Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
unsloth
trl
sft
conversational
Instructions to use Dogge/llama-3-8B-instruct-Bluemoon-Freedom-RP-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Dogge/llama-3-8B-instruct-Bluemoon-Freedom-RP-4bit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Dogge/llama-3-8B-instruct-Bluemoon-Freedom-RP-4bit") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Dogge/llama-3-8B-instruct-Bluemoon-Freedom-RP-4bit") model = AutoModelForCausalLM.from_pretrained("Dogge/llama-3-8B-instruct-Bluemoon-Freedom-RP-4bit", device_map="auto") 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Dogge/llama-3-8B-instruct-Bluemoon-Freedom-RP-4bit with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Dogge/llama-3-8B-instruct-Bluemoon-Freedom-RP-4bit" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Dogge/llama-3-8B-instruct-Bluemoon-Freedom-RP-4bit", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Dogge/llama-3-8B-instruct-Bluemoon-Freedom-RP-4bit
- SGLang
How to use Dogge/llama-3-8B-instruct-Bluemoon-Freedom-RP-4bit 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 "Dogge/llama-3-8B-instruct-Bluemoon-Freedom-RP-4bit" \ --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": "Dogge/llama-3-8B-instruct-Bluemoon-Freedom-RP-4bit", "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 "Dogge/llama-3-8B-instruct-Bluemoon-Freedom-RP-4bit" \ --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": "Dogge/llama-3-8B-instruct-Bluemoon-Freedom-RP-4bit", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Desktop
- Docker Model Runner
How to use Dogge/llama-3-8B-instruct-Bluemoon-Freedom-RP-4bit with Docker Model Runner:
docker model run hf.co/Dogge/llama-3-8B-instruct-Bluemoon-Freedom-RP-4bit
Upload 3 files
Browse files- config.json +6 -6
- generation_config.json +1 -1
- tokenizer_config.json +1 -1
config.json
CHANGED
|
@@ -1,20 +1,20 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "unsloth/llama-3-
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_bias": false,
|
| 7 |
"attention_dropout": 0.0,
|
| 8 |
"bos_token_id": 128000,
|
| 9 |
-
"eos_token_id":
|
| 10 |
"hidden_act": "silu",
|
| 11 |
-
"hidden_size":
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
-
"intermediate_size":
|
| 14 |
"max_position_embeddings": 8192,
|
| 15 |
"model_type": "llama",
|
| 16 |
-
"num_attention_heads":
|
| 17 |
-
"num_hidden_layers":
|
| 18 |
"num_key_value_heads": 8,
|
| 19 |
"pretraining_tp": 1,
|
| 20 |
"rms_norm_eps": 1e-05,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "unsloth/llama-3-70b-Instruct-bnb-4bit",
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_bias": false,
|
| 7 |
"attention_dropout": 0.0,
|
| 8 |
"bos_token_id": 128000,
|
| 9 |
+
"eos_token_id": 128009,
|
| 10 |
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 8192,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 28672,
|
| 14 |
"max_position_embeddings": 8192,
|
| 15 |
"model_type": "llama",
|
| 16 |
+
"num_attention_heads": 64,
|
| 17 |
+
"num_hidden_layers": 80,
|
| 18 |
"num_key_value_heads": 8,
|
| 19 |
"pretraining_tp": 1,
|
| 20 |
"rms_norm_eps": 1e-05,
|
generation_config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 128000,
|
| 4 |
-
"eos_token_id":
|
| 5 |
"transformers_version": "4.40.0"
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 128000,
|
| 4 |
+
"eos_token_id": 128009,
|
| 5 |
"transformers_version": "4.40.0"
|
| 6 |
}
|
tokenizer_config.json
CHANGED
|
@@ -2052,7 +2052,7 @@
|
|
| 2052 |
"bos_token": "<|begin_of_text|>",
|
| 2053 |
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
| 2054 |
"clean_up_tokenization_spaces": true,
|
| 2055 |
-
"eos_token": "<|
|
| 2056 |
"model_input_names": [
|
| 2057 |
"input_ids",
|
| 2058 |
"attention_mask"
|
|
|
|
| 2052 |
"bos_token": "<|begin_of_text|>",
|
| 2053 |
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
| 2054 |
"clean_up_tokenization_spaces": true,
|
| 2055 |
+
"eos_token": "<|eot_id|>",
|
| 2056 |
"model_input_names": [
|
| 2057 |
"input_ids",
|
| 2058 |
"attention_mask"
|