099fe363c7613cde44d35c6c177863f3fb828105759891585bcd174d024d1232

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -25,101 +25,6 @@ datasets:
 - sequelbox/Tachibana
 - sequelbox/Supernova
 model_type: llama
-model-index:
-- name: Llama3.1-8B-Enigma
-  results:
-  - task:
-      type: text-generation
-      name: Text Generation
-    dataset:
-      name: IFEval (0-Shot)
-      type: HuggingFaceH4/ifeval
-      args:
-        num_few_shot: 0
-    metrics:
-    - type: inst_level_strict_acc and prompt_level_strict_acc
-      value: 55.39
-      name: strict accuracy
-    source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Enigma
-      name: Open LLM Leaderboard
-  - task:
-      type: text-generation
-      name: Text Generation
-    dataset:
-      name: BBH (3-Shot)
-      type: BBH
-      args:
-        num_few_shot: 3
-    metrics:
-    - type: acc_norm
-      value: 28.47
-      name: normalized accuracy
-    source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Enigma
-      name: Open LLM Leaderboard
-  - task:
-      type: text-generation
-      name: Text Generation
-    dataset:
-      name: MATH Lvl 5 (4-Shot)
-      type: hendrycks/competition_math
-      args:
-        num_few_shot: 4
-    metrics:
-    - type: exact_match
-      value: 10.12
-      name: exact match
-    source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Enigma
-      name: Open LLM Leaderboard
-  - task:
-      type: text-generation
-      name: Text Generation
-    dataset:
-      name: GPQA (0-shot)
-      type: Idavidrein/gpqa
-      args:
-        num_few_shot: 0
-    metrics:
-    - type: acc_norm
-      value: 1.57
-      name: acc_norm
-    source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Enigma
-      name: Open LLM Leaderboard
-  - task:
-      type: text-generation
-      name: Text Generation
-    dataset:
-      name: MuSR (0-shot)
-      type: TAUR-Lab/MuSR
-      args:
-        num_few_shot: 0
-    metrics:
-    - type: acc_norm
-      value: 11.41
-      name: acc_norm
-    source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Enigma
-      name: Open LLM Leaderboard
-  - task:
-      type: text-generation
-      name: Text Generation
-    dataset:
-      name: MMLU-PRO (5-shot)
-      type: TIGER-Lab/MMLU-Pro
-      config: main
-      split: test
-      args:
-        num_few_shot: 5
-    metrics:
-    - type: acc
-      value: 26.2
-      name: accuracy
-    source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Enigma
-      name: Open LLM Leaderboard
 license: llama3.1
 ---
 
@@ -135,13 +40,13 @@ Enigma is a code-instruct model built on Llama 3.1 8b.
 
 ## Version
 
-This is the **2024-09-04** release of Enigma for Llama 3.1 8b, enhancing code-instruct and general chat capabilities.
+This is the **2024-10-02** release of Enigma for Llama 3.1 8b, enhancing code-instruct and general chat capabilities.
 
 [**Enigma is now available for Llama 3.2 3b** - get it here!](https://huggingface.co/ValiantLabs/Llama3.2-3B-Enigma)
 
 Help us and recommend Enigma to your friends! We're excited for more Enigma releases in the future. 
 
-Right now, we're working on more new Build Tools to come very soon, built on Llama 3.1 :)
+Right now, we're working on more new Build Tools to come very soon, built on Llama 3.1 and 3.2 :)
 
 
 ## Prompting Guide
@@ -167,7 +72,7 @@ messages = [
 
 outputs = pipeline(
     messages,
-    max_new_tokens=1024,
+    max_new_tokens=2048,
 )
 
 print(outputs[0]["generated_text"][-1])

config.json

@@ -11,6 +11,7 @@
     128008,
     128009
   ],
+  "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -33,7 +34,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
+  "transformers_version": "4.45.1",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -8,5 +8,5 @@
   ],
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.44.2"
+  "transformers_version": "4.45.1"
 }