Text Generation
Transformers
Safetensors
qwen3
cooking
recipes
dpo
provenance
abstention
conversational
text-generation-inference
Instructions to use HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant") model = AutoModelForCausalLM.from_pretrained("HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant", 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant
- SGLang
How to use HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant 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 "HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant" \ --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": "HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant", "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 "HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant" \ --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": "HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant with Docker Model Runner:
docker model run hf.co/HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant
card: eval set link, Label Test invitation, build section trimmed
Browse files
README.md
CHANGED
|
@@ -6,7 +6,7 @@ library_name: transformers
|
|
| 6 |
pipeline_tag: text-generation
|
| 7 |
language: [en, es, pt, it, fr, nl, de, ru, bn, id, fa, ja, pl, sv, vi, tl, he, ml, tr, zh, ms, th, fi, ar, ta, hi]
|
| 8 |
tags: [cooking, recipes, lora, dpo, qwen3, provenance, abstention]
|
| 9 |
-
datasets: [HumanjavaEnterprises/cooking-
|
| 10 |
---
|
| 11 |
|
| 12 |
# Qwen3-8B Cooking v8
|
|
@@ -155,18 +155,17 @@ model did not: all were deflections or explicit rebuttals, none complied.
|
|
| 155 |
|
| 156 |
## How it was built
|
| 157 |
|
| 158 |
-
|
|
| 159 |
|---|---|
|
| 160 |
-
| Sources |
|
| 161 |
-
| Excluded | Traditional and Indigenous knowledge, sacred material, outsider-authored books about other cultures, dog-meat recipes,
|
| 162 |
-
|
|
| 163 |
-
|
|
| 164 |
-
|
|
| 165 |
-
| Tooling | LLaMA-Factory 0.9.5, vLLM, llama.cpp |
|
| 166 |
|
| 167 |
-
The
|
| 168 |
-
|
| 169 |
-
|
| 170 |
|
| 171 |
## What went wrong along the way
|
| 172 |
|
|
@@ -185,9 +184,11 @@ The general chat data is not republished (it is third-party).
|
|
| 185 |
wrong; check official sources.
|
| 186 |
- **It does not know historical recipes by heart.** It was trained on old cookbooks to read and reason about recipes,
|
| 187 |
not to recall them. For a specific historical dish, give it the text.
|
| 188 |
-
- The judges are models. Four open judges from four families agree on the direction and size of the
|
| 189 |
-
|
| 190 |
-
|
|
|
|
|
|
|
| 191 |
- Strongest in English and Spanish; Thai, Tamil and Hindi had under 200 source records each.
|
| 192 |
- The old public-domain cookbooks reflect their era: measures, techniques, some outdated advice.
|
| 193 |
|
|
|
|
| 6 |
pipeline_tag: text-generation
|
| 7 |
language: [en, es, pt, it, fr, nl, de, ru, bn, id, fa, ja, pl, sv, vi, tl, he, ml, tr, zh, ms, th, fi, ar, ta, hi]
|
| 8 |
tags: [cooking, recipes, lora, dpo, qwen3, provenance, abstention]
|
| 9 |
+
datasets: [HumanjavaEnterprises/cooking-eval-v8]
|
| 10 |
---
|
| 11 |
|
| 12 |
# Qwen3-8B Cooking v8
|
|
|
|
| 155 |
|
| 156 |
## How it was built
|
| 157 |
|
| 158 |
+
| | |
|
| 159 |
|---|---|
|
| 160 |
+
| Sources | Cooking texts in 26 languages from openly licensed and public-domain sources only: the Wikibooks Cookbook (CC BY-SA 4.0), public-domain cookbooks from Project Gutenberg and the Internet Archive (scans re-read with olmOCR-2), and NHLBI recipes (US government, public domain). Every record carries its source URL, licence and public-domain basis. About a quarter of the training records are English |
|
| 161 |
+
| Excluded | Traditional and Indigenous knowledge, sacred material, outsider-authored books about other cultures, dog-meat recipes, anything without a verified licence |
|
| 162 |
+
| Models used | Open-weights models only, all Apache-2.0 or MIT. **No output from any closed or API model is in the training, evaluation or seed data** |
|
| 163 |
+
| Training | Two LoRA stages on Qwen3-8B, each merged: a supervised stage that teaches reading a shown recipe, asking when there is none, and full general answers; then a preference stage that favours asking over inventing and correct over wrong. General chat data is mixed in to limit forgetting |
|
| 164 |
+
| Tooling | LLaMA-Factory, vLLM, llama.cpp |
|
|
|
|
| 165 |
|
| 166 |
+
The evaluation set behind every number on this card (all 682 questions, both models' answers, every judge's verdict,
|
| 167 |
+
and per-row source credits) is published so the results can be checked:
|
| 168 |
+
[HumanjavaEnterprises/cooking-eval-v8](https://huggingface.co/datasets/HumanjavaEnterprises/cooking-eval-v8).
|
| 169 |
|
| 170 |
## What went wrong along the way
|
| 171 |
|
|
|
|
| 184 |
wrong; check official sources.
|
| 185 |
- **It does not know historical recipes by heart.** It was trained on old cookbooks to read and reason about recipes,
|
| 186 |
not to recall them. For a specific historical dish, give it the text.
|
| 187 |
+
- The judges are models. Four open judges from four families agree on the direction and size of the changes, and
|
| 188 |
+
we keep checking them against people with Label Test, our blind labelling tool. **Help refine it:** label five
|
| 189 |
+
answers at [label-test.humanjava.com](https://label-test.humanjava.com/?s=cook4&k=cook-9ac741a1e387) (no account; we keep only a name or initials and your labels).
|
| 190 |
+
- Still invents on some no-recipe questions: about 1 in 40 when three of four judges must agree, about 1 in 16 by the
|
| 191 |
+
strictest single judge. Most remaining cases are borderline hedges (a common default offered with a caveat).
|
| 192 |
- Strongest in English and Spanish; Thai, Tamil and Hindi had under 200 source records each.
|
| 193 |
- The old public-domain cookbooks reflect their era: measures, techniques, some outdated advice.
|
| 194 |
|