Instructions to use voidful/llm-codec-librispeech with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use voidful/llm-codec-librispeech with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("voidful/llm-codec")
model = PeftModel.from_pretrained(base_model, "voidful/llm-codec-librispeech")

Transformers

How to use voidful/llm-codec-librispeech with Transformers:

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

pipe = pipeline("text-generation", model="voidful/llm-codec-librispeech")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("voidful/llm-codec-librispeech")
model = AutoModelForCausalLM.from_pretrained("voidful/llm-codec-librispeech")
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 voidful/llm-codec-librispeech with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/voidful/llm-codec-librispeech

SGLang

How to use voidful/llm-codec-librispeech 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 "voidful/llm-codec-librispeech" \
    --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": "voidful/llm-codec-librispeech",
		"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 "voidful/llm-codec-librispeech" \
        --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": "voidful/llm-codec-librispeech",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use voidful/llm-codec-librispeech with Docker Model Runner:
```
docker model run hf.co/voidful/llm-codec-librispeech
```

voidful commited on Jan 3

Commit

6949b21

verified ·

1 Parent(s): 9af9c46

Training in progress, epoch 2

Browse files

Files changed (3) hide show

adapter_config.json +11 -4
adapter_model.safetensors +1 -1
training_args.bin +1 -1

adapter_config.json CHANGED Viewed

@@ -1,9 +1,12 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
   "base_model_name_or_path": "voidful/llm-codec",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": false,
@@ -20,20 +23,24 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "k_proj",
     "q_proj",
-    "up_proj",
     "o_proj",
     "v_proj",
-    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,
   "use_rslora": false
 }

 {
+  "alora_invocation_tokens": null,
   "alpha_pattern": {},
+  "arrow_config": null,
   "auto_mapping": null,
   "base_model_name_or_path": "voidful/llm-codec",
   "bias": "none",
   "corda_config": null,
+  "ensure_weight_tying": false,
   "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": false,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
   "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "q_proj",
     "o_proj",
+    "k_proj",
+    "down_proj",
     "v_proj",
+    "up_proj",
+    "gate_proj"
   ],
+  "target_parameters": null,
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,
+  "use_qalora": false,
   "use_rslora": false
 }

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01f1adfb4d4f0a2f044323aa36e6c31cb24bfadfa7406d2ff26dd9deb8027ff2
 size 528550256

 version https://git-lfs.github.com/spec/v1
+oid sha256:4af9c056765e599d2a4ce35908801edf4f9ff2ba4ba9ec7d22de8aa5e9694682
 size 528550256

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09ef793003aa3f31e0fa9d57c9998371626de0241ae516edb6c9795266860010
 size 5841

 version https://git-lfs.github.com/spec/v1
+oid sha256:086a4fbc7538a577fb092ba511f7e1a4d6b3867e138da19ed05f63656337f331
 size 5841