Upload 10 files

chat_template.jinja

@@ -0,0 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

config.json

@@ -1,40 +1,29 @@
 {
-  "activation": "gelu",
-  "alibi": true,
-  "apply_residual_connection_post_layernorm": false,
   "architectures": [
-    "FalconForCausalLM"
+    "LlamaForCausalLM"
   ],
+  "attention_bias": false,
   "attention_dropout": 0.0,
-  "auto_map": {
-    "AutoConfig": "tiiuae/falcon-rw-1b--configuration_falcon.FalconConfig",
-    "AutoModel": "tiiuae/falcon-rw-1b--modeling_falcon.FalconModel",
-    "AutoModelForCausalLM": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForCausalLM",
-    "AutoModelForQuestionAnswering": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForQuestionAnswering",
-    "AutoModelForSequenceClassification": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForSequenceClassification",
-    "AutoModelForTokenClassification": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForTokenClassification"
-  },
-  "bias": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "ffn_hidden_size": 8192,
-  "hidden_dropout": 0.0,
+  "head_dim": 64,
+  "hidden_act": "silu",
   "hidden_size": 2048,
   "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
+  "intermediate_size": 5632,
   "max_position_embeddings": 2048,
-  "model_type": "falcon",
-  "multi_query": false,
-  "new_decoder_architecture": false,
+  "mlp_bias": false,
+  "model_type": "llama",
   "num_attention_heads": 32,
-  "num_hidden_layers": 24,
-  "num_kv_heads": 32,
-  "num_ln_in_parallel_attn": null,
-  "parallel_attn": false,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
-  "torch_dtype": "float32",
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
   "transformers_version": "4.52.4",
   "use_cache": true,
-  "vocab_size": 50304
+  "vocab_size": 32000
 }

generation_config.json

@@ -1,6 +1,7 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
   "transformers_version": "4.52.4"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c16f5a3eb38dc730bed874ec2e4bd8ac3d47667035aae853995438bd3ccd86c8
+size 2200119664

special_tokens_map.json

@@ -1,21 +1,27 @@
 {
   "bos_token": {
-    "content": "<|endoftext|>",
+    "content": "<s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
   "unk_token": {
-    "content": "<|endoftext|>",
+    "content": "<unk>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -1,8 +1,26 @@
 {
-  "add_prefix_space": false,
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
-    "50256": {
-      "content": "<|endoftext|>",
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -10,12 +28,16 @@
       "special": true
     }
   },
-  "bos_token": "<|endoftext|>",
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
   "extra_special_tokens": {},
-  "model_max_length": 1024,
-  "pad_token": "<|endoftext|>",
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>"
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
 }