Downloads · 30 days
942
42% of all-time downloads
Qwen3.8-4B-Function-Calling-xLAM-Unsloth-GGUF
ermiaazarkhalili/Qwen3.8-4B-Function-Calling-xLAM-Unsloth-GGUF
Qwen3.8-4B-Function-Calling-xLAM-Unsloth-GGUF is a text generation model from ermiaazarkhalili. Use it when you need the model to write or continue text. It is set up for gguf. The card lists the license as apache-2.0.
GGUF quantizations of a LoRA fine-tune of empero-ai/Qwen3.8-4B, supervised fine-tuned on Salesforce/xlam-function-calling-60k.
All-time downloads
2.3K
Public
Repo size
18.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf18.4 GB · 100%
At a glance
- Task
- Text Generation
- Library
- gguf
- License
- apache-2.0
- Access
- Public
- Created
- Aug 21, 2026
- Updated
- Aug 21, 2026
- SHA
- 0462c30d
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3.8-4B-Function-Calling-xLAM-Unsloth-GGUF
GGUF quantizations of a LoRA fine-tune of empero-ai/Qwen3.8-4B, supervised fine-tuned on Salesforce/xlam-function-calling-60k.
Quantized from ermiaazarkhalili/Qwen3.8-4B-Function-Calling-xLAM-Unsloth. See that repository for the full-precision weights.
| Base model | empero-ai/Qwen3.8-4B |
| Training data | Salesforce/xlam-function-calling-60k |
| Method | LoRA supervised fine-tuning via Unsloth + TRL |
| License | apache-2.0 (inherited from the base model) |
Available quantizations
| File | Size |
|---|---|
qwen3.8-4b-function-calling-xlam-unsloth.q2_k.gguf | 1.96 GB |
qwen3.8-4b-function-calling-xlam-unsloth.q3_k_m.gguf | 2.32 GB |
qwen3.8-4b-function-calling-xlam-unsloth.q4_k_m.gguf | 2.78 GB |
qwen3.8-4b-function-calling-xlam-unsloth.q5_k_m.gguf | 3.16 GB |
qwen3.8-4b-function-calling-xlam-unsloth.q6_k.gguf | 3.56 GB |
qwen3.8-4b-function-calling-xlam-unsloth.q8_0.gguf | 4.61 GB |
Usage
llama.cpp
huggingface-cli download ermiaazarkhalili/Qwen3.8-4B-Function-Calling-xLAM-Unsloth-GGUF qwen3.8-4b-function-calling-xlam-unsloth.q4_k_m.gguf --local-dir .
llama-cli -m qwen3.8-4b-function-calling-xlam-unsloth.q4_k_m.gguf -p "Explain gradient checkpointing in two sentences." -n 256
Ollama
echo 'FROM ./qwen3.8-4b-function-calling-xlam-unsloth.q4_k_m.gguf' > Modelfile
ollama create qwen3.8-4b-function-calling-xlam-unsloth-gguf -f Modelfile
ollama run qwen3.8-4b-function-calling-xlam-unsloth-gguf
Training configuration
| Setting | Value |
|---|---|
| LoRA rank (r) | 64 |
| LoRA alpha | 64 |
| Learning rate | 0.0002 |
| Epochs | 1 |
| Effective batch size | 8 (1 x 8 grad accum) |
| Max sequence length | 2048 |
| Base precision | 4-bit (QLoRA) |
| Target modules | down_proj, gate_proj, in_proj_qkv, in_proj_z, k_proj, o_proj, out_proj, q_proj, up_proj, v_proj |
Observed training loss
Measured from our SLURM logs for this configuration. These are training-loss observations only — no downstream benchmark evaluation has been run on this model, so they should not be read as a quality claim.
| SLURM job | Steps | First loss | Final loss |
|---|---|---|---|
55745501 | 22,200 | 1.0008 | 0.8924 |
55541068 | 7,500 | 0.5731 | 0.1184 |
Limitations
- No benchmark evaluation has been run on this checkpoint. The only reported numbers are training-loss observations.
- Inherits the biases, knowledge cutoff and failure modes of the base model.
- Fine-tuned on a single instruction-following dataset; behaviour outside that distribution is untested.
- LoRA adapters were merged into the base weights, so the merged model cannot be detached from this fine-tune.
Reproducing
Trained by notebooks/xlam_function_calling_qwen38-4b_unsloth.ipynb, executed non-interactively with
papermill on a SLURM H100 partition (Unsloth + TRL, LoRA).
Card generated from the training run's own configuration and logs by
scripts/generate_hub_model_card.py.
- Task
- Text Generation
- Library
- gguf
- License
- apache-2.0
- Created
- Aug 21, 2026
- Updated
- Aug 21, 2026