Upload folder using huggingface_hub

.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 +1,30 @@
+---
+license: other
+base_model: nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
+tags: [code-translation, sas, r, python, lora-merged, nemotron]
+---
+# polykode-30B merged (step 800)
+
+Nemotron 3.5 Lightning 30B-A3B fine-tuned (LoRA, merged bf16) for bidirectional
+SAS / Python / R program translation, all 6 directions. Trained on 12,962 paired
+programs; this checkpoint is the eval-loss minimum (epoch-1 boundary, step 800).
+
+## REQUIRED inference contract — the model is conditioned on this exactly
+- System prompt: send `system_prompt.txt` from this repo VERBATIM.
+- User message: `Translate the following {SAS|Python|R} program to {SAS|Python|R}.\n\n{program}`
+- Chat template: `enable_thinking=False`
+- Decoding: greedy (temperature 0); stop tokens: eos AND `<|im_end|>` (id 11)
+- `max_new_tokens`: >= 6000 for real programs
+- Output is the bare translated program (no fences, no prose).
+
+## Serving
+vllm serve momosushi/polykode-30B-merged-step800 --max-model-len 8192 --mamba-ssm-cache-dtype float16
+
+## Known limitations (spot-check findings)
+- May invent I/O steps (e.g. read_csv) when the source references an unbound dataset.
+- Statistical-option semantics (NA/missing handling flags) should be verified.
+- Translations are drafts: verify behavