Instructions to use TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b", device_map="auto")

llama-cpp-python

How to use TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b",
	filename="Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b-BF16-mmproj.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b:Q4_K_M

Use Docker

docker model run hf.co/TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b:Q4_K_M

LM Studio
Jan

vLLM

How to use TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b:Q4_K_M

SGLang

How to use TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b 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 "TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b" \
    --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": "TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b",
		"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 "TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b" \
        --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": "TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b with Ollama:
```
ollama run hf.co/TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b:Q4_K_M
```

Unsloth Studio

How to use TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b 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 TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b 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 TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b to start chatting

How to use TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b with Docker Model Runner:
```
docker model run hf.co/TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b:Q4_K_M
```

Lemonade

How to use TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b-Q4_K_M

List all available models

lemonade list

Qwen3-VL-8B SumTablets — Cuneiform Transliteration Model

A fine-tuned language model for automatic transliteration of Sumerian cuneiform sign sequences into scholarly Latin transliteration, trained on the SumTablets dataset. This model is intended to assist Assyriologists, digital humanities researchers, and anyone working with ancient Mesopotamian texts.

Evaluation result: 92.4% average token overlap on held-out test samples, 100% numerical marker accuracy, 100% structural tag preservation.

Model Description

This model is a QLoRA fine-tune of Qwen3-VL-8B-Instruct on the task of converting cuneiform sign name sequences (glyph_names) to standard Assyriological transliteration. It learns the mapping between the ASCII sign name representation used in cuneiform databases and the scholarly transliteration format used in academic publications.

What it can do

Convert cuneiform sign name sequences (e.g. DIŠ LU ŠE AN EN KID) to transliterated Sumerian (e.g. 1(diš) udu še {d}en-lil₂)
Preserve scholarly structural markers: <SURFACE>, <COLUMN>, <BLANK_SPACE>, <RULING>
Handle subscript numerals and diacritics: ₂, ₃, š, ŋ, ḫ
Correctly produce divine determinatives: {d}, {ki}, {geš}, {munus}, {dug}
Accurately render numerical qualifiers: 1(diš), 2(ban₂), 3(barig), 4(geš₂), sexagesimal notation
Handle <unk> tokens for damaged or illegible signs
Generalize across historical periods and tablet genres

What it cannot do (current limitations)

Read tablet images directly (text-only inference; vision tower not fine-tuned)
Transliterate sign sequences outside the SumTablets training distribution with guaranteed accuracy
Replace expert Assyriological review for publication-quality work
Handle all sign variants, particularly rare or archaic forms not well-represented in the training data

Intended Use

Intended users: Assyriologists, cuneiform scholars, digital humanities researchers, historians of ancient Mesopotamia, archaeologists working with tablet corpora, and developers building tools for ancient language processing.

Intended use cases:

Rapid first-pass transliteration of large tablet corpora
Assistance tool for researchers working with Cuneiform Digital Library Initiative (CDLI) data
Educational tool for students learning Sumerian
Integration into digital humanities pipelines for ancient text processing
Baseline model for further fine-tuning on specific tablet genres or periods

Not intended for: Authoritative scholarly publication without expert review. This model is an assistive tool, not a replacement for trained Assyriologists.

Training Details

Base Model

Property	Value
Base model	`unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit`
Architecture	Qwen3-VL (Vision-Language Model, language tower only)
Parameters	8.8B total, 43.6M trainable (0.50%)
Quantization	NF4 4-bit (QLoRA)
Compute dtype	bfloat16

Training Configuration

Hyperparameter	Value
Method	QLoRA (Quantized Low-Rank Adaptation)
LoRA rank (r)	16
LoRA alpha	16
RSLoRA	enabled
Target modules	`q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj`
Learning rate	8e-05
LR scheduler	Cosine
Warmup	20 steps
Batch size	2 per device
Gradient accumulation	8 steps
Effective batch size	16
Optimizer	AdamW 8-bit
Weight decay	0.01
Gradient clipping	1.0 (max_grad_norm)
Max sequence length	4096 tokens
Packing	enabled
Gradient checkpointing	Unsloth optimized
Epochs	1 (stopped at step ~1161, ~22% through epoch)
Training framework	Unsloth Studio 2026.5.10
Hardware	A Single NVIDIA RTX 5080 16GB (3h 54m 38s)

Training Dataset

Property	Value
Dataset	colesimmons/SumTablets
Train split	82,452 samples
Validation split	4,580 samples
Test split	4,580 samples
License	CC-BY-4.0
Input field	`glyph_names` (cuneiform sign names in ASCII)
Target field	`transliteration` (scholarly Latin transliteration)

Training Trajectory

The model was trained with early stopping based on loss monitoring. Training proceeded through several distinct phases:

Step range	Loss range	Phase
1–100	3.63 → 0.72	Rapid initial learning
100–450	0.72 → 0.55	First plateau, optimizer stabilizing
450–700	0.55 → 0.38	Breakthrough descent
700–1000	0.38 → 0.30	Continued descent, sub-0.40 consolidation
1000–1161	0.30 → 0.20	Final descent, target zone reached

Final reported loss: ~0.202 at step 1161
Best observed single-step loss: 0.2844
Gradient norm at checkpoint: consistently 0.55–0.90 (stable)

Note on reported loss: Training included full sequence loss (prompt + completion) for the resume phase due to a template mapping issue. Completion-only loss is estimated to be lower than the reported figures. This is documented for scientific transparency.

