Text Generation
Transformers
PyTorch
TensorBoard
bloom
Generated from Trainer
text-generation-inference
Instructions to use mgiraud/bloom_pimo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mgiraud/bloom_pimo with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="mgiraud/bloom_pimo")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("mgiraud/bloom_pimo") model = AutoModelForCausalLM.from_pretrained("mgiraud/bloom_pimo") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use mgiraud/bloom_pimo with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "mgiraud/bloom_pimo" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mgiraud/bloom_pimo", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/mgiraud/bloom_pimo
- SGLang
How to use mgiraud/bloom_pimo 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 "mgiraud/bloom_pimo" \ --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": "mgiraud/bloom_pimo", "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 "mgiraud/bloom_pimo" \ --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": "mgiraud/bloom_pimo", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use mgiraud/bloom_pimo with Docker Model Runner:
docker model run hf.co/mgiraud/bloom_pimo
bloom-pimo
Browse files
config.json
CHANGED
|
@@ -25,7 +25,7 @@
|
|
| 25 |
"skip_bias_add_qkv": false,
|
| 26 |
"slow_but_exact": false,
|
| 27 |
"torch_dtype": "float32",
|
| 28 |
-
"transformers_version": "4.30.
|
| 29 |
"unk_token_id": 0,
|
| 30 |
"use_cache": true,
|
| 31 |
"vocab_size": 250880
|
|
|
|
| 25 |
"skip_bias_add_qkv": false,
|
| 26 |
"slow_but_exact": false,
|
| 27 |
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.30.1",
|
| 29 |
"unk_token_id": 0,
|
| 30 |
"use_cache": true,
|
| 31 |
"vocab_size": 250880
|
generation_config.json
CHANGED
|
@@ -3,5 +3,5 @@
|
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"pad_token_id": 3,
|
| 6 |
-
"transformers_version": "4.30.
|
| 7 |
}
|
|
|
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"pad_token_id": 3,
|
| 6 |
+
"transformers_version": "4.30.1"
|
| 7 |
}
|
runs/Jun12_06-42-51_1b584e55ea11/events.out.tfevents.1686552724.1b584e55ea11.585.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b81d079b4d5448e4a073e5ac2e0276a49161f18a306e8875d3e7d7dc266a2efd
|
| 3 |
+
size 4453
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3899
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:223034ae482a0d3b54bbd73928665fb87fbd125f0ad568a82e0e5070856a694b
|
| 3 |
size 3899
|