Instructions to use EricSpencer00/chattla-v2-sft2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EricSpencer00/chattla-v2-sft2 with Transformers:

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

pipe = pipeline("text-generation", model="EricSpencer00/chattla-v2-sft2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EricSpencer00/chattla-v2-sft2")
model = AutoModelForCausalLM.from_pretrained("EricSpencer00/chattla-v2-sft2", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use EricSpencer00/chattla-v2-sft2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EricSpencer00/chattla-v2-sft2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EricSpencer00/chattla-v2-sft2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/EricSpencer00/chattla-v2-sft2

SGLang

How to use EricSpencer00/chattla-v2-sft2 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 "EricSpencer00/chattla-v2-sft2" \
    --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": "EricSpencer00/chattla-v2-sft2",
		"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 "EricSpencer00/chattla-v2-sft2" \
        --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": "EricSpencer00/chattla-v2-sft2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use EricSpencer00/chattla-v2-sft2 with Docker Model Runner:
```
docker model run hf.co/EricSpencer00/chattla-v2-sft2
```

ChatTLA v2-sft2 — first verifier-gated RFT checkpoint with holdout passes

gpt-oss-20b fine-tuned on 260 verifier-certified TLA+ generation pairs (chattla-rft-corpora-v2) — every training example survived a hard-metric gate chain (SANY, TLC model-check, non-vacuity, mutation battery, decontamination; zero LLM-judge scoring). Targets are rendered through the gpt-oss harmony template with final-channel targets (plain-text SFT provably breaks gpt-oss channel discipline — that was this project's v2_sft1 lesson).

Training: experts-reaching LoRA (r=8, α=16; q/k/v/o_proj + target_parameters on mlp.experts.gate_up_proj/down_proj, MXFP4 dequantized to bf16), FSDP2, 4 epochs on 260 pairs, loss 2.67→0.52. This is a full merged bf16 model (verified: all 48 expert tensors present).

Honest evaluation (directional, NOT the project's frozen Gate-2 budget): NL→spec generation on a frozen 30-spec holdout, temp 0.8, TLC-verified:

pass@4 = 2/30 (specs that base gpt-oss-20b never passes even at pass@32)
base gpt-oss-20b comparison: pass@1 0/30, pass@32 4/30 (disjoint spec set → capability shift, not sampling luck)
Known limits: 20B (the project's target is 120B), k=4 vs the frozen k=32 budget; ~23% of samples still fail module extraction.

Part of the prove-TLA project: a verify-until-correct loop (SANY → TLC → non-vacuity → repair) provides a structural correctness guarantee; the model's job is only to make the loop converge. This checkpoint is the first evidence that training on the loop's own survivors transfers capability.

Downloads last month: 396

Safetensors

Model size

21B params

Tensor type

BF16

Model tree for EricSpencer00/chattla-v2-sft2

Base model

openai/gpt-oss-20b

Finetuned

(546)

this model

EricSpencer00
/

chattla-v2-sft2

ChatTLA v2-sft2 — first verifier-gated RFT checkpoint with holdout passes

Model tree for EricSpencer00/chattla-v2-sft2

Dataset used to train EricSpencer00/chattla-v2-sft2