Evaluation

Test Set Performance (10% held-out samples)

Evaluation was performed at checkpoint step 1161 against held-out samples from the SumTablets test split, spanning Administrative, Literary, and Royal Inscription genres across Ur III, Old Akkadian, Early Dynastic IIIb, and Old Babylonian periods.

Metric	Score
Average token overlap	92.4%
Numerical marker accuracy	100%
Format tag preservation	100%
Samples with >84% overlap	9/10
Samples with >97% overlap	2/10
Exact matches	1/10

Sample-level Results

Sample	Genre	Token Overlap	Notes
1	Administrative	High	Long output (~900 chars), correct format throughout
2	Administrative	Good	Minor sign errors: `ka`→`sumurₓ(KA)`, `ama`→`gid₂`
3	Administrative	Excellent	Strong match across full tablet
4	Administrative	Excellent	Numerics and structure correct
5	Numeric	Excellent	All number qualifiers flawless
6	Administrative	92%	Perfect numericals, minor token variation
7	Administrative	89%	Minor spacing variation only
8	Administrative	84%	Perfect numericals, some sign-level divergence
9	Administrative	97%	Near-perfect across all lines
10	Administrative	100%	Exact match

Strengths

Structural tags: Perfect preservation of <SURFACE>, <COLUMN>, <BLANK_SPACE>, <RULING> markers
Numerical system: Flawless handling of the Sumerian counting system across all numeral classes (ordinal, capacity, weight, area, sexagesimal)
Determinatives: Correct rendering of divine ({d}), geographic ({ki}), wooden ({geš}), and other determinative classes
Diacritics and subscripts: Accurate production of subscripted signs (š, ŋ, ḫ, subscript numerals)
Damaged signs: Appropriate <unk> token use for illegible signs

Known Limitations

Occasional sign-level confusions between visually or contextually similar signs (e.g. elam/dih₃, gaš/gazi) — consistent with the difficulty of the task rather than systematic failure
Performance on Literary and Royal Inscription genres is less characterized than Administrative tablets, which dominate the training distribution (~85% of SumTablets)
Output truncation possible on very long tablets; not observed in evaluation samples but possible at the margins of the 4096 token context window

Usage

Basic Inference

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
import torch

# Load base model and adapter
base_model_id = "unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit"
adapter_path = "TRACCERR/Qwen3-VL-8B-SumTablets"

tokenizer = AutoTokenizer.from_pretrained(base_model_id)
model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)
model = PeftModel.from_pretrained(model, adapter_path)
model.eval()

# Format input
sign_sequence = "DIŠ |GA₂×PA| GA A LU |HI×AŠ₂| SAG BA TIL UD 4(DIŠ) |HI×BAD|"

system_prompt = (
    "You are an expert Assyriologist specializing in Sumerian cuneiform tablets. "
    "Given a sequence of cuneiform sign names, produce the correct transliteration. "
    "Preserve all structural markers (<SURFACE>, <COLUMN>, <BLANK_SPACE>, <RULING>), "
    "subscript numerals, and <unk> tokens for damaged or illegible signs. "
    "Output only the transliteration."
)

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": f"Sign sequence:\n{sign_sequence}\n\nProvide the transliteration."}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.1,
        do_sample=False,
        repetition_penalty=1.1
    )

response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
print(response)
# Expected: 1(diš) sila₄ ga a udu hur-sag ba-uš₂ u₄ 4(diš)-kam

With Unsloth (recommended for speed)

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="TRACCERR/Qwen3-VL-8B-SumTablets",
    max_seq_length=4096,
    dtype=None,  # Auto-detect
    load_in_4bit=True,
)
FastLanguageModel.for_inference(model)

Input Format

The model expects cuneiform sign names in CDLI/ATF format — uppercase sign names, compound signs in pipes (e.g. |GA₂×PA|), numerical notations like 4(DIŠ). This corresponds directly to the glyph_names field in the SumTablets dataset.

Dataset Credit and Attribution

This model was trained on the SumTablets dataset created by Cole Simmons.

Dataset: colesimmons/SumTablets
License: CC-BY-4.0
Description: A comprehensive dataset of Sumerian cuneiform tablets containing transliterations, sign names, and Unicode cuneiform characters, sourced from the Cuneiform Digital Library Initiative (CDLI)

The underlying tablet data originates from the Cuneiform Digital Library Initiative (CDLI), a collaborative project of the University of California Los Angeles, the Max Planck Institute for the History of Science, and partner institutions worldwide. The CDLI database represents decades of work by hundreds of Assyriologists who created the original transliterations.

We gratefully acknowledge:

The scholars who produced the original tablet transliterations archived in CDLI
Cole Simmons for curating and publishing the SumTablets dataset
The CDLI project for making cuneiform scholarship openly accessible

Scientific Transparency

This section documents training decisions, anomalies, and limitations for the benefit of the research community.

