r1.1 (#3)

- r1.1 (84ed6e09e50abf1162617c56ae5c0e502150138f)


Co-authored-by: sahil sunejaa <[email protected]>

config.json

@@ -1,20 +1,21 @@
 {
-  "base_model_name_or_path": "ibm-granite/granite-20b-code-instruct",
   "architectures": [
     "MLPSpeculatorPreTrainedModel"
   ],
   "emb_dim": 6144,
   "inner_dim": 4096,
   "model_type": "mlp_speculator",
-  "n_candidates": 5,
+  "n_candidates": 4,
   "n_predict": 4,
+  "scale_input": false,
+  "tie_weights": false,
   "top_k_tokens_per_head": [
-    5,
+    4,
     3,
     2,
     2
   ],
   "torch_dtype": "float16",
-  "transformers_version": "4.35.0",
+  "transformers_version": "4.41.2",
   "vocab_size": 49152
 }

model.safetensors → pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:095151ffe70aa7af5d857ee828e5f74ee053643ecb00b386be5bcc3be1fa4eef
-size 3372287960
+oid sha256:9519727c3beb5569b89d74e55929db90d3bfbce69e796afea66d0b02a55d76d2
+size 3372292714

special_tokens_map.json

@@ -20,8 +20,32 @@
     "<commit_after>",
     "<reponame>"
   ],
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
-  "pad_token": "<|endoftext|>",
-  "unk_token": "<|endoftext|>"
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -206,6 +206,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       "<|endoftext|>": 0,
       "<fim_prefix>": 1,

tokenizer_config.json

@@ -176,6 +176,7 @@
     "<reponame>"
   ],
   "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ 'Question:\n' + message['content'] + '\n\n' }}{% elif message['role'] == 'system' %}\n{{ 'System:\n' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Answer:\n'  + message['content'] + '\n\n' }}{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ 'Answer:\n' }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "model_max_length": 8192,