Text Generation
Transformers
TensorBoard
Safetensors
English
retrain-pipelines
function-calling
LLM Agent
code
unsloth
conversational
Eval Results (legacy)
Instructions to use retrain-pipelines/function_caller_lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use retrain-pipelines/function_caller_lora with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="retrain-pipelines/function_caller_lora") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("retrain-pipelines/function_caller_lora", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use retrain-pipelines/function_caller_lora with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "retrain-pipelines/function_caller_lora" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "retrain-pipelines/function_caller_lora", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/retrain-pipelines/function_caller_lora
- SGLang
How to use retrain-pipelines/function_caller_lora 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 "retrain-pipelines/function_caller_lora" \ --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": "retrain-pipelines/function_caller_lora", "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 "retrain-pipelines/function_caller_lora" \ --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": "retrain-pipelines/function_caller_lora", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Studio
How to use retrain-pipelines/function_caller_lora with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for retrain-pipelines/function_caller_lora to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for retrain-pipelines/function_caller_lora to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for retrain-pipelines/function_caller_lora to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="retrain-pipelines/function_caller_lora", max_seq_length=2048, ) - Docker Model Runner
How to use retrain-pipelines/function_caller_lora with Docker Model Runner:
docker model run hf.co/retrain-pipelines/function_caller_lora
v0.24 - 2025-04-05 01:49:20 UTC - retrain-pipelines v0.1.1 - Upload model and tokenizer with README.
Browse files- README.md +16 -16
- adapter_config.json +7 -7
- adapter_model.safetensors +1 -1
- runs/cpt/{events.out.tfevents.1743611017.f3a8d62f839d.4543.0 → events.out.tfevents.1743790171.36a9ecb31cfe.5422.0} +1 -1
- runs/sft/{events.out.tfevents.1743612468.f3a8d62f839d.12023.0 → events.out.tfevents.1743791576.36a9ecb31cfe.11789.0} +1 -1
README.md
CHANGED
|
@@ -3,9 +3,9 @@
|
|
| 3 |
# @see https://huggingface.co/docs/huggingface_hub/guides/model-cards#update-metadata
|
| 4 |
# @see https://huggingface.co/docs/hub/model-cards#model-card-metadata
|
| 5 |
|
| 6 |
-
version: '0.
|
| 7 |
|
| 8 |
-
timestamp: '
|
| 9 |
|
| 10 |
model_name: retrain-pipelines Function Caller
|
| 11 |
|
|
@@ -49,7 +49,7 @@ widget:
|
|
| 49 |
output:
|
| 50 |
text: '[{"name": "is_perfect_square", "arguments": {"num": 49}}]'
|
| 51 |
|
| 52 |
-
mf_run_id: '
|
| 53 |
|
| 54 |
# @see https://huggingface.co/docs/huggingface_hub/guides/model-cards#include-evaluation-results
|
| 55 |
# @see https://huggingface.co/docs/huggingface_hub/main/en/package_reference/cards#huggingface_hub.EvalResult
|
|
@@ -63,16 +63,16 @@ model-index:
|
|
| 63 |
name: retrain-pipelines Function Calling
|
| 64 |
type: retrain-pipelines/func_calls_ds
|
| 65 |
split: validation
|
| 66 |
-
revision:
|
| 67 |
metrics:
|
| 68 |
- type: precision
|
| 69 |
-
value: 0.
|
| 70 |
- type: recall
|
| 71 |
-
value: 0.
|
| 72 |
- type: f1
|
| 73 |
-
value: 0.
|
| 74 |
- type: jaccard
|
| 75 |
-
value: 0.
|
| 76 |
|
| 77 |
---
|
| 78 |
|
|
@@ -96,19 +96,19 @@ model-index:
|
|
| 96 |
>
|
| 97 |
<b>retrain-pipelines Function Caller</b>
|
| 98 |
</div>
|
| 99 |
-
<code>version 0.
|
| 100 |
(retraining
|
| 101 |
<a target="_blank"
|
| 102 |
-
href="https://huggingface.co/retrain-pipelines/function_caller_lora/tree/retrain-pipelines_source-code/v0.
