steps_per_second": 223052.876
     }
   ],
   "logging_steps": 5,

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba20262b91d1c5bd36ec84daa40444b32b0b2ded70bfd2d7bbb532d9644364c6
 size 7032

 version https://git-lfs.github.com/spec/v1
+oid sha256:9ec15cf7f3d7674b8632ba4265172cc34db912cf47629cdd878878ad6a4fb739
 size 7032