Update README.md

README.md

@@ -1,170 +1,29 @@
 ---
 tags:
-  - bittensor
-  - subnet-20
-  - agent
-  - function-calling
-  - generated_from_trainer
+- bittensor
+- subnet-20
+- agent
+- function-calling
+- json-output
+- mistral
+- conversational
 license: mit
-datasets:
-  - HuggingFaceH4/ultrachat_200k
-  - HuggingFaceH4/ultrafeedback_binarized
 language:
-  - en
+- en
 base_model: mistralai/Mistral-7B-v0.1
+datasets:
+- HuggingFaceH4/ultrachat_200k
+- HuggingFaceH4/ultrafeedback_binarized
 pipeline_tag: text-generation
-widget:
-  - example_title: Pirate!
-    messages:
-      - role: system
-        content: You are a pirate chatbot who always responds with Arr!
-      - role: user
-        content: There's a llama on my lawn, how can I get rid of him?
-    output:
-      text: >-
-        Arr! 'Tis a puzzlin' matter, me hearty! A llama on yer lawn be a rare
-        sight, but I've got a plan that might help ye get rid of 'im. Ye'll need
-        to gather some carrots and hay, and then lure the llama away with the
-        promise of a tasty treat. Once he's gone, ye can clean up yer lawn and
-        enjoy the peace and quiet once again. But beware, me hearty, for there
-        may be more llamas where that one came from! Arr!
-model-index:
-  - name: zephyr-7b-beta
-    results:
-      - task:
-          type: text-generation
-          name: Text Generation
-        dataset:
-          name: AI2 Reasoning Challenge (25-Shot)
-          type: ai2_arc
-          config: ARC-Challenge
-          split: test
-          args:
-            num_few_shot: 25
-        metrics:
-          - type: acc_norm
-            name: normalized accuracy
-            value: 62.03
-      - task:
-          type: text-generation
-          name: Text Generation
-        dataset:
-          name: HellaSwag (10-Shot)
-          type: hellaswag
-          split: validation
-          args:
-            num_few_shot: 10
-        metrics:
-          - type: acc_norm
-            name: normalized accuracy
-            value: 84.36
-      - task:
-          type: text-generation
-          name: Text Generation
-        dataset:
-          name: Drop (3-Shot)
-          type: drop
-          split: validation
-          args:
-            num_few_shot: 3
-        metrics:
-          - type: f1
-            name: f1 score
-            value: 9.66
-      - task:
-          type: text-generation
-          name: Text Generation
-        dataset:
-          name: TruthfulQA (0-shot)
-          type: truthful_qa
-          config: multiple_choice
-          split: validation
-          args:
-            num_few_shot: 0
-        metrics:
-          - type: mc2
-            value: 57.45
-      - task:
-          type: text-generation
-          name: Text Generation
-        dataset:
-          name: GSM8k (5-shot)
-          type: gsm8k
-          config: main
-          split: test
-          args:
-            num_few_shot: 5
-        metrics:
-          - type: acc
-            name: accuracy
-            value: 12.74
-      - task:
-          type: text-generation
-          name: Text Generation
-        dataset:
-          name: MMLU (5-Shot)
-          type: cais/mmlu
-          config: all
-          split: test
-          args:
-            num_few_shot: 5
-        metrics:
-          - type: acc
-            name: accuracy
-            value: 61.07
-      - task:
-          type: text-generation
-          name: Text Generation
-        dataset:
-          name: Winogrande (5-shot)
-          type: winogrande
-          config: winogrande_xl
-          split: validation
-          args:
-            num_few_shot: 5
-        metrics:
-          - type: acc
-            name: accuracy
-            value: 77.74
-      - task:
-          type: text-generation
-          name: Text Generation
-        dataset:
-          name: AlpacaEval
-          type: tatsu-lab/alpaca_eval
-        metrics:
-          - type: unknown
-            name: win rate
-            value: 0.906
-      - task:
-          type: text-generation
-          name: Text Generation
-        dataset:
-          name: MT-Bench
-          type: unknown
-        metrics:
-          - type: unknown
-            name: score
-            value: 7.34
 ---
 
-# Zephyr-7B-Beta (Fine-tuned for Subnet 20 BitAgent)
-
-This is a fine-tuned version of **Mistral-7B** adapted for **function-calling and reasoning tasks** in **Bittensor Subnet 20 (BitAgent)**.
-
-## 🧠 Use Case
-- Works as an **agent LLM** inside the BitAgent subnet.
-- Supports **reasoning** and **function-calling outputs**.
-- Optimized for **task delegation and structured outputs**.
-
-## 🚀 How to Use
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
+# lia21/bitagent — Zephyr-7B for **Bittensor Subnet 20 (BitAgent)**
 
-model = AutoModelForCausalLM.from_pretrained("username/zephyr-7b-beta-bitagent")
-tokenizer = AutoTokenizer.from_pretrained("username/zephyr-7b-beta-bitagent")
+Fine-tuned version of **Mistral-7B** adapted for **function-calling** and **structured reasoning** inside **Subnet 20 (BitAgent)**.  
+The model is optimized to produce **valid JSON outputs** of the form:
 
-prompt = "Summarize the latest research in AI safety in 3 bullet points."
-inputs = tokenizer(prompt, return_tensors="pt")
-outputs = model.generate(**inputs, max_new_tokens=200)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```json
+{
+  "name": "<function_name>",
+  "arguments": { "...": "..." }
+}