Instructions to use nilq/lua-mistral-2L-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nilq/lua-mistral-2L-tiny with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="nilq/lua-mistral-2L-tiny")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("nilq/lua-mistral-2L-tiny") model = AutoModelForCausalLM.from_pretrained("nilq/lua-mistral-2L-tiny") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use nilq/lua-mistral-2L-tiny with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "nilq/lua-mistral-2L-tiny" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nilq/lua-mistral-2L-tiny", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/nilq/lua-mistral-2L-tiny
- SGLang
How to use nilq/lua-mistral-2L-tiny 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 "nilq/lua-mistral-2L-tiny" \ --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": "nilq/lua-mistral-2L-tiny", "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 "nilq/lua-mistral-2L-tiny" \ --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": "nilq/lua-mistral-2L-tiny", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use nilq/lua-mistral-2L-tiny with Docker Model Runner:
docker model run hf.co/nilq/lua-mistral-2L-tiny
End of training
Browse files- .gitattributes +1 -0
- README.md +5 -1
- all_results.json +9 -0
- eval_results.json +9 -0
- trainer_state.json +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -1,6 +1,8 @@
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
|
|
|
|
|
|
| 4 |
model-index:
|
| 5 |
- name: lua-mistral-2L-tiny
|
| 6 |
results: []
|
|
@@ -11,7 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 11 |
|
| 12 |
# lua-mistral-2L-tiny
|
| 13 |
|
| 14 |
-
This model is a fine-tuned version of [](https://huggingface.co/) on
|
|
|
|
|
|
|
| 15 |
|
| 16 |
## Model description
|
| 17 |
|
|
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
| 4 |
+
datasets:
|
| 5 |
+
- nilq/small-lua-stack
|
| 6 |
model-index:
|
| 7 |
- name: lua-mistral-2L-tiny
|
| 8 |
results: []
|
|
|
|
| 13 |
|
| 14 |
# lua-mistral-2L-tiny
|
| 15 |
|
| 16 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the nilq/small-lua-stack dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 1.6229
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 1.6229156255722046,
|
| 4 |
+
"eval_runtime": 417.4929,
|
| 5 |
+
"eval_samples": 570721,
|
| 6 |
+
"eval_samples_per_second": 1367.02,
|
| 7 |
+
"eval_steps_per_second": 170.88,
|
| 8 |
+
"perplexity": 5.067844734636701
|
| 9 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 1.6229156255722046,
|
| 4 |
+
"eval_runtime": 417.4929,
|
| 5 |
+
"eval_samples": 570721,
|
| 6 |
+
"eval_samples_per_second": 1367.02,
|
| 7 |
+
"eval_steps_per_second": 170.88,
|
| 8 |
+
"perplexity": 5.067844734636701
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd2b682da44f6d2bc16029b81e8ec93b11299f8a39dd5d351799be50480f8d57
|
| 3 |
+
size 37218130
|