Add Keen midtrain-longcontext-1B-32K trained checkpoint

.gitattributes

@@ -54,3 +54,4 @@ Vanilla-qwen4b-20b/checkpoint-5726/tokenizer.json filter=lfs diff=lfs merge=lfs
 Vanilla-qwen4b-20b/checkpoint-13362/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 Vanilla-qwen4b-20b/checkpoint-15273/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 datasets/KLLM-20B/packing/source2b/READY.json filter=lfs diff=lfs merge=lfs -text
+Keen-qwen4b-20b/midtrain-longcontext-1B-32K/checkpoint-1155/tokenizer.json filter=lfs diff=lfs merge=lfs -text

Keen-qwen4b-20b/midtrain-longcontext-1B-32K/checkpoint-1155/README.md

@@ -0,0 +1,28 @@
+# Keen Qwen3.5-4B — midtrain-longcontext-1B-32K
+
+Continued from the 9B instruction-mixture midtraining checkpoint for exactly 1,000,000,000 supervised tokens at a 32,768-token window. The prepared long-context pool contains 5,072,536,771 targets, but only 1B was trained. This is not a 5B-trained checkpoint. The actual mixture is 65.756% FineWeb-Edu, 17.090% PDF, 8.651% CWE and 8.503% REX.
+
+This is a text-only Keen checkpoint with its original tokenizer. Training used ordinary NTP,
+without added fact wrappers. This release precedes financial SFT. The architecture configuration
+retains its original positional capacity; it does not establish quality beyond the trained window.
+Weights, tokenizer and chat-template files are included. Optimizer state is retained locally.
+
+The verified training runtime used Transformers 5.6.2 and tokenizers 0.22.2. To preserve the
+effective tokenizer, load the supplied backend explicitly. Preserve the checkpoint's FP32
+`A_log` and `dt_bias` tensors if using a loader that casts every parameter to BF16.
+
+```python
+from huggingface_hub import snapshot_download
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from tokenizers import Tokenizer
+from pathlib import Path
+
+subfolder = "Keen-qwen4b-20b/midtrain-longcontext-1B-32K/checkpoint-1155"
+root = snapshot_download("meihant/AnonymousModel-mht", allow_patterns=[subfolder + "/*"])
+path = Path(root) / subfolder
+tokenizer = AutoTokenizer.from_pretrained(path)
+tokenizer._tokenizer = Tokenizer.from_file(str(path / "tokenizer.json"))
+model = AutoModelForCausalLM.from_pretrained(path, dtype="auto")
+```
+
+See `training_metadata.json` for token accounting and lineage and `manifest.json` for file hashes.

Keen-qwen4b-20b/midtrain-longcontext-1B-32K/checkpoint-1155/chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

Keen-qwen4b-20b/midtrain-longcontext-1B-32K/checkpoint-1155/config.json

@@ -0,0 +1,83 @@
+{
+  "architectures": [
+    "Qwen3_5ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_output_gate": true,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 248044,
+  "full_attention_interval": 4,
+  "head_dim": 256,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9216,
+  "layer_types": [
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention"
+  ],
+  "linear_conv_kernel_dim": 4,
+  "linear_key_head_dim": 128,
+  "linear_num_key_heads": 16,
+  "linear_num_value_heads": 32,
+  "linear_value_head_dim": 128,
+  "mamba_ssm_dtype": "float32",
+  "max_position_embeddings": 262144,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_5_text",
+  "mtp_num_hidden_layers": 1,
+  "mtp_use_dedicated_embeddings": false,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 4,
+  "pad_token_id": 248044,
+  "partial_rotary_factor": 0.25,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "mrope_interleaved": true,
+    "mrope_section": [
+      11,
+      11,
+      10
+    ],
+    "partial_rotary_factor": 0.25,
+    "rope_theta": 10000000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.6.2",
+  "use_cache": true,
+  "vocab_size": 248320
+}

Keen-qwen4b-20b/midtrain-longcontext-1B-32K/checkpoint-1155/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 248044,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 248044,
+  "transformers_version": "5.6.2",
+  "use_cache": false
+}

Keen-qwen4b-20b/midtrain-longcontext-1B-32K/checkpoint-1155/manifest.json

@@ -0,0 +1,53 @@
+{
+  "files": [
+    {
+      "name": "README.md",
+      "bytes": 1707,
+      "sha256": "336b4abe5144e111da702c69eb8d31dd9ccdde96d77f228967c2a73700f0415d",
+      "git_blob_sha1": "0b8da5dcc37870edae838b5f11f811469e58e63d"
+    },
+    {
+      "name": "chat_template.jinja",
+      "bytes": 7756,
+      "sha256": "a4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715",
+      "git_blob_sha1": "a585dec894e63da457d9440ec6aa7caa16d20860"
+    },
+    {
+      "name": "config.json",
+      "bytes": 1980,
+      "sha256": "eac5a6e0ba2e18c79768899a66a50997393c6ca2e50df8763d2c6787fb077c27",
+      "git_blob_sha1": "65f95a09d021431a51836127668a8ecbc2fc21e2"
+    },
+    {
+      "name": "generation_config.json",
+      "bytes": 205,
+      "sha256": "859817f149747a3645f7706735a71d572091a2616b9b8c648333d05422247f85",
+      "git_blob_sha1": "c98efef4f4396feaf1ce5d8ef4f5a141467e858a"
+    },
+    {
+      "name": "model.safetensors",
+      "bytes": 8411554440,
+      "sha256": "932889cf4b62a0903dbe357f4c358b1eadec2d300b0ddab7f4399cd3a35e9a71",
+      "git_blob_sha1": null
+    },
+    {
+      "name": "tokenizer.json",
+      "bytes": 19989710,
+      "sha256": "76cc6bc2453583ba12d5e108102967821b81f8413c66c048778617154e782acf",
+      "git_blob_sha1": "fdf075e84c5f6fa7e0e293ba6d794ede81e6f567"
+    },
+    {
+      "name": "tokenizer_config.json",
+      "bytes": 1470,
+      "sha256": "ab8728a2e6116725250212041642e345238a2f9af4cb18b43c26b680f2d95b67",
+      "git_blob_sha1": "db5a7cc577677b3516a9d62d5c4405d3cfc0d7c4"
+    },
+    {
+      "name": "training_metadata.json",
+      "bytes": 2616,
+      "sha256": "03fd63981d7c594b2f02bf37e2a697899f47e555b53fa1b25ee6ebe8487484c4",
+      "git_blob_sha1": "80fbf1c61380f0cab858fbfe4404c11ec832170d"
+    }
+  ],
+  "source_checkpoint": "checkpoint-1155"
+}

