Instructions to use nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2 with Transformers:

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

pipe = pipeline("text-generation", model="nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2")
model = AutoModelForCausalLM.from_pretrained("nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2")
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 nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2

SGLang

How to use nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2 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 "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2" \
    --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": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2",
		"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 "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2" \
        --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": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2 with Docker Model Runner:
```
docker model run hf.co/nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2
```

sadkins65 commited on Jun 11, 2024

Commit

ad04724

verified ·

1 Parent(s): 8422d52

Upload folder using huggingface_hub

Browse files

Files changed (6) hide show

config.json +6 -6
generation_config.json +1 -1
model.safetensors +2 -2
recipe.yaml +1 -1
special_tokens_map.json +7 -1
tokenizer_config.json +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/root/.cache/huggingface/hub/models--TinyLlama--TinyLlama-1.1B-intermediate-step-1431k-3T/snapshots/036fa4651240b9a1487f709833b9e4b96b4c1574",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -31,14 +31,14 @@
           "num_bits": 8,
           "observer": "minmax",
           "observer_kwargs": {},
-          "strategy": "tensor",
           "symmetric": true,
           "type": "int"
         }
       }
     },
     "format": "int-quantized",
-    "global_compression_ratio": 1.2391304140415598,
     "ignore": [
       "lm_head"
     ],
@@ -46,7 +46,7 @@
     "quantization_status": "frozen",
     "sparsity_config": {
       "format": "dense",
-      "global_sparsity": 7.826375935115232,
       "registry_requires_subclass": false,
       "sparsity_structure": "unstructured"
     }
@@ -66,8 +66,8 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.40.0",
   "use_cache": true,
   "vocab_size": 32000
 }

 {
+  "_name_or_path": "/root/.cache/huggingface/hub/models--TinyLlama--TinyLlama-1.1B-Chat-v1.0/snapshots/fe8a4ea1ffedaf415f4da2f062534de366a451e6",
   "architectures": [
     "LlamaForCausalLM"
   ],
           "num_bits": 8,
           "observer": "minmax",
           "observer_kwargs": {},
+          "strategy": "channel",
           "symmetric": true,
           "type": "int"
         }
       }
     },
     "format": "int-quantized",
+    "global_compression_ratio": 1.2390773684863086,
     "ignore": [
       "lm_head"
     ],
     "quantization_status": "frozen",
     "sparsity_config": {
       "format": "dense",
+      "global_sparsity": 1.1879092038191659,
       "registry_requires_subclass": false,
       "sparsity_structure": "unstructured"
     }
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.2",
   "use_cache": true,
   "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": "4.40.0"
 }

   "eos_token_id": 2,
   "max_length": 2048,
   "pad_token_id": 0,
+  "transformers_version": "4.40.2"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b77c5cda8b7af33e238158ceadff4e01d904b0ef3e66c19cb04fa6f628b35a1
-size 1231252356

 version https://git-lfs.github.com/spec/v1
+oid sha256:aa0a2b2eacbec0d3252875883400855a36e72eda3d6fc21d8d016e7961468748
+size 1232041608

recipe.yaml CHANGED Viewed

@@ -5,6 +5,6 @@ quant_stage:
       ignore: [lm_head]
       config_groups:
         group_0:
-          weights: {num_bits: 8, type: int, symmetric: true, strategy: tensor}
           input_activations: {num_bits: 8, type: int, symmetric: true, dynamic: true, strategy: token}
           targets: [Linear]

       ignore: [lm_head]
       config_groups:
         group_0:
+          weights: {num_bits: 8, type: int, symmetric: true, strategy: channel}
           input_activations: {num_bits: 8, type: int, symmetric: true, dynamic: true, strategy: token}
           targets: [Linear]

special_tokens_map.json CHANGED Viewed

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": 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,

tokenizer_config.json CHANGED Viewed

@@ -32,7 +32,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": false,
-  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "</s>",
   "padding_side": "right",
   "sp_model_kwargs": {},

   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": false,
+  "model_max_length": 2048,
   "pad_token": "</s>",
   "padding_side": "right",
   "sp_model_kwargs": {},