Push model using huggingface_hub.

README.md

@@ -26,7 +26,7 @@ You can then generate text as follows:
 ```python
 from transformers import pipeline
 
-generator = pipeline("text-generation", model="Mithilhf01//tmp/tmpp90aqkcd/Mithilhf01/mistral-ppo")
+generator = pipeline("text-generation", model="Mithilhf01//tmp/tmpxg2uubos/Mithilhf01/mistral-ppo")
 outputs = generator("Hello, my llama is cute")
 ```
 
@@ -36,8 +36,8 @@ If you want to use the model for training or to obtain the outputs from the valu
 from transformers import AutoTokenizer
 from trl import AutoModelForCausalLMWithValueHead
 
-tokenizer = AutoTokenizer.from_pretrained("Mithilhf01//tmp/tmpp90aqkcd/Mithilhf01/mistral-ppo")
-model = AutoModelForCausalLMWithValueHead.from_pretrained("Mithilhf01//tmp/tmpp90aqkcd/Mithilhf01/mistral-ppo")
+tokenizer = AutoTokenizer.from_pretrained("Mithilhf01//tmp/tmpxg2uubos/Mithilhf01/mistral-ppo")
+model = AutoModelForCausalLMWithValueHead.from_pretrained("Mithilhf01//tmp/tmpxg2uubos/Mithilhf01/mistral-ppo")
 
 inputs = tokenizer("Hello, my llama is cute", return_tensors="pt")
 outputs = model(**inputs, labels=inputs["input_ids"])

config.json

@@ -6,19 +6,19 @@
   "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "head_dim": 32,
+  "head_dim": 24,
   "hidden_act": "silu",
-  "hidden_size": 512,
+  "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "max_position_embeddings": 512,
   "model_type": "mistral",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 4,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 8,
   "num_key_value_heads": 8,
   "rms_norm_eps": 1e-06,
   "rope_theta": 10000.0,
-  "sliding_window": 512,
+  "sliding_window": 768,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.47.1",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:859e7582744a4c7cffc9125ace6d98fd4101d5402263c72e4206afe5afb2e3bb
-size 219177356
+oid sha256:dc494b524ea8be5b41dba1d8f51b10a55372c79c495cbee259bd4760f0e17052
+size 470350116

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 1024,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {