Instructions to use bactrianus/HotpotQA-Reader-CoT-Llama-3-8B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bactrianus/HotpotQA-Reader-CoT-Llama-3-8B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="bactrianus/HotpotQA-Reader-CoT-Llama-3-8B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bactrianus/HotpotQA-Reader-CoT-Llama-3-8B-Instruct")
model = AutoModelForCausalLM.from_pretrained("bactrianus/HotpotQA-Reader-CoT-Llama-3-8B-Instruct", 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 bactrianus/HotpotQA-Reader-CoT-Llama-3-8B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bactrianus/HotpotQA-Reader-CoT-Llama-3-8B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bactrianus/HotpotQA-Reader-CoT-Llama-3-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bactrianus/HotpotQA-Reader-CoT-Llama-3-8B-Instruct

SGLang

How to use bactrianus/HotpotQA-Reader-CoT-Llama-3-8B-Instruct 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 "bactrianus/HotpotQA-Reader-CoT-Llama-3-8B-Instruct" \
    --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": "bactrianus/HotpotQA-Reader-CoT-Llama-3-8B-Instruct",
		"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 "bactrianus/HotpotQA-Reader-CoT-Llama-3-8B-Instruct" \
        --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": "bactrianus/HotpotQA-Reader-CoT-Llama-3-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bactrianus/HotpotQA-Reader-CoT-Llama-3-8B-Instruct with Docker Model Runner:
```
docker model run hf.co/bactrianus/HotpotQA-Reader-CoT-Llama-3-8B-Instruct
```

Bactrainus HotpotQA Rationale Reader — Llama 3 8B Instruct

Artifact identity

Status: complete merged causal-language-model checkpoint
Base model: meta-llama/Meta-Llama-3-8B-Instruct
Audited Hub revision: 852277e5b9534ff51a66adbad1ad43b7a3ef4457
Public artifact date: August 2024
Role: rationale-plus-answer generation from supplied evidence

This is a historical Llama 3 artifact. It must not be represented as either revised Llama 3.1 rationale-reader variant described in the updated manuscript.

Model summary

This reader is adapted to generate an intermediate natural-language rationale followed by an answer. The rationale is process supervision generated for task adaptation; it is not a hidden trace recovered from the base model and is not a gold supporting-fact annotation.

Intended use

Studying natural-language rationale supervision for HotpotQA readers.
Qualitative inspection of an evidence-conditioned answer path.
Reader-stage comparisons where evidence is supplied independently.

Out-of-scope use

Treating generated rationales as faithful explanations or verified proofs.
Using rationale text as a substitute for HotpotQA supporting-fact labels.
Open-domain retrieval, safety-critical decisions, or factual verification.
Associating revised Llama 3.1 rationale results with this legacy checkpoint.

Input and output contract

Input should contain a question and selected, title-preserving evidence. Output is expected to contain rationale text and a final answer. Downstream code must parse the final answer explicitly and must keep rationale evaluation separate from answer/evidence metrics.

The public legacy configuration does not preserve a complete prompt-version manifest or an independently verified rationale delimiter. Do not assume that a newly invented delimiter exactly matches historical training.

Loading

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

MODEL_ID = "bactrianus/HotpotQA-Reader-CoT-Llama-3-8B-Instruct"
REVISION = "852277e5b9534ff51a66adbad1ad43b7a3ef4457"

tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, revision=REVISION)
model = AutoModelForCausalLM.from_pretrained(
    MODEL_ID,
    revision=REVISION,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
model.eval()

Training data and lineage

The checkpoint derives from Meta Llama 3 8B Instruct and HotpotQA-based reader/rationale supervision. Two separately versioned dataset resources are relevant to this task:

cot-reader-sft in the canonical dataset at v1.0.0 is a complete deterministic view with 90,447 unique training source IDs. Its assistant targets serialize indexed gold evidence followed by the reference answer; they are not model-generated rationales.
teacher-cot-llama31-8b-sft in the teacher-trace dataset at v1.0.0 contains one resolved Llama 3.1 8B-labelled rationale per source ID for 71,238 training examples.
teacher-cot-llama31-70b-sft in the teacher-trace dataset at v1.0.0 contains 28,176 recovered Llama 3.1 70B-labelled records: all 15,661 hard examples and 12,515 medium examples. Each row includes the archived annotation and an SFT conversation joined to the canonical dataset through source_id.

from datasets import load_dataset

deterministic_train = load_dataset(
    "bactrianus/bactrainus-hotpotqa",
    "cot-reader-sft",
    split="train",
    revision="v1.0.0",
)

teacher_8b_train = load_dataset(
    "bactrianus/bactrainus-hotpotqa-teacher-traces",
    "teacher-cot-llama31-8b-sft",
    split="train",
    revision="v1.0.0",
)

teacher_70b_train = load_dataset(
    "bactrianus/bactrainus-hotpotqa-teacher-traces",
    "teacher-cot-llama31-70b-sft",
    split="train",
    revision="v1.0.0",
)

These resources document the current dataset release; neither is asserted to be byte-identical to the historical training serialization for this legacy Llama 3 checkpoint. The teacher configuration's Llama 3.1 label describes its archived generator record and must not be used to relabel these Llama 3 weights or infer an unrecorded training dependency.

Likewise, the revised reader_8b_rationale_8b.yaml and reader_8b_rationale_70b.yaml files describe Llama 3.1 experiments, not this Llama 3 weight artifact.

Evaluation boundary

No predictions or evaluation results are bundled with this card. The Bactrainus paper reports rationale-supervision experiments with explicit recipe caveats. A correct final answer does not establish rationale faithfulness.

Limitations

Generated rationales can be post-hoc, incomplete, contradictory, or unsupported.
Longer outputs increase parsing and truncation risk.
Evidence omissions propagate to both rationale and answer.
The model is specialized for English HotpotQA-style inputs.
Wikipedia-derived data carries temporal and representational biases.
Historical prompt, generator, and environment details are incomplete.

License and attribution

The weights remain subject to the Meta Llama 3 Community License and Acceptable Use Policy.

Meta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright Meta Platforms, Inc. All Rights Reserved.

Built with Meta Llama 3.

HotpotQA-derived data is licensed under CC BY-SA 4.0. Bactrainus code is Apache-2.0 licensed.

Citation

@article{barati2025bactrainus,
  title   = {Bactrainus: Optimizing Large Language Models for Multi-hop Complex Question Answering Tasks},
  author  = {Barati, Iman and Ghafouri, Arash and Minaei-Bidgoli, Behrouz},
  journal = {arXiv preprint arXiv:2501.06286},
  year    = {2025},
  doi     = {10.48550/arXiv.2501.06286},
  url     = {https://arxiv.org/abs/2501.06286}
}

Downloads last month: 462

Safetensors

Model size

8B params

Tensor type

BF16

F16

Model tree for bactrianus/HotpotQA-Reader-CoT-Llama-3-8B-Instruct

Base model

meta-llama/Meta-Llama-3-8B-Instruct

Finetuned

(1087)

this model

Datasets used to train bactrianus/HotpotQA-Reader-CoT-Llama-3-8B-Instruct

Paper for bactrianus/HotpotQA-Reader-CoT-Llama-3-8B-Instruct

Bactrainus: Optimizing Large Language Models for Multi-hop Complex Question Answering Tasks

Paper • 2501.06286 • Published Jan 10, 2025 • 1