Mungert/Llama-xLAM-2-8b-fc-r-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: Mungert/Llama-xLAM-2-8b-fc-r-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-30 17:39:18 +08:00
commit a01b9a2b33
30 changed files with 569 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

77
.gitattributes vendored Normal file
View File

@@ -0,0 +1,77 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-f16.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-f16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-bf16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-f16_q6_k.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-bf16_q6_k.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-f16_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-bf16_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-q2_k_l.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-q4_k_l.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-q5_k_l.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-q6_k_l.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-q2_k_m.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-q2_k_s.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-q4_0_l.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-q4_1_l.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-q5_1.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-q5_0_l.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-q5_1_l.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-iq2_xs.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-iq2_xxs.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-iq2_s.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-iq2_m.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r.imatrix filter=lfs diff=lfs merge=lfs -text
Llama-xLAM-2-8b-fc-r-bf16.gguf filter=lfs diff=lfs merge=lfs -text

3
Llama-xLAM-2-8b-fc-r-bf16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7fc0a3ae557327005b312a84bb5e1f33a5cc8b0b20723cab5bcdbae1ba035eb9
size 16068895328

3
Llama-xLAM-2-8b-fc-r-bf16_q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dab42d402c277acffdb6fa71b34a9a8fe22032f22034f40c34cd4198b7f55f13
size 11916534368

3
Llama-xLAM-2-8b-fc-r-f16_q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6315be385000b2292c96171242b56d82d4c3eea428b0d7b60dd8dcc345ec95b7
size 11916534368

3
Llama-xLAM-2-8b-fc-r-iq2_m.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:798673467d1759c8eab21df9bbb88a9829e1087ba323ae83edef0cdfde304e80
size 3180782496

3
Llama-xLAM-2-8b-fc-r-iq2_s.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a8012e35910e4386f7dff0a7361cd6b248b4226288b74245a3b35e06eefebcf8
size 3051545504

3
Llama-xLAM-2-8b-fc-r-iq2_xs.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9d2de0cd5204f4dad713d61f3ad154229e661e2092bfb1eb3264a916fc281d90
size 2970805152

3
Llama-xLAM-2-8b-fc-r-iq2_xxs.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:eb803d1e0cd326bdb731b93368f86077ecab00aad33847c79d863d03caf29bd3
size 2768888736

3
Llama-xLAM-2-8b-fc-r-iq3_m.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9f41d089e34866ee3e53369382ef14bc2b3d5a9eca177c2f77dd4fb932c00cdd
size 3797017504

3
Llama-xLAM-2-8b-fc-r-iq3_s.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:69b640a28eb56b6f77659f81714bdd4b6e69990d713f45d5272e7a725137bd0b
size 3743540128

3
Llama-xLAM-2-8b-fc-r-iq3_xs.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5eb31f1eecd23ba111745decc58391e1be2332616356b945a09ee66a74dcc281
size 3579962272

3
Llama-xLAM-2-8b-fc-r-iq3_xxs.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e3d0e8cb3e520f34260ba5813040b663ddd204e1b24063679b1d4e6be900602f
size 3427918752

3
Llama-xLAM-2-8b-fc-r-iq4_nl.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:eb77307d5aa71a2cbcc38f831fb3ce9cbb28a1e91b0b3e5e24580bfa62076a27
size 4677993376

3
Llama-xLAM-2-8b-fc-r-iq4_xs.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f184d4ce19e63bbea396094470288709454305acf298e07205337a86f9a371de
size 4447667104

3
Llama-xLAM-2-8b-fc-r-q2_k_m.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:376d6e6eb6024f5675aeb854259dcf1594d4046df9d934050666b22e1526d010
size 3403359136

3
Llama-xLAM-2-8b-fc-r-q2_k_s.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4df38543b646e1d61c930f68fd1762dc7afb829b4c602c61220ae70eba30e6b4
size 3079791520

3
Llama-xLAM-2-8b-fc-r-q3_k_m.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b7a82bdacce6177fe7057b37583b2b9b403172d24047f9a1b101cf66c246e856
size 4188480416

