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: recipe-only numbers throughout
Browse files
README.md
CHANGED
|
@@ -72,8 +72,9 @@ only, every training record traceable to its source, and the checks published al
|
|
| 72 |
|
| 73 |
## Results
|
| 74 |
|
| 75 |
-
All cooking scores are on a fixed held-out set of 682 questions
|
| 76 |
-
|
|
|
|
| 77 |
(thinking off) and this model are compared by an open-weights judge from a different model family
|
| 78 |
(DeepSeek-V4-Flash, MIT licence), blind, in both orders. 95% confidence intervals in brackets.
|
| 79 |
|
|
@@ -81,7 +82,7 @@ the model is not shown, 82 general questions), in 26 languages, never used in tr
|
|
| 81 |
|---|---|---|
|
| 82 |
| **Invents recipe details when no recipe is shown** | 30.0% [25.1, 35.4] | **9.0%** [6.3, 12.8] |
|
| 83 |
| same, after a rule check that removes judge false alarms | 27.7% | **4.0%** [2.3, 6.9] |
|
| 84 |
-
| **Correct when the recipe is shown** |
|
| 85 |
| Preferred by the judge, all 682 questions | — | **0.610** [0.581, 0.639] (0.50 = tie) |
|
| 86 |
| Preferred by the judge, general questions only | — | 0.460 [0.369, 0.549] (level with base) |
|
| 87 |
|
|
@@ -118,7 +119,7 @@ itself, or a common default ("a pinch of salt") offered with a hedge.
|
|
| 118 |
| | Q4_K_M | Q6_K | Q8_0 |
|
| 119 |
|---|---|---|---|
|
| 120 |
| Judge preference vs full precision | 0.492 [0.475, 0.509] | 0.501 [0.485, 0.517] | 0.481 [0.466, 0.494] |
|
| 121 |
-
| Correct when the recipe is shown |
|
| 122 |
| Invents with no recipe (full precision on that run) | 9.3% (7.3%) | 6.3% (6.3%) | 6.7% (6.7%) |
|
| 123 |
| Invents with no recipe, 3 of 4 judges (full precision) | 4.7% (3.3%) | 3.0% (3.3%) | 3.3% (2.7%) |
|
| 124 |
| Correct when the recipe is shown, 3 of 4 judges (full precision) | 95.5% (94.1%) | 95.5% (94.1%) | 95.2% (94.8%) |
|
|
@@ -127,7 +128,7 @@ With all four judges, no quantised file differs significantly from full precisio
|
|
| 127 |
Q4_K_M p = 0.34, Q6_K p = 1.0, Q8_0 p = 0.69 for inventing; p ≥ 0.22 for correctness with the recipe shown). On Q4_K_M two of the four judges on their own
|
| 128 |
(GLM-4.7-Flash, gpt-oss-120b) do see slightly more invented details (p = 0.02 and 0.04); pick Q6_K or Q8_0 if that matters.
|
| 129 |
|
| 130 |
-
|
| 131 |
general questions (0.418) and is most likely judge noise on a small set; Q4_K_M and Q6_K, which remove more bits,
|
| 132 |
sit at parity.
|
| 133 |
|
|
|
|
| 72 |
|
| 73 |
## Results
|
| 74 |
|
| 75 |
+
All cooking scores are on a fixed held-out set of 682 questions in 26 languages, never used in training: 290 with the
|
| 76 |
+
recipe shown, 10 recall questions with no recipe ("how do you make X?"), 300 that need a recipe the model is not shown,
|
| 77 |
+
and 82 general questions. Answers from base Qwen3-8B
|
| 78 |
(thinking off) and this model are compared by an open-weights judge from a different model family
|
| 79 |
(DeepSeek-V4-Flash, MIT licence), blind, in both orders. 95% confidence intervals in brackets.
|
| 80 |
|
|
|
|
| 82 |
|---|---|---|
|
| 83 |
| **Invents recipe details when no recipe is shown** | 30.0% [25.1, 35.4] | **9.0%** [6.3, 12.8] |
|
| 84 |
| same, after a rule check that removes judge false alarms | 27.7% | **4.0%** [2.3, 6.9] |
|
| 85 |
+
| **Correct when the recipe is shown** (290 questions) | 87.6% | **96.2%** |
|
| 86 |
| Preferred by the judge, all 682 questions | — | **0.610** [0.581, 0.639] (0.50 = tie) |
|
| 87 |
| Preferred by the judge, general questions only | — | 0.460 [0.369, 0.549] (level with base) |
|
| 88 |
|
|
|
|
| 119 |
| | Q4_K_M | Q6_K | Q8_0 |
|
| 120 |
|---|---|---|---|
|
| 121 |
| Judge preference vs full precision | 0.492 [0.475, 0.509] | 0.501 [0.485, 0.517] | 0.481 [0.466, 0.494] |
|
| 122 |
+
| Correct when the recipe is shown, 290 questions (full precision on that run) | 97.2% (96.6%) | 96.6% (96.2%) | 96.9% (96.2%) |
|
| 123 |
| Invents with no recipe (full precision on that run) | 9.3% (7.3%) | 6.3% (6.3%) | 6.7% (6.7%) |
|
| 124 |
| Invents with no recipe, 3 of 4 judges (full precision) | 4.7% (3.3%) | 3.0% (3.3%) | 3.3% (2.7%) |
|
| 125 |
| Correct when the recipe is shown, 3 of 4 judges (full precision) | 95.5% (94.1%) | 95.5% (94.1%) | 95.2% (94.8%) |
|
|
|
|
| 128 |
Q4_K_M p = 0.34, Q6_K p = 1.0, Q8_0 p = 0.69 for inventing; p ≥ 0.22 for correctness with the recipe shown). On Q4_K_M two of the four judges on their own
|
| 129 |
(GLM-4.7-Flash, gpt-oss-120b) do see slightly more invented details (p = 0.02 and 0.04); pick Q6_K or Q8_0 if that matters.
|
| 130 |
|
| 131 |
+
With the DeepSeek judge alone, no quantisation changes the invents rate significantly (McNemar p ≥ 0.29). Q8_0's small dip comes from the 82
|
| 132 |
general questions (0.418) and is most likely judge noise on a small set; Q4_K_M and Q6_K, which remove more bits,
|
| 133 |
sit at parity.
|
| 134 |
|