humanvprojectceo/Astro-HumanV-Nano-Instruct

.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

@@ -0,0 +1,72 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: astro_nano_final
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# astro_nano_final
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.1154
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0006
+- train_batch_size: 6
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 48
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.05
+- num_epochs: 50
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss |
+|:-------------:|:-------:|:----:|:---------------:|
+| 39.4094       | 1.0754  | 200  | 4.8414          |
+| 26.9608       | 2.1507  | 400  | 3.3385          |
+| 21.1754       | 3.2261  | 600  | 2.6653          |
+| 18.1758       | 4.3015  | 800  | 2.3504          |
+| 16.4671       | 5.3769  | 1000 | 2.1928          |
+| 15.3800       | 6.4522  | 1200 | 2.1093          |
+| 14.4885       | 7.5276  | 1400 | 2.0712          |
+| 13.9465       | 8.6030  | 1600 | 2.0451          |
+| 13.3508       | 9.6783  | 1800 | 2.0418          |
+| 12.6249       | 10.7537 | 2000 | 2.0428          |
+| 12.4236       | 11.8291 | 2200 | 2.0498          |
+| 11.9930       | 12.9044 | 2400 | 2.0606          |
+| 11.7952       | 13.9798 | 2600 | 2.0762          |
+| 9.7503        | 15.0538 | 2800 | 2.1154          |
+
+
+### Framework versions
+
+- Transformers 5.0.0.dev0
+- Pytorch 2.4.1+cu124
+- Datasets 4.4.2
+- Tokenizers 0.22.1

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,65 @@
+{
+  "activation_backend": "silu",
+  "architectures": [
+    "HumanVForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.1,
+  "attn_backend": "gqa_matmul",
+  "attn_implementation": "eager",
+  "bos_token_id": 151643,
+  "dtype": "float32",
+  "eos_token_id": 151643,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "kv_cache_dtype": "auto",
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention"
+  ],
+  "max_position_embeddings": 2048,
+  "max_window_layers": 0,
+  "mlp_bias": false,
+  "model_type": "humanv",
+  "norm_backend": "rmsnorm",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "resid_dropout": 0.1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "rope_partial_rotary_factor": 1.0,
+  "selective_rope_scale": 1.0,
+  "sliding_window": null,
+  "sparse_attention_impl": "local_global_block",
+  "sparse_attention_window": 256,
+  "sparse_block_size": 64,
+  "sparse_global_block_stride": 4,
+  "sparse_global_num_blocks": 2,
+  "sparse_local_num_blocks": 4,
+  "sparse_prefill_chunk_blocks": 16,
+  "transformers_version": "5.0.0.dev0",
+  "use_cache": false,
+  "use_selective_rope": false,
+  "use_sliding_window": false,
+  "use_sparse_attention": true,
+  "vocab_size": 151665
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "pad_token_id": 151643,
+  "transformers_version": "5.0.0.dev0",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc06892e187a60f013126ba16242cdc0cff75246746d30692c40398a274d419d
+size 499417152

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb4443d0f12b3b4298b5d1b9207d3352f1b6a56716e4d189add1728457b621d1
+size 4728