|
| 103 |
<a target="_blank"
|
| 104 |
-
href="https://huggingface.co/spaces/retrain-pipelines/online_pipeline_card_renderer/?model_repo_id=retrain-pipelines/function_caller_lora&version_id=v0.
|
| 105 |
</div>
|
| 106 |
|
| 107 |
Training dataset :
|
| 108 |
-
- <code>retrain-pipelines/func_calls_ds v0.
|
| 109 |
-
(<a href="https://huggingface.co/datasets/retrain-pipelines/func_calls_ds/blob/
|
| 110 |
-
target="_blank">
|
| 111 |
-
2025-04-
|
| 112 |
<br />
|
| 113 |
<img alt="" src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fhuggingface.co%2Fapi%2Fdatasets%2Fretrain-pipelines/func_calls_ds&query=%24.downloads&logo=huggingface&label=downloads" class="inline-block" /> <img alt="" src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fhuggingface.co%2Fapi%2Fdatasets%2Fretrain-pipelines/func_calls_ds&query=%24.likes&logo=huggingface&label=likes" class="inline-block" />
|
| 114 |
|
|
@@ -174,7 +174,7 @@ generate_tool_calls_list("Is 49 a perfect square ?")
|
|
| 174 |
href="https://github.com/aurelienmorgan/retrain-pipelines">retrain-pipelines
|
| 175 |
0.1.1</a></code> -
|
| 176 |
<code>Run by <a target="_blank" href="https://huggingface.co/Aurelien-Morgan-Bot">Aurelien-Morgan-Bot</a></code> -
|
| 177 |
-
<em><b>UnslothFuncCallFlow</b></em> - mf_run_id : <code>
|
| 178 |
</div>
|
| 179 |
</div>
|
| 180 |
|
|
|
|
| 3 |
# @see https://huggingface.co/docs/huggingface_hub/guides/model-cards#update-metadata
|
| 4 |
# @see https://huggingface.co/docs/hub/model-cards#model-card-metadata
|
| 5 |
|
| 6 |
+
version: '0.24'
|
| 7 |
|
| 8 |
+
timestamp: '20250405_014920180_UTC'
|
| 9 |
|
| 10 |
model_name: retrain-pipelines Function Caller
|
| 11 |
|
|
|
|
| 49 |
output:
|
| 50 |
text: '[{"name": "is_perfect_square", "arguments": {"num": 49}}]'
|
| 51 |
|
| 52 |
+
mf_run_id: '95'
|
| 53 |
|
| 54 |
# @see https://huggingface.co/docs/huggingface_hub/guides/model-cards#include-evaluation-results
|
| 55 |
# @see https://huggingface.co/docs/huggingface_hub/main/en/package_reference/cards#huggingface_hub.EvalResult
|
|
|
|
| 63 |
name: retrain-pipelines Function Calling
|
| 64 |
type: retrain-pipelines/func_calls_ds
|
| 65 |
split: validation
|
| 66 |
+
revision: acf61743e7c3e846b74162444f86e65852d2bbf6
|
| 67 |
metrics:
|
| 68 |
- type: precision
|
| 69 |
+
value: 0.7742409706115723
|
| 70 |
- type: recall
|
| 71 |
+
value: 0.7735999822616577
|
| 72 |
- type: f1
|
| 73 |
+
value: 0.7736773490905762
|
| 74 |
- type: jaccard
|
| 75 |
+
value: 0.7556698322296143
|
| 76 |
|
| 77 |
---
|
| 78 |
|
|
|
|
| 96 |
>
|
| 97 |
<b>retrain-pipelines Function Caller</b>
|
| 98 |
</div>
|
| 99 |
+
<code>version 0.24</code> - <code>2025-04-05 01:49:20 UTC</code>
|
| 100 |
(retraining
|
| 101 |
<a target="_blank"
|
| 102 |
+
href="https://huggingface.co/retrain-pipelines/function_caller_lora/tree/retrain-pipelines_source-code/v0.24_20250405_014920180_UTC">source-code</a> |
|
| 103 |
<a target="_blank"
|
| 104 |
+
href="https://huggingface.co/spaces/retrain-pipelines/online_pipeline_card_renderer/?model_repo_id=retrain-pipelines/function_caller_lora&version_id=v0.24_20250405_014920180_UTC">pipeline-card</a>)
