Upload folder using huggingface_hub

README.md

@@ -0,0 +1,48 @@
+---
+base_model:
+- Pedro13543/qwq_finetuned_results_chat_finetune
+- Pedro13543/qwq_finetune_result
+- nisten/Biggie-SmoLlm-0.15B-Base
+- Pedro13543/fast_r1_small_experiment
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [nisten/Biggie-SmoLlm-0.15B-Base](https://huggingface.co/nisten/Biggie-SmoLlm-0.15B-Base) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [Pedro13543/qwq_finetuned_results_chat_finetune](https://huggingface.co/Pedro13543/qwq_finetuned_results_chat_finetune)
+* [Pedro13543/qwq_finetune_result](https://huggingface.co/Pedro13543/qwq_finetune_result)
+* [Pedro13543/fast_r1_small_experiment](https://huggingface.co/Pedro13543/fast_r1_small_experiment)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: Pedro13543/fast_r1_small_experiment
+  - model: Pedro13543/qwq_finetune_result
+  - model: Pedro13543/qwq_finetuned_results_chat_finetune
+
+
+
+merge_method: model_stock
+base_model: nisten/Biggie-SmoLlm-0.15B-Base
+parameters:
+  normalize: false
+  int8_mask: true
+dtype: float16
+
+```

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "nisten/Biggie-SmoLlm-0.15B-Base",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 35,
+  "num_key_value_heads": 3,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.48.2",
+  "use_cache": true,
+  "vocab_size": 49152
+}

mergekit_config.yml

@@ -0,0 +1,13 @@
+models:
+  - model: Pedro13543/fast_r1_small_experiment
+  - model: Pedro13543/qwq_finetune_result
+  - model: Pedro13543/qwq_finetuned_results_chat_finetune
+
+
+
+merge_method: model_stock
+base_model: nisten/Biggie-SmoLlm-0.15B-Base
+parameters:
+  normalize: false
+  int8_mask: true
+dtype: float16

model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa341bd63b7d93b6fd62c949252b71d0406e9baa0209ebe5d511ebe7a9a76891
+size 361089584

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.6", "total_size": 361054080}, "weight_map": {"lm_head.weight": "model-00001-of-00001.safetensors", "model.embed_tokens.weight": "model-00001-of-00001.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.norm.weight": "model-00001-of-00001.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,42 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
+  ],
+  "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
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,168 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}