Instructions to use almanach/manta-lm-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use almanach/manta-lm-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="almanach/manta-lm-base", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("almanach/manta-lm-base", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use almanach/manta-lm-base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "almanach/manta-lm-base" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "almanach/manta-lm-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/almanach/manta-lm-base
- SGLang
How to use almanach/manta-lm-base 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 "almanach/manta-lm-base" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "almanach/manta-lm-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "almanach/manta-lm-base" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "almanach/manta-lm-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use almanach/manta-lm-base with Docker Model Runner:
docker model run hf.co/almanach/manta-lm-base
bs256 version
#1
by nthngdy - opened
- config.json +2 -7
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -2,13 +2,8 @@
|
|
| 2 |
"architectures": [
|
| 3 |
"MantaForConditionalGeneration"
|
| 4 |
],
|
| 5 |
-
"auto_map": {
|
| 6 |
-
"AutoConfig": "configuration_manta.MantaConfig",
|
| 7 |
-
"AutoModel": "modeling_manta.MantaModel",
|
| 8 |
-
"AutoModelForSeq2SeqLM": "modeling_manta.MantaForConditionalGeneration"
|
| 9 |
-
},
|
| 10 |
"byte_embedding_dim": 128,
|
| 11 |
-
"d_ff":
|
| 12 |
"d_kv": 64,
|
| 13 |
"d_model": 768,
|
| 14 |
"dense_act_fn": "gelu_new",
|
|
@@ -22,7 +17,7 @@
|
|
| 22 |
"is_encoder_decoder": true,
|
| 23 |
"is_gated_act": true,
|
| 24 |
"layer_norm_epsilon": 1e-06,
|
| 25 |
-
"max_length_encoder_decoder":
|
| 26 |
"max_length_inputs": 2048,
|
| 27 |
"model_type": "manta",
|
| 28 |
"num_decoder_layers": 12,
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"MantaForConditionalGeneration"
|
| 4 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"byte_embedding_dim": 128,
|
| 6 |
+
"d_ff": 3072,
|
| 7 |
"d_kv": 64,
|
| 8 |
"d_model": 768,
|
| 9 |
"dense_act_fn": "gelu_new",
|
|
|
|
| 17 |
"is_encoder_decoder": true,
|
| 18 |
"is_gated_act": true,
|
| 19 |
"layer_norm_epsilon": 1e-06,
|
| 20 |
+
"max_length_encoder_decoder": 256,
|
| 21 |
"max_length_inputs": 2048,
|
| 22 |
"model_type": "manta",
|
| 23 |
"num_decoder_layers": 12,
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c93fe5198c403ace584c8fc1b56770b7497d35deaf8eb82e2ac71d80fcf15219
|
| 3 |
+
size 1024404765
|