|
| 105 |
</div>
|
| 106 |
|
| 107 |
Training dataset :
|
| 108 |
+
- <code>retrain-pipelines/func_calls_ds v0.23</code>
|
| 109 |
+
(<a href="https://huggingface.co/datasets/retrain-pipelines/func_calls_ds/blob/acf61743e7c3e846b74162444f86e65852d2bbf6/README.md"
|
| 110 |
+
target="_blank">acf6174</a> -
|
| 111 |
+
2025-04-04 18:05:46 UTC)
|
| 112 |
<br />
|
| 113 |
<img alt="" src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fhuggingface.co%2Fapi%2Fdatasets%2Fretrain-pipelines/func_calls_ds&query=%24.downloads&logo=huggingface&label=downloads" class="inline-block" /> <img alt="" src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fhuggingface.co%2Fapi%2Fdatasets%2Fretrain-pipelines/func_calls_ds&query=%24.likes&logo=huggingface&label=likes" class="inline-block" />
|
| 114 |
|
|
|
|
| 174 |
href="https://github.com/aurelienmorgan/retrain-pipelines">retrain-pipelines
|
| 175 |
0.1.1</a></code> -
|
| 176 |
<code>Run by <a target="_blank" href="https://huggingface.co/Aurelien-Morgan-Bot">Aurelien-Morgan-Bot</a></code> -
|
| 177 |
+
<em><b>UnslothFuncCallFlow</b></em> - mf_run_id : <code>95</code>
|
| 178 |
</div>
|
| 179 |
</div>
|
| 180 |
|
adapter_config.json
CHANGED
|
@@ -18,21 +18,21 @@
|
|
| 18 |
"megatron_config": null,
|
| 19 |
"megatron_core": "megatron.core",
|
| 20 |
"modules_to_save": [
|
| 21 |
-
"
|
| 22 |
-
"
|
| 23 |
],
|
| 24 |
"peft_type": "LORA",
|
| 25 |
"r": 128,
|
| 26 |
"rank_pattern": {},
|
| 27 |
"revision": null,
|
| 28 |
"target_modules": [
|
| 29 |
-
"q_proj",
|
| 30 |
-
"down_proj",
|
| 31 |
"k_proj",
|
| 32 |
-
"o_proj",
|
| 33 |
-
"up_proj",
|
| 34 |
"gate_proj",
|
| 35 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
],
|
| 37 |
"task_type": "CAUSAL_LM",
|
| 38 |
"use_dora": false,
|
|
|
|
| 18 |
"megatron_config": null,
|
| 19 |
"megatron_core": "megatron.core",
|
| 20 |
"modules_to_save": [
|
| 21 |
+
"lm_head",
|
| 22 |
+
"embed_tokens"
|
| 23 |
],
|
| 24 |
"peft_type": "LORA",
|
| 25 |
"r": 128,
|
| 26 |
"rank_pattern": {},
|
| 27 |
"revision": null,
|
| 28 |
"target_modules": [
|
|
|
|
|
|
|
| 29 |
"k_proj",
|
|
|
|
|
|
|
| 30 |
"gate_proj",
|
| 31 |
+
"o_proj",
|
| 32 |
+
"v_proj",
|
| 33 |
+
"q_proj",
|
| 34 |
+
"down_proj",
|
| 35 |
+
"up_proj"
|
| 36 |
],
|
| 37 |
"task_type": "CAUSAL_LM",
|
| 38 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2457916480
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78a778a411b2d359d1aa9afd160897718d90de722d40bb351cbe2857cac53079
|
| 3 |
size 2457916480
|
runs/cpt/{events.out.tfevents.1743611017.f3a8d62f839d.4543.0 → events.out.tfevents.1743790171.36a9ecb31cfe.5422.0}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 61059
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d13061fe05a25e6ee422a5a3f79e251e20e43a9e4338d31244ffa5eaa4720f6e
|
| 3 |
size 61059
|
runs/sft/{events.out.tfevents.1743612468.f3a8d62f839d.12023.0 → events.out.tfevents.1743791576.36a9ecb31cfe.11789.0}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1079367
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb949b084b6285d97b929650b080370bd5e86eace775ef69bd4c9771d2992776
|
| 3 |
size 1079367
|