3
Llama-xLAM-2-8b-fc-r-q3_k_s.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7aedd2136746ba85e359d3026acf838557826f0944a22ef4ff09d8b6142518cf
size 3794920352

3
Llama-xLAM-2-8b-fc-r-q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:92dd37dfeb1c6f9531f5697d9d75852a97c3696901ccae8496e2d184c0f380be
size 4525777824

3
Llama-xLAM-2-8b-fc-r-q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9d0602cdf630be3e942c04538c774fbdf98fcc4a40fc37351cdf5ec939030155
size 5027652512

3
Llama-xLAM-2-8b-fc-r-q4_k_m.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8b560cc211e22c30f584d8d16f63d8b5af90ae5f1a303617172ce8417041a18b
size 5006107552

3
Llama-xLAM-2-8b-fc-r-q4_k_s.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:da23b692b97447205a96532fad8365d3a4c80401bee668a0bb966eff3c3ff9ff
size 4876346272

3
Llama-xLAM-2-8b-fc-r-q5_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ebfefd0a8a2d9d1144448f04cb1e95f40d20ab0136aa1cde0b19d8513f9a6161
size 5529527200

3
Llama-xLAM-2-8b-fc-r-q5_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:71661d9d4b7ef3754cfb8d314eff57339501656a010e6287509742e42a3ec39a
size 6031401888

3
Llama-xLAM-2-8b-fc-r-q5_k_m.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:15a03874986332e388d3c09ff5686b38327f8b5004daa9a8462ecb24ac17b2fa
size 5820588960

3
Llama-xLAM-2-8b-fc-r-q5_k_s.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4f7e9cb9a13521a8e3816cde56b063897dd04a52bb8d41c4551f6e28a57145e9
size 5753742240

3
Llama-xLAM-2-8b-fc-r-q6_k_m.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ebda1423e8bed62256608fc37347f5d47514b585b45cda6bb7b4e864deb14b1b
size 6596010912

3
Llama-xLAM-2-8b-fc-r-q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:befd68f4152a95d5ceffc37c5cfa12eb60734811e46cbb803f77d8ba8476c44c
size 8540775008

3
Llama-xLAM-2-8b-fc-r.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bb581e1812f3f3aedbce0661cf830955ae6a3c03a5cef839204a4607383af8df
size 4988204