Training Anomalies Documented

Scheduler miscalibration: Sequence packing reduced the effective step count from the displayed 5,154 to approximately 330 per epoch, but the cosine LR scheduler was anchored to the display total. This resulted in near-peak LR (7.8–7.9e-05) throughout training rather than the intended cosine decay. The model trained at approximately constant high LR for the full run.

Packing disabled on resume: After manual checkpoint resume, Unsloth detected the VLM architecture and silently disabled sequence packing ("Sample packing skipped (vision-language model detected)"). The resumed training ran unpacked, changing the effective token density per step.

Completion masking failure on resume: The train_on_completions=true setting (intended to mask prompt tokens and compute loss only on transliteration output) failed to apply on resume due to missing template mapping for the VLM model ID. The resumed training computed loss over full sequences including system prompt and user turn. This inflates the reported loss but does not indicate incorrect training — the model still learned the target mapping.

Loss reporting: The "0.202 final loss" figure includes prompt tokens in the loss calculation for the resumed portion of training. True completion-only loss is estimated lower. Single-step minimums of 0.2844 were observed under completion-only conditions earlier in training.

Historical Accuracy Notes

The model's transliteration output reflects the scholarly conventions encoded in the CDLI database as of the SumTablets dataset creation date. Cuneiform transliteration involves interpretive choices by scholars, and the training data represents one scholarly tradition. Known conventions include:

Sign readings follow CDLI/ePSD2 (electronic Pennsylvania Sumerian Dictionary) conventions
Numerical notation follows ATF (Ascii Transliteration Format) standards
Uncertain readings are represented as <unk> in both input and output
The model will reproduce the transliteration conventions of the training corpus, which may differ from alternative scholarly traditions

The model should not be used as an authority on disputed sign readings. Expert Assyriological review is recommended for any publication-quality use.

Reproducibility

Component	Version
Unsloth Studio	2026.5.10
Transformers	4.57.6
PyTorch	2.10.0+cu130
CUDA	12.0 / Toolkit 13.0
bitsandbytes	(Unsloth bundled)
Random seed	42
Hardware	NVIDIA RTX 5080 16GB, Windows 11

Model Card Authors

TRACCERR — Fine-tuning, training infrastructure, evaluation, and documentation.
Trained using Unsloth Studio for accelerated QLoRA fine-tuning on Windows.

Citation

If you use this model in research, please cite the SumTablets dataset and the CDLI:

@dataset{simmons2024sumtablets,
  author    = {Cole Simmons},
  title     = {SumTablets: A Dataset for Sumerian Cuneiform Transliteration},
  year      = {2024},
  publisher = {Hugging Face},
  url       = {https://huggingface.co/datasets/colesimmons/SumTablets},
  license   = {CC-BY-4.0}
}

@misc{cdli,
  title        = {Cuneiform Digital Library Initiative},
  howpublished = {\url{https://cdli.ucla.edu}},
  note         = {Collaborative project of UCLA, MPIWG, and partner institutions}
}

@misc{traccerr2026sumtablets_model,
  author       = {TRACCERR},
  title        = {Qwen3-VL-8B SumTablets: A Fine-Tuned Model for Sumerian Cuneiform Transliteration},
  year         = {2026},
  publisher    = {Hugging Face},
  url          = {https://huggingface.co/TRACCERR/Qwen3-VL-8B-SumTablets}
}

License

This model is released under CC-BY-4.0, consistent with the license of the SumTablets training dataset.

You are free to use, share, and adapt this model for any purpose, including commercial use, provided appropriate credit is given to:

Cole Simmons (SumTablets dataset)
The CDLI project (underlying tablet data)
TRACCERR (model fine-tuning)

Related Resources

SumTablets Dataset — Training data
SumTablets Photos Dataset — Tablet images (for future multimodal work)
CDLI — Cuneiform Digital Library Initiative
ePSD2 — Electronic Pennsylvania Sumerian Dictionary
ORACC — Open Richly Annotated Cuneiform Corpus
Unsloth — Training framework used
ATF Format Documentation — Input format specification

Downloads last month: 127

GGUF

Model size

8B params

Architecture

qwen3vl

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

Model tree for TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b

Base model

Qwen/Qwen3-VL-8B-Instruct

Quantized

unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit

Adapter

(41)

this model

TRACCERR
/

Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b

Qwen3-VL-8B SumTablets — Cuneiform Transliteration Model

Model Description

What it can do

What it cannot do (current limitations)

Intended Use

Training Details

Base Model

Training Configuration

Training Dataset

Training Trajectory

Evaluation

Test Set Performance (10% held-out samples)

Sample-level Results

Strengths

Known Limitations

Usage

Basic Inference

With Unsloth (recommended for speed)

Input Format

Dataset Credit and Attribution

Scientific Transparency

Training Anomalies Documented

Historical Accuracy Notes

Reproducibility

Model Card Authors

Citation

License

Related Resources

Model tree for TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b

Dataset used to train TRACCERR/Qwen3-VL-8B-Instruct-Sumtablets-V2-bnb-4b