Instructions to use Promptengineering/tinyllama-colorist-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Promptengineering/tinyllama-colorist-v0 with Transformers:

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

pipe = pipeline("text-generation", model="Promptengineering/tinyllama-colorist-v0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Promptengineering/tinyllama-colorist-v0")
model = AutoModelForCausalLM.from_pretrained("Promptengineering/tinyllama-colorist-v0")
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]:]))

Inference
Local Apps Settings

vLLM

How to use Promptengineering/tinyllama-colorist-v0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Promptengineering/tinyllama-colorist-v0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Promptengineering/tinyllama-colorist-v0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Promptengineering/tinyllama-colorist-v0

SGLang

How to use Promptengineering/tinyllama-colorist-v0 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 "Promptengineering/tinyllama-colorist-v0" \
    --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": "Promptengineering/tinyllama-colorist-v0",
		"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 "Promptengineering/tinyllama-colorist-v0" \
        --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": "Promptengineering/tinyllama-colorist-v0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Promptengineering/tinyllama-colorist-v0 with Docker Model Runner:
```
docker model run hf.co/Promptengineering/tinyllama-colorist-v0
```

Promptengineering commited on Jul 17, 2024

Commit

349ba2e

verified ·

1 Parent(s): 3fa892d

Upload LlamaForCausalLM

Browse files

Files changed (4) hide show

README.md +3 -1
config.json +19 -4
generation_config.json +1 -1
model.safetensors +2 -2

README.md CHANGED Viewed

@@ -1,6 +1,8 @@
 ---
 library_name: transformers
-tags: []
 ---
 # Model Card for Model ID

 ---
 library_name: transformers
+tags:
+- trl
+- sft
 ---
 # Model Card for Model ID

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -18,12 +18,27 @@
   "num_hidden_layers": 22,
   "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": "float16",
-  "transformers_version": "4.42.3",
-  "use_cache": true,
   "vocab_size": 32000
 }

 {
+  "_name_or_path": "Codex07/RD05_1",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "num_hidden_layers": 22,
   "num_key_value_heads": 4,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "use_cache": false,
   "vocab_size": 32000
 }

generation_config.json CHANGED Viewed

@@ -3,5 +3,5 @@
   "eos_token_id": 2,
   "max_length": 2048,
   "pad_token_id": 0,
-  "transformers_version": "4.42.3"
 }

   "eos_token_id": 2,
   "max_length": 2048,
   "pad_token_id": 0,
+  "transformers_version": "4.42.4"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29a949c3e5aaaf67446cbcf555f5b0f4635ba8c81e7730e0a277f60541b13059
-size 2200119664

 version https://git-lfs.github.com/spec/v1
+oid sha256:df7e02c1c26ef92e5e55498bed9fc785cef750c64432344add2d624401866332
+size 1029304351