408
README.md Normal file
View File

@@ -0,0 +1,408 @@
---
license: cc-by-nc-4.0
datasets:
- Salesforce/APIGen-MT-5k
- Salesforce/xlam-function-calling-60k
language:
- en
pipeline_tag: text-generation
tags:
- function-calling
- LLM Agent
- tool-use
- llama
- qwen
- pytorch
- LLaMA-factory
library_name: transformers
---
# <span style="color: #7FFF7F;">Llama-xLAM-2-8b-fc-r GGUF Models</span>
## <span style="color: #7F7FFF;">Model Generation Details</span>
This model was generated using [llama.cpp](https://github.com/ggerganov/llama.cpp) at commit [`6adc3c3e`](https://github.com/ggerganov/llama.cpp/commit/6adc3c3ebc029af058ac950a8e2a825fdf18ecc6).
---
## <span style="color: #7FFF7F;">Quantization Beyond the IMatrix</span>
I've been experimenting with a new quantization approach that selectively elevates the precision of key layers beyond what the default IMatrix configuration provides.
In my testing, standard IMatrix quantization underperforms at lower bit depths, especially with Mixture of Experts (MoE) models. To address this, I'm using the `--tensor-type` option in `llama.cpp` to manually "bump" important layers to higher precision. You can see the implementation here:
👉 [Layer bumping with llama.cpp](https://github.com/Mungert69/GGUFModelBuilder/blob/main/model-converter/tensor_list_builder.py)
While this does increase model file size, it significantly improves precision for a given quantization level.
### **I'd love your feedback—have you tried this? How does it perform for you?**
---
<a href="https://readyforquantum.com/huggingface_gguf_selection_guide.html" style="color: #7FFF7F;">
Click here to get info on choosing the right GGUF model format
</a>
---
<!--Begin Original Model Card-->
<p align="center">
<img width="500px" alt="xLAM" src="https://huggingface.co/datasets/jianguozhang/logos/resolve/main/xlam-no-background.png">
</p>
<p align="center">
<a href="https://arxiv.org/abs/2504.03601">[Paper]</a> |
<a href="https://apigen-mt.github.io/">[Homepage]</a> |
<a href="https://huggingface.co/datasets/Salesforce/APIGen-MT-5k">[Dataset]</a> |
<a href="https://github.com/SalesforceAIResearch/xLAM">[Github]</a>
</p>
<hr>
# Welcome to the xLAM-2 Model Family!
[Large Action Models (LAMs)](https://blog.salesforceairesearch.com/large-action-models/) are advanced language models designed to enhance decision-making by translating user intentions into executable actions. As the **brains of AI agents**, LAMs autonomously plan and execute tasks to achieve specific goals, making them invaluable for automating workflows across diverse domains.
**This model release is for research purposes only.**
The new **xLAM-2** series, built on our most advanced data synthesis, processing, and training pipelines, marks a significant leap in **multi-turn conversation** and **tool usage**. Trained using our novel APIGen-MT framework, which generates high-quality training data through simulated agent-human interactions. Our models achieve state-of-the-art performance on [**BFCL**](https://gorilla.cs.berkeley.edu/leaderboard.html) and **τ-bench** benchmarks, outperforming frontier models like GPT-4o and Claude 3.5. Notably, even our smaller models demonstrate superior capabilities in multi-turn scenarios while maintaining exceptional consistency across trials.
We've also refined the **chat template** and **vLLM integration**, making it easier to build advanced AI agents. Compared to previous xLAM models, xLAM-2 offers superior performance and seamless deployment across applications.
<p align="center">
<img width="100%" alt="Model Performance Overview" src="https://github.com/apigen-mt/apigen-mt.github.io/blob/main/img/model_board.png?raw=true">
<br>
<small><i>Comparative performance of larger xLAM-2-fc-r models (8B-70B, trained with APIGen-MT data) against state-of-the-art baselines on function-calling (BFCL v3, as of date 04/02/2025) and agentic (τ-bench) capabilities.</i></small>
</p>
## Table of Contents
- [Usage](#usage)
- [Basic Usage with Huggingface Chat Template](#basic-usage-with-huggingface-chat-template)
- [Using vLLM for Inference](#using-vllm-for-inference)
- [Setup and Serving](#setup-and-serving)
- [Testing with OpenAI API](#testing-with-openai-api)
- [Benchmark Results](#benchmark-results)
- [Citation](#citation)
---
## Model Series
[xLAM](https://huggingface.co/collections/Salesforce/xlam-models-65f00e2a0a63bbcd1c2dade4) series are significant better at many things including general tasks and function calling.
