Downloads · 30 days
52
5% of all-time downloads
FastContext-4B-RL_base-Function-Calling-xLAM-Unsloth-GGUF
ermiaazarkhalili/FastContext-4B-RL_base-Function-Calling-xLAM-Unsloth-GGUF
FastContext-4B-RL_base-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.
GGUF quantizations of a LoRA fine-tune of microsoft/FastContext-1.0-4B-RL (no longer available on the Hub), supervised fine-tuned on Salesforce/xlam-function-calling-60k.
All-time downloads
964
Public
Repo size
16.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf16.7 GB · 100%
At a glance
- Task
- Text Generation
- Library
- gguf
- Access
- Public
- Created
- Jun 22, 2026
- Updated
- Aug 23, 2026
- SHA
- 04a45a2f
Try a prompt
Base models
Model card
From the Hugging Face model README
FastContext-4B-RL_base-Function-Calling-xLAM-Unsloth-GGUF
GGUF quantizations of a LoRA fine-tune of microsoft/FastContext-1.0-4B-RL (no longer available on the Hub), supervised fine-tuned on Salesforce/xlam-function-calling-60k.
Quantized from ermiaazarkhalili/FastContext-4B-RL_base-Function-Calling-xLAM-Unsloth. See that repository for the full-precision weights.
| Base model | microsoft/FastContext-1.0-4B-RL (no longer available on the Hub) |
| Training data | Salesforce/xlam-function-calling-60k |
| Method | LoRA supervised fine-tuning via Unsloth + TRL |
Available quantizations
| File | Size |
|---|---|
fastcontext-4b-rl_base-function-calling-xlam-unsloth.q2_k.gguf | 1.67 GB |
fastcontext-4b-rl_base-function-calling-xlam-unsloth.q3_k_m.gguf | 2.08 GB |
fastcontext-4b-rl_base-function-calling-xlam-unsloth.q4_k_m.gguf | 2.50 GB |
fastcontext-4b-rl_base-function-calling-xlam-unsloth.q5_k_m.gguf | 2.89 GB |
fastcontext-4b-rl_base-function-calling-xlam-unsloth.q6_k.gguf | 3.31 GB |
fastcontext-4b-rl_base-function-calling-xlam-unsloth.q8_0.gguf | 4.28 GB |
Usage
llama.cpp
huggingface-cli download ermiaazarkhalili/FastContext-4B-RL_base-Function-Calling-xLAM-Unsloth-GGUF fastcontext-4b-rl_base-function-calling-xlam-unsloth.q4_k_m.gguf --local-dir .
llama-cli -m fastcontext-4b-rl_base-function-calling-xlam-unsloth.q4_k_m.gguf -p "Explain gradient checkpointing in two sentences." -n 256
Ollama
echo 'FROM ./fastcontext-4b-rl_base-function-calling-xlam-unsloth.q4_k_m.gguf' > Modelfile
ollama create fastcontext-4b-rl_base-function-calling-xlam-unsloth-gguf -f Modelfile
ollama run fastcontext-4b-rl_base-function-calling-xlam-unsloth-gguf
Training configuration
| Setting | Value |
|---|---|
| LoRA rank (r) | 16 |
| LoRA alpha | 16 |
| Learning rate | 0.0002 |
| Epochs | 1 |
| Effective batch size | 8 (2 x 4 grad accum) |
| Max sequence length | 2048 |
| Base precision | 4-bit (QLoRA) |
| Target modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_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 |
|---|---|---|---|
53225525 | 94,254 | 1.1631 | 0.8687 |
45169150 | 7,500 | 0.6748 | 0.1439 |
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_fastcontext-4b-rl_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
- Created
- Jun 22, 2026
- Updated
- Aug 23, 2026