ermiaazarkhalili

Qwen3.8-2B-Function-Calling-xLAM-Unsloth

README

License: apache-2.0

Usage

python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "ermiaazarkhalili/Qwen3.8-2B-Function-Calling-xLAM-Unsloth"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, dtype='auto', device_map='auto')

messages = [{"role": "user", "content": "Explain gradient checkpointing in two sentences."}]
inputs = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True, return_tensors='pt'
).to(model.device)

outputs = model.generate(inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Training configuration

Table with columns: Setting, Value
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.

Table with columns: SLURM job, Steps, First loss, Final loss
SLURM job	Steps	First loss	Final loss
`55745478`	29,700	1.1972	1.0091
`55541067`	7,500	0.6355	0.1270

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_qwen38-2b_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.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

ermiaazarkhalili

Model Tree

Base

empero-ai/Qwen3.8-2B-Distill

Fine-tuned

this model

Input Modalities

TextImageVideo

Output Modalities

Text

Supported Functionality