For the same number of parameters, the model have been fine-tuned across a wide range of agent tasks and scenarios, all while preserving the capabilities of the original model.
| Model | # Total Params | Context Length | Category | Download Model | Download GGUF files |
|------------------------|----------------|------------|-------|----------------|----------|
| Llama-xLAM-2-70b-fc-r | 70B | 128k | Multi-turn Conversation, Function-calling | [🤗 Link](https://huggingface.co/Salesforce/Llama-xLAM-2-70b-fc-r) | NA |
| Llama-xLAM-2-8b-fc-r | 8B | 128k | Multi-turn Conversation, Function-calling | [🤗 Link](https://huggingface.co/Salesforce/Llama-xLAM-2-8b-fc-r) | [🤗 Link](https://huggingface.co/Salesforce/Llama-xLAM-2-8b-fc-r-gguf) |
| xLAM-2-32b-fc-r | 32B | 32k (max 128k)* | Multi-turn Conversation, Function-calling | [🤗 Link](https://huggingface.co/Salesforce/xLAM-2-32b-fc-r) | NA |
| xLAM-2-3b-fc-r | 3B | 32k (max 128k)* | Multi-turn Conversation, Function-calling | [🤗 Link](https://huggingface.co/Salesforce/xLAM-2-3b-fc-r) | [🤗 Link](https://huggingface.co/Salesforce/xLAM-2-3b-fc-r-gguf) |
| xLAM-2-1b-fc-r | 1B | 32k (max 128k)* | Multi-turn Conversation, Function-calling | [🤗 Link](https://huggingface.co/Salesforce/xLAM-2-1b-fc-r) | [🤗 Link](https://huggingface.co/Salesforce/xLAM-2-1b-fc-r-gguf) |
***Note:** The default context length for Qwen-2.5-based models is 32k, but you can use techniques like YaRN (Yet Another Recursive Network) to achieve maximum 128k context length. Please refer to [here](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct#processing-long-texts) for more details.
You can also explore our previous xLAM series [here](https://huggingface.co/collections/Salesforce/xlam-models-65f00e2a0a63bbcd1c2dade4).
The `-fc` suffix indicates that the models are fine-tuned for **function calling** tasks, while the `-r` suffix signifies a **research** release.
✅ All models are fully compatible with vLLM and Transformers-based inference frameworks.
## Usage
### Framework versions
- Transformers 4.46.1 (or later)
- PyTorch 2.5.1+cu124 (or later)
- Datasets 3.1.0 (or later)
- Tokenizers 0.20.3 (or later)
### Basic Usage with Huggingface Chat Template
The new xLAM models are designed to work seamlessly with the Hugging Face Transformers library and utilize natural chat templates for an easy and intuitive conversational experience. Below are examples of how to use these models.
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("Salesforce/Llama-xLAM-2-3b-fc-r")
model = AutoModelForCausalLM.from_pretrained("Salesforce/Llama-xLAM-2-3b-fc-r", torch_dtype=torch.bfloat16, device_map="auto")
# Example conversation with a tool call
messages = [
{"role": "user", "content": "Hi, how are you?"},
{"role": "assistant", "content": "Thanks. I am doing well. How can I help you?"},
{"role": "user", "content": "What's the weather like in London?"},
]
tools = [
{
"name": "get_weather",
"description": "Get the current weather for a location",
"parameters": {
"type": "object",
"properties": {
"location": {"type": "string", "description": "The city and state, e.g. San Francisco, CA"},
"unit": {"type": "string", "enum": ["celsius", "fahrenheit"], "description": "The unit of temperature to return"}
},
"required": ["location"]
}
}
]
print("====== prompt after applying chat template ======")
print(tokenizer.apply_chat_template(messages, tools=tools, add_generation_prompt=True, tokenize=False))
inputs = tokenizer.apply_chat_template(messages, tools=tools, add_generation_prompt=True, return_dict=True, return_tensors="pt")
input_ids_len = inputs["input_ids"].shape[-1] # Get the length of the input tokens
inputs = {k: v.to(model.device) for k, v in inputs.items()}
print("====== model response ======")
outputs = model.generate(**inputs, max_new_tokens=256)
generated_tokens = outputs[:, input_ids_len:] # Slice the output to get only the newly generated tokens
print(tokenizer.decode(generated_tokens[0], skip_special_tokens=True))
```
### Using vLLM for Inference
The xLAM models can also be efficiently served using vLLM for high-throughput inference. Please use `vllm>=0.6.5` since earlier versions will cause degraded performance for Qwen-based models.
#### Setup and Serving
1. Install vLLM with the required version:
```bash
pip install "vllm>=0.6.5"
```
2. Download the tool parser plugin to your local path:
```bash
wget https://huggingface.co/Salesforce/xLAM-2-1b-fc-r/raw/main/xlam_tool_call_parser.py
```
3. Start the OpenAI API-compatible endpoint:
```bash
vllm serve Salesforce/xLAM-2-1b-fc-r \
