Upload Qwen2ForCausalLM

README.md

@@ -33,83 +33,72 @@ inference:
     max_new_tokens: 256
     top_p: 0.9
   widget:
-    - text: "Send an email to Beer with the subject 'Status update' and body 'The model is running well.'"
-      output:
-        text: "<tool_call>{'name': 'send_email', 'arguments': {'to': 'Beer', 'subject': 'Status update', 'body': 'The model is running well.'}}"
-    - text: "What's the weather in Bangkok?"
-      output:
-        text: "<tool_call>{'name': 'get_weather', 'arguments': {'location': 'Bangkok'}}"
-model-index:
-  - name: sakthai-plus-1.5b
-    results:
-      - task:
-          type: text-generation
-          name: Tool-Calling Accuracy
-        dataset:
-          type: custom
-          name: llama.cpp tool-calling (3-trial, q4_k_m)
-        metrics:
-          - type: tool_call_success
-            value: 1.0
-            name: Tool Call Success Rate
-            verified: true
-          - type: valid-json
-            value: 1.0
-            name: Valid JSON Arguments
-            verified: true
-          - type: correct-answer
-            value: 1.0
-            name: Correct Answer Rate
-            verified: true
-      - task:
-          type: text-generation
-          name: SakThai Bench v2 — Tool Selection
-        dataset:
-          type: custom
-          name: sakthai-bench-v2
-        metrics:
-          - type: selection-accuracy
-            value: 84.8
-            name: Selection Accuracy
-            verified: false
-          - type: arguments-accuracy
-            value: 33.7
-            name: Arguments Accuracy
-            verified: false
-          - type: strict-accuracy
-            value: 33.7
-            name: Strict Accuracy
-            verified: false
-      - task:
-          type: text-generation
-          name: Commonsense Reasoning
-        dataset:
-          type: lighteval
-          name: lighteval
-        metrics:
-          - type: winogrande
-            value: 59.6
-            name: WinoGrande (WSC)
-            verified: false
-          - type: hellaswag
-            value: 34.0
-            name: HellaSwag
-            verified: false
-      - task:
-          type: text-generation
-          name: Math Reasoning
-        dataset:
-          type: lighteval
-          name: lighteval
-        metrics:
-          - type: gsm8k
-            value: 50.9
-            name: GSM8K
-            verified: false
+  - text: Send an email to Beer with the subject 'Status update' and body 'The model
+      is running well.'
+    output:
+      text: '<tool_call>{''name'': ''send_email'', ''arguments'': {''to'': ''Beer'',
+        ''subject'': ''Status update'', ''body'': ''The model is running well.''}}'
+  - text: What's the weather in Bangkok?
+    output:
+      text: '<tool_call>{''name'': ''get_weather'', ''arguments'': {''location'':
+        ''Bangkok''}}'
 extra:
   downloads: 297
   likes: 0
   last_modified: 2026-08-01 07:31:41+00:00
+model-index:
+- name: sakthai-plus-1.5b
+  results:
+  - task:
+      type: text-generation
+      name: Tool-Calling Accuracy
+    dataset:
+      name: llama.cpp tool-calling (3-trial, q4_k_m)
+      type: custom
+    metrics:
+    - type: tool_call_success
+      value: 1.0
+      name: Tool Call Success Rate
+      verified: true
+    - type: valid-json
+      value: 1.0
+      name: Valid JSON Arguments
+      verified: true
+    - type: correct-answer
+      value: 1.0
+      name: Correct Answer Rate
+      verified: true
+    - type: selection-accuracy
+      value: 84.8
+      name: Selection Accuracy
+      verified: false
+    - type: arguments-accuracy
+      value: 33.7
+      name: Arguments Accuracy
+      verified: false
+    - type: strict-accuracy
+      value: 33.7
+      name: Strict Accuracy
+      verified: false
+  - task:
+      type: text-generation
+      name: Commonsense Reasoning
+    dataset:
+      name: lighteval
+      type: lighteval
+    metrics:
+    - type: winogrande
+      value: 59.6
+      name: WinoGrande (WSC)
+      verified: false
+    - type: hellaswag
+      value: 34.0
+      name: HellaSwag
+      verified: false
+    - type: gsm8k
+      value: 50.9
+      name: GSM8K
+      verified: false
 ---
 
 <p align="center">

config.json

@@ -4,7 +4,7 @@
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
-  "dtype": "bfloat16",
+  "dtype": "float16",
   "eos_token_id": 151645,
   "hidden_act": "silu",
   "hidden_size": 1536,
@@ -46,15 +46,12 @@
   "num_attention_heads": 12,
   "num_hidden_layers": 28,
   "num_key_value_heads": 2,
-  "pad_token_id": null,
   "rms_norm_eps": 1e-06,
-  "rope_parameters": {
-    "rope_theta": 1000000.0,
-    "rope_type": "default"
-  },
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
   "sliding_window": null,
   "tie_word_embeddings": true,
-  "transformers_version": "5.14.1",
+  "transformers_version": "4.57.6",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936

generation_config.json

@@ -10,5 +10,5 @@
   "temperature": 0.7,
   "top_k": 20,
   "top_p": 0.8,
-  "transformers_version": "5.14.1"
+  "transformers_version": "4.57.6"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cc67cb8fa13f45800fd4fb97beb4b4def012b9075ff4c33a2e3a87ff674bbef
-size 3087467144
+oid sha256:a420583b0ad672a239a905b49d3e208e031104c486c43c31a892ac1f6399b639
+size 3087466808