Vveerrgg commited on
Commit
c0ea23d
·
verified ·
1 Parent(s): 6535376

cards: behaviour + proof first, non-affiliation line, Q4_K_M default for 6 GB, no lora tag

Browse files
Files changed (1) hide show
  1. README.md +10 -5
README.md CHANGED
@@ -5,18 +5,23 @@ base_model_relation: finetune
5
  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-assistant-eval]
10
  ---
11
 
12
  # Qwen3-8B Cooking Assistant
13
 
14
- A multilingual cooking assistant fine-tuned from Qwen3-8B on public-domain and openly licensed cookbooks, as
15
- full-precision (bf16) safetensors for Transformers and vLLM. For llama.cpp, Ollama and LM Studio:
 
 
 
 
 
 
16
  [HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant-GGUF](https://huggingface.co/HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant-GGUF).
17
 
18
- It answers from the recipe you give it, asks for the recipe when an answer depends on one it cannot see, and gives
19
- full answers to general cooking questions. It does not memorise recipes: give it the recipe (paste it, or have your
20
  app look it up) and it will read it.
21
 
22
  ## Files
 
5
  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, dpo, qwen3, provenance, abstention]
9
  datasets: [HumanjavaEnterprises/cooking-assistant-eval]
10
  ---
11
 
12
  # Qwen3-8B Cooking Assistant
13
 
14
+ A cooking assistant that reads the recipe you give it, and asks for the recipe instead of inventing details when it
15
+ can't see one. On questions that need a recipe it wasn't shown, it invents details 2.7% of the time vs 25.8% for base
16
+ Qwen3-8B; given the recipe, it answers correctly 94.8% of the time vs 83.1% (four open judges, 3 of 4 agreeing). General
17
+ cooking answers are level with the base. 26 languages; runs on a 6 GB GPU (Q4_K_M).
18
+
19
+ *Unofficial fine-tune of Qwen3-8B by Humanjava Enterprises; not made or endorsed by Alibaba Cloud or the Qwen team.*
20
+
21
+ Full-precision (bf16) safetensors for Transformers and vLLM. For llama.cpp, Ollama and LM Studio:
22
  [HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant-GGUF](https://huggingface.co/HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant-GGUF).
23
 
24
+ It does not memorise recipes: give it the recipe (paste it, or have your
 
25
  app look it up) and it will read it.
26
 
27
  ## Files