--enable-auto-tool-choice \
--tool-parser-plugin ./xlam_tool_call_parser.py \
--tool-call-parser xlam \
--tensor-parallel-size 1
```
Note: Ensure that the tool parser plugin file is downloaded and that the path specified in `--tool-parser-plugin` correctly points to your local copy of the file. The xLAM series models all utilize the **same** tool call parser, so you only need to download it **once** for all models.
#### Testing with OpenAI API
Here's a minimal example to test tool usage with the served endpoint:
```python
import openai
import json
# Configure the client to use your local vLLM endpoint
client = openai.OpenAI(
base_url="http://localhost:8000/v1", # Default vLLM server URL
api_key="empty" # Can be any string
)
# Define a tool/function
tools = [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the current weather for a location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA"
},
"unit": {
"type": "string",
"enum": ["celsius", "fahrenheit"],
"description": "The unit of temperature to return"
}
},
"required": ["location"]
}
}
}
]
# Create a chat completion
response = client.chat.completions.create(
model="Salesforce/xLAM-2-1b-fc-r", # Model name doesn't matter, vLLM uses the served model
messages=[
{"role": "system", "content": "You are a helpful assistant that can use tools."},
{"role": "user", "content": "What's the weather like in San Francisco?"}
],
tools=tools,
tool_choice="auto"
)
# Print the response
print("Assistant's response:")
print(json.dumps(response.model_dump(), indent=2))
```
For more advanced configurations and deployment options, please refer to the [vLLM documentation](https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html).
## Benchmark Results
### Berkeley Function-Calling Leaderboard (BFCL v3)
<p align="center">
<img width="80%" alt="BFCL Results" src="https://github.com/apigen-mt/apigen-mt.github.io/blob/main/img/bfcl-result.png?raw=true">
<br>
<small><i>Performance comparison of different models on [BFCL leaderboard](https://gorilla.cs.berkeley.edu/leaderboard.html). The rank is based on the overall accuracy, which is a weighted average of different evaluation categories. "FC" stands for function-calling mode in contrast to using a customized "prompt" to extract the function calls.</i></small>
</p>
### τ-bench Benchmark
<p align="center">
<img width="80%" alt="Tau-bench Results" src="https://github.com/apigen-mt/apigen-mt.github.io/blob/main/img/taubench-result.png?raw=true">
<br>
<small><i>Success Rate (pass@1) on τ-bench benchmark averaged across at least 5 trials. Our xLAM-2-70b-fc-r model achieves an overall success rate of 56.2% on τ-bench, significantly outperforming the base Llama 3.1 70B Instruct model (38.2%) and other open-source models like DeepSeek v3 (40.6%). Notably, our best model even outperforms proprietary models such as GPT-4o (52.9%) and approaches the performance of more recent models like Claude 3.5 Sonnet (new) (60.1%).</i></small>
</p>
<p align="center">
<img width="80%" alt="Pass^k curves" src="https://github.com/apigen-mt/apigen-mt.github.io/blob/main/img/pass_k_curves_retail_airline.png?raw=true">
<br>
<small><i>Pass^k curves measuring the probability that all 5 independent trials succeed for a given task, averaged across all tasks for τ-retail (left) and τ-airline (right) domains. Higher values indicate better consistency of the models.</i></small>
</p>
## Ethical Considerations
This release is for research purposes only in support of an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. We encourage users to consider the common limitations of AI, comply with applicable laws, and leverage best practices when selecting use cases, particularly for high-risk scenarios where errors or misuse could significantly impact people's lives, rights, or safety. For further guidance on use cases, refer to our AUP and AI AUP.
### Model Licenses
For all Llama relevant models, please also follow corresponding Llama license and terms. Meta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.
## Citation
If you use our model or dataset in your work, please cite our paper:
```bibtex
@article{prabhakar2025apigen,
title={APIGen-MT: Agentic PIpeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay},
author={Prabhakar, Akshara and Liu, Zuxin and Zhu, Ming and Zhang, Jianguo and Awalgaonkar, Tulika and Wang, Shiyu and Liu, Zhiwei and Chen, Haolin and Hoang, Thai and others},
journal={arXiv preprint arXiv:2504.03601},
year={2025}
}
```
Additionally, please check our other awesome related works regarding xLAM series and consider citing them as well:
```bibtex
@article{zhang2025actionstudio,
title={ActionStudio: A Lightweight Framework for Data and Training of Action Models},
author={Zhang, Jianguo and Hoang, Thai and Zhu, Ming and Liu, Zuxin and Wang, Shiyu and Awalgaonkar, Tulika and Prabhakar, Akshara and Chen, Haolin and Yao, Weiran and Liu, Zhiwei and others},
journal={arXiv preprint arXiv:2503.22673},
year={2025}
}
```
```bibtex
@article{zhang2024xlam,
title={xLAM: A Family of Large Action Models to Empower AI Agent Systems},
author={Zhang, Jianguo and Lan, Tian and Zhu, Ming and Liu, Zuxin and Hoang, Thai and Kokane, Shirley and Yao, Weiran and Tan, Juntao and Prabhakar, Akshara and Chen, Haolin and others},
journal={arXiv preprint arXiv:2409.03215},
year={2024}
}
```
```bibtex
@article{liu2024apigen,
title={Apigen: Automated pipeline for generating verifiable and diverse function-calling datasets},
author={Liu, Zuxin and Hoang, Thai and Zhang, Jianguo and Zhu, Ming and Lan, Tian and Tan, Juntao and Yao, Weiran and Liu, Zhiwei and Feng, Yihao and RN, Rithesh and others},
journal={Advances in Neural Information Processing Systems},
volume={37},
pages={54463--54482},
year={2024}
}
```
```bibtex
@article{zhang2024agentohana,
title={AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning},
author={Zhang, Jianguo and Lan, Tian and Murthy, Rithesh and Liu, Zhiwei and Yao, Weiran and Tan, Juntao and Hoang, Thai and Yang, Liangwei and Feng, Yihao and Liu, Zuxin and others},
journal={arXiv preprint arXiv:2402.15506},
year={2024}
}
```
<!--End Original Model Card-->
---
# <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span>
Help me test my **AI-Powered Quantum Network Monitor Assistant** with **quantum-ready security checks**:
👉 [Quantum Network Monitor](https://readyforquantum.com/?assistant=open&utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme)
The full Open Source Code for the Quantum Network Monitor Service available at my github repos ( repos with NetworkMonitor in the name) : [Source Code Quantum Network Monitor](https://github.com/Mungert69). You will also find the code I use to quantize the models if you want to do it yourself [GGUFModelBuilder](https://github.com/Mungert69/GGUFModelBuilder)
💬 **How to test**:
Choose an **AI assistant type**:
- `TurboLLM` (GPT-4.1-mini)
- `HugLLM` (Hugginface Open-source models)
- `TestLLM` (Experimental CPU-only)
### **What I’m Testing**
I’m pushing the limits of **small open-source models for AI network monitoring**, specifically:
- **Function calling** against live network services
- **How small can a model go** while still handling:
- Automated **Nmap security scans**
- **Quantum-readiness checks**
- **Network Monitoring tasks**
🟡 **TestLLM** – Current experimental model (llama.cpp on 2 CPU threads on huggingface docker space):
- ✅ **Zero-configuration setup**
- ⏳ 30s load time (slow inference but **no API costs**) . No token limited as the cost is low.
- 🔧 **Help wanted!** If you’re into **edge-device AI**, let’s collaborate!
### **Other Assistants**
🟢 **TurboLLM** – Uses **gpt-4.1-mini** :
- **It performs very well but unfortunatly OpenAI charges per token. For this reason tokens usage is limited.
- **Create custom cmd processors to run .net code on Quantum Network Monitor Agents**
- **Real-time network diagnostics and monitoring**
- **Security Audits**
- **Penetration testing** (Nmap/Metasploit)
🔵 **HugLLM** – Latest Open-source models:
- 🌐 Runs on Hugging Face Inference API. Performs pretty well using the lastest models hosted on Novita.
### 💡 **Example commands you could test**:
1. `"Give me info on my websites SSL certificate"`
2. `"Check if my server is using quantum safe encyption for communication"`
3. `"Run a comprehensive security audit on my server"`
4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a [Quantum Network Monitor Agent](https://readyforquantum.com/Download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) to run the .net code on. This is a very flexible and powerful feature. Use with caution!
### Final Word
I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is [open source](https://github.com/Mungert69). Feel free to use whatever you find helpful.
If you appreciate the work, please consider [buying me a coffee](https://www.buymeacoffee.com/mahadeva) ☕. Your support helps cover service costs and allows me to raise token limits for everyone.
I'm also open to job opportunities or sponsorship.
Thank you! 😊