Instructions to use sahilchachra/Tessera-4B-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sahilchachra/Tessera-4B-Preview with Transformers:

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

pipe = pipeline("text-generation", model="sahilchachra/Tessera-4B-Preview")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("sahilchachra/Tessera-4B-Preview")
model = AutoModelForMultimodalLM.from_pretrained("sahilchachra/Tessera-4B-Preview")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sahilchachra/Tessera-4B-Preview with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/sahilchachra/Tessera-4B-Preview

SGLang

How to use sahilchachra/Tessera-4B-Preview 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 "sahilchachra/Tessera-4B-Preview" \
    --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": "sahilchachra/Tessera-4B-Preview",
		"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 "sahilchachra/Tessera-4B-Preview" \
        --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": "sahilchachra/Tessera-4B-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sahilchachra/Tessera-4B-Preview with Docker Model Runner:
```
docker model run hf.co/sahilchachra/Tessera-4B-Preview
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Tessera-4B

A tessera is a single tile in a mosaic — and its Greek root means "four." Tessera-4B = four curriculum stages composed into one capable model.

Tessera-4B is a 4-stage curriculum fine-tune of Qwen/Qwen3.5-4B (instruct): Reason → Plan → Use Tools → Align. Each stage trains on the previous stage's merged weights and replays ~10% of earlier data to prevent forgetting.

Base: Qwen/Qwen3.5-4B (instruct) · VLM + hybrid-attention · supports a <think> channel
Method: QLoRA (4-bit NF4), adapter merged between stages
Compute: a single NVIDIA B200 (192 GB), ~8 h, ~$40 end-to-end (training + evaluation, including false starts)
Thinking preserved: emits <think>…</think> on hard problems, stays direct on tool calls / simple asks

Results below separate standardized benchmarks from internal proxies, and note the evaluation issues encountered. See the full write-up for details.

Quantized variants

Ready-to-run quantizations for local / edge inference (Apple Silicon MLX + llama.cpp GGUF):

Format	Repo
MLX · MXFP4	Tessera-4B-Preview-mxfp4-mlx
MLX · MXFP8	Tessera-4B-Preview-mxfp8-mlx
MLX · INT4 (affine)	Tessera-4B-Preview-int4-mlx
MLX · INT8 (affine)	Tessera-4B-Preview-int8-mlx
MLX · OptiQ 5-bpw (mixed)	Tessera-4B-Preview-optiq-5bpw-mlx
GGUF · Q4_K_M / Q5_K_M / Q8_0	Tessera-4B-Preview-GGUF

Results

Standardized benchmarks — lm-evaluation-harness (base → Tessera-4B)

Benchmark	base	Tessera-4B	Δ
MMLU	0.743	0.723	−0.020
ARC-Challenge (acc_norm)	0.543	0.561	+0.018
HellaSwag (acc_norm)	0.731	0.750	+0.019
Winogrande	0.699	0.693	−0.006

Tool calling — held-out, 20 cases (function selection)

	base	Tessera-4B
Function selection	0.90	0.85

Internal proxy (per stage) — GSM8K-style reasoning, 200 samples

After stage	Reasoning (proxy)
base	0.375
1 Reasoning	0.78
2 Planning	0.775
3 Tools	0.79
4 Align	0.785

Interpretation: on standardized benchmarks, Tessera ≈ base — expected when specializing an already-strong instruct model on a budget. We trained reasoning/agentic/tools, not broad knowledge, so MMLU holds roughly flat (−2% is a small, normal SFT cost — we retained general ability rather than regressing it). The large reasoning gain (0.38→0.79) is from an internal proxy, not a standardized GSM8K-generative run, and is reported as such.

Curriculum & training

Stage	Skill	Examples	Context	Epochs	Loss start→end
1	Reasoning	25,000	8,192	1	1.03 → ~0.70
2	Agentic	13,000	8,192	1	1.27 → 0.67
3	Tool calling	18,000	8,192	1	1.16 → 0.55
4	Instruction	9,998	4,096	2	0.95 → 0.87

LoRA r64/α128 (1–3), r32/α64 (4); paged AdamW 8-bit; micro-batch 16 + gradient checkpointing. Each stage's loss signature differs because each is learning something different (Stage 3's steep drop = function calling is highly learnable; Stage 4's flat curve = a gentle, broad nudge). 10% replay kept Stage-1 reasoning stable through Stages 2–4 (no catastrophic forgetting).

Datasets (all open)

Reasoning: OpenMathReasoning, OpenCodeReasoning, OpenThoughts3
Agentic: Nemotron-Post-Training-v2 (chat), APIGen-MT
Tools: ToolACE, xLAM-60k (⚠️ CC-BY-NC)
Instruction: Tülu-3, OpenHermes-2.5, No-Robots

Evaluation methodology & pitfalls

Three eval bugs nearly produced wrong numbers — documented so others can avoid them:

--apply_chat_template tanked MMLU to ~0.26 (random) on multiple-choice loglikelihood. Fix: no chat template for MC tasks → MMLU 0.74.
Generation cap truncated <think> (default 256 tokens) → low GSM8K. Fix: raised to 2048.
Tool calls are XML-style (<function=...><parameter=...>), not JSON — a JSON parser scored 0 real calls. Fix: parse the XML form.

Still TODO (where a reasoning/tool curriculum should pull ahead): standardized GSM8K-generative, MATH/AIME, full BFCL, τ-bench. Single run; no replay/order ablation yet.

Intended use & limitations

Research / non-commercial use (Stage 3 includes CC-BY-NC xLAM; also a Qwen3.5 derivative). Reasoning, planning, and function calling for a small, locally-runnable model. Can hallucinate; verify tool arguments before executing. Inherits base-model biases.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
mid = "sahilchachra/Tessera-4B-Preview"
tok = AutoTokenizer.from_pretrained(mid)
model = AutoModelForCausalLM.from_pretrained(mid, torch_dtype=torch.bfloat16, device_map="auto")
msgs = [{"role":"user","content":"A train travels 60 km in 45 min. Speed in km/h?"}]
ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to(model.device)
print(tok.decode(model.generate(ids, max_new_tokens=1024)[0][ids.shape[1]:], skip_special_tokens=True))
# May emit a <think>…</think> block before the answer.

Acknowledgements

Built on Qwen3.5-4B (Alibaba Qwen). Data: NVIDIA (OpenMath/OpenCode Reasoning, Nemotron), Open Thoughts, Salesforce (xLAM, APIGen-MT), Team-ACE (ToolACE), Allen AI (Tülu-3), Teknium (OpenHermes), HuggingFace H4 (No-Robots). Tooling: Unsloth, TRL, PEFT, bitsandbytes, lm-evaluation-harness.