Keen-qwen4b-20b/midtrain-longcontext-1B-32K/checkpoint-1155/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:932889cf4b62a0903dbe357f4c358b1eadec2d300b0ddab7f4399cd3a35e9a71
+size 8411554440

Keen-qwen4b-20b/midtrain-longcontext-1B-32K/checkpoint-1155/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76cc6bc2453583ba12d5e108102967821b81f8413c66c048778617154e782acf
+size 19989710

Keen-qwen4b-20b/midtrain-longcontext-1B-32K/checkpoint-1155/tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "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|>",
+    "<fact>",
+    "</fact>"
+  ],
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "local_files_only": true,
+  "model_max_length": 32768,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

Keen-qwen4b-20b/midtrain-longcontext-1B-32K/checkpoint-1155/training_metadata.json

@@ -0,0 +1,58 @@
+{
+  "stage": "midtrain-longcontext-1B-32K",
+  "checkpoint_step": 1155,
+  "cumulative_optimizer_step": 33584,
+  "stage_supervised_tokens": 1000000000,
+  "trained_sequence_window": 32768,
+  "parent_checkpoint": "Keen-qwen4b-20b/midtrain-if-9B/checkpoint-9765",
+  "architecture": [
+    "Qwen3_5ForCausalLM"
+  ],
+  "model_type": "qwen3_5_text",
+  "objective": "ordinary next-token prediction on original text",
+  "fact_markers_injected": false,
+  "financial_sft_applied": false,
+  "training_code_sha256": {
+    "benchmark.py": "1cb435ca92937f1eebbc1fa9adde5f6faccf9c74149b70c70e0c2c63597510e4",
+    "checkpoint_offload.py": "6bdd88c3296f7f70280843bc2793f2559b7e70d276d8d066f4977a13824f3514",
+    "common.py": "d2c090024fd4ee7330c365261b7f6ffb963c6c05a49703efd76f01bdb8d153ec",
+    "finalize.py": "85a98c540ccadb648cb4c799711ac5e9ed7b55a0e002974d93c1002e7c05160e",
+    "optimizer.py": "f724a7beebe0c69c2686a221edefe33d333c87450f5347427766d83c6e612c1e",
+    "packed_model.py": "accc6489f83979a8cdad6d0863e133a5689ad00deb97941be7ddf4e2854c598a",
+    "packer.py": "53250b9f95bc75a79a1c893503605a657ec3cae7b6129fe41173673794aa9418",
+    "prepare.py": "40c95af2b293be14259f1e6cc8774a911dd415fc9f94a26d478817007e2765b8",
+    "repack.py": "b24d9668b51de2d7992030261d93b8b8267aee14ce00e71b66e470010f407bb6",
+    "runtime.py": "2b8c92f1ad6bd32a5cdd260aba89753e67c8b0ff11992f607e3a73030a038a12",
+    "source_rows.py": "7aec972eb94bbbbd55ee1aa0e53dd3ec062e99692a68d02cc3e11a760b69d3dd",
+    "submit.py": "36300b02ffdf15ae24736d457f2dafbad293b863cc63abd42c60c5c6011cf11a",
+    "test_checkpoint_offload.py": "7e5e3067c2ccea103d9bdc0a63b9f25733bd9eaf01fc1d80b4fe1800a605b183",
+    "test_data.py": "541c992730b2a8e0c06045d5427b5d7d386f832d206ed20d7b07e4e4b2269141",
+    "tokenizer_utils.py": "bf5ac7268f92a0a8c5645ddbcceb6c6342971de3f196dd7a1bff97b8bfc6ddef",
+    "train.py": "58d1457598a87405f175849719c158bd7a5305bed3727c4975221d925c944dfd",
+    "config.json": "5b9434b57d2aceb33a31b1f71b1714c6324814a786a052386d38dcb3a2b573dd"
+  },
+  "export_changes": {
+    "config.use_cache": true
+  },
+  "weights": "Unmodified original safetensors; optimizer state retained locally.",
+  "available_pool_targets": 5072536771,
+  "entire_5B_pool_trained": false,
+  "actual_training_mix": {
+    "FineWeb-Edu": {
+      "target_tokens": 657559147,
+      "percent": 65.75591469999999
+    },
+    "PDF": {
+      "target_tokens": 170902036,
+      "percent": 17.090203600000002
+    },
+    "REX": {
+      "target_tokens": 85027655,
+      "percent": 8.502765499999999
+    },
+    "CWE": {
+      "target_tokens": 86511162,
+      "percent": 8.6511162
+    }
+  }
+}