Instructions to use Josephgflowers/tinyllama-730M-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Josephgflowers/tinyllama-730M-test with Transformers:

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

pipe = pipeline("text-generation", model="Josephgflowers/tinyllama-730M-test")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Josephgflowers/tinyllama-730M-test")
model = AutoModelForCausalLM.from_pretrained("Josephgflowers/tinyllama-730M-test")
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 Josephgflowers/tinyllama-730M-test with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Josephgflowers/tinyllama-730M-test"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Josephgflowers/tinyllama-730M-test",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Josephgflowers/tinyllama-730M-test

SGLang

How to use Josephgflowers/tinyllama-730M-test 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 "Josephgflowers/tinyllama-730M-test" \
    --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": "Josephgflowers/tinyllama-730M-test",
		"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 "Josephgflowers/tinyllama-730M-test" \
        --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": "Josephgflowers/tinyllama-730M-test",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Josephgflowers/tinyllama-730M-test with Docker Model Runner:
```
docker model run hf.co/Josephgflowers/tinyllama-730M-test
```

Josephgflowers commited on Feb 15, 2024

Commit

71195ef

verified ·

1 Parent(s): 9d8664a

Upload 12 files

Browse files

Files changed (12) hide show

config.json +29 -0
generation_config.json +7 -0
model.safetensors +3 -0
optimizer.pt +3 -0
rng_state.pth +3 -0
scheduler.pt +3 -0
special_tokens_map.json +30 -0
tokenizer.json +0 -0
tokenizer.model +3 -0
tokenizer_config.json +46 -0
trainer_state.json +381 -0
training_args.bin +3 -0

config.json ADDED Viewed

	@@ -0,0 +1,29 @@

+{
+  "_name_or_path": "/content/740-M-checkpoint-3108",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 14,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.0.dev0",
+  "unsloth_version": "2024.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.38.0.dev0",
+  "use_cache": false
+}

model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:86e7b4bcf4e67a101cc24fa5825024f076bf2045afd1b4517ed91592941005db
+size 2990791024

optimizer.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a4766397f416f5f6b517adf0c6b0921b74b1b39d8e23526181b51e9caa68111b
+size 2618682

rng_state.pth ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

scheduler.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:47743ce1a1f83b0fd753c7f0f81e90340a93350c8168453372bb1a775797d93e
+size 1064

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,30 @@

+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer.model ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,46 @@

+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "max_length": 2048,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json ADDED Viewed

	@@ -0,0 +1,381 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.21150219433526624,
+  "eval_steps": 500,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.9823745064861824e-05,
+      "loss": 1.064,
+      "step": 50
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.964749012972363e-05,
+      "loss": 0.9951,
+      "step": 100
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.9471235194585454e-05,
+      "loss": 1.0051,
+      "step": 150
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.929498025944726e-05,
+      "loss": 1.0086,
+      "step": 200
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.9118725324309084e-05,
+      "loss": 1.1256,
+      "step": 250
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.89424703891709e-05,
+      "loss": 1.0419,
+      "step": 300
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.8766215454032714e-05,
+      "loss": 1.0368,
+      "step": 350
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.8589960518894536e-05,
+      "loss": 0.9884,
+      "step": 400
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.8413705583756344e-05,
+      "loss": 1.01,
+      "step": 450
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.8237450648618166e-05,
+      "loss": 1.0734,
+      "step": 500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.806119571347998e-05,
+      "loss": 1.0388,
+      "step": 550
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.7884940778341796e-05,
+      "loss": 1.0576,
+      "step": 600
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.770868584320361e-05,
+      "loss": 1.0449,
+      "step": 650
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.7532430908065426e-05,
+      "loss": 1.0809,
+      "step": 700
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.735617597292725e-05,
+      "loss": 1.0888,
+      "step": 750
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.717992103778906e-05,
+      "loss": 1.031,
+      "step": 800
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.700366610265088e-05,
+      "loss": 1.0546,
+      "step": 850
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.682741116751269e-05,
+      "loss": 1.093,
+      "step": 900
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.665468133107727e-05,
+      "loss": 1.0729,
+      "step": 950
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.647842639593909e-05,
+      "loss": 1.0771,
+      "step": 1000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.6302171460800905e-05,
+      "loss": 1.1318,
+      "step": 1050
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.612591652566272e-05,
+      "loss": 1.0114,
+      "step": 1100
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.5949661590524535e-05,
+      "loss": 1.0272,
+      "step": 1150
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.577340665538635e-05,
+      "loss": 1.0503,
+      "step": 1200
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.559715172024817e-05,
+      "loss": 0.9816,
+      "step": 1250
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.542794698251551e-05,
+      "loss": 1.001,
+      "step": 1300
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.525169204737733e-05,
+      "loss": 1.1184,
+      "step": 1350
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.507543711223914e-05,
+      "loss": 1.0958,
+      "step": 1400
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.4899182177100965e-05,
+      "loss": 1.0912,
+      "step": 1450
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.472292724196277e-05,
+      "loss": 1.0226,
+      "step": 1500
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.4546672306824595e-05,
+      "loss": 1.0038,
+      "step": 1550
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.437041737168641e-05,
+      "loss": 0.9825,
+      "step": 1600
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.4194162436548225e-05,
+      "loss": 1.0476,
+      "step": 1650
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.401790750141005e-05,
+      "loss": 1.0642,
+      "step": 1700
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.3841652566271855e-05,
+      "loss": 1.0254,
+      "step": 1750
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.366539763113368e-05,
+      "loss": 1.0941,
+      "step": 1800
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.3489142695995485e-05,
+      "loss": 0.9739,
+      "step": 1850
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.331288776085731e-05,
+      "loss": 1.0468,
+      "step": 1900
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.313663282571912e-05,
+      "loss": 1.0706,
+      "step": 1950
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.296037789058094e-05,
+      "loss": 0.9796,
+      "step": 2000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.278412295544276e-05,
+      "loss": 1.0202,
+      "step": 2050
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.260786802030457e-05,
+      "loss": 1.0263,
+      "step": 2100
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.243161308516639e-05,
+      "loss": 0.9823,
+      "step": 2150
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.2255358150028204e-05,
+      "loss": 1.0187,
+      "step": 2200
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.207910321489002e-05,
+      "loss": 1.0219,
+      "step": 2250
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.1902848279751834e-05,
+      "loss": 1.0641,
+      "step": 2300
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.172659334461365e-05,
+      "loss": 0.9979,
+      "step": 2350
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.155033840947547e-05,
+      "loss": 0.9762,
+      "step": 2400
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.1374083474337286e-05,
+      "loss": 0.983,
+      "step": 2450
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.11978285391991e-05,
+      "loss": 1.0849,
+      "step": 2500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.1021573604060916e-05,
+      "loss": 1.0281,
+      "step": 2550
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.084531866892273e-05,
+      "loss": 1.0041,
+      "step": 2600
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.0669063733784546e-05,
+      "loss": 1.0055,
+      "step": 2650
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.049280879864636e-05,
+      "loss": 1.014,
+      "step": 2700
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.0316553863508176e-05,
+      "loss": 1.0347,
+      "step": 2750
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.014029892837e-05,
+      "loss": 0.9675,
+      "step": 2800
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 3.996404399323181e-05,
+      "loss": 1.0086,
+      "step": 2850
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 3.978778905809363e-05,
+      "loss": 0.9836,
+      "step": 2900
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 3.961153412295544e-05,
+      "loss": 1.0441,
+      "step": 2950
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 3.943527918781726e-05,
+      "loss": 1.0613,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 14184,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "total_flos": 1.0058830184448e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a66f85176067747802ad533b8a3c6046a84588e845ff8847619e673d9a5605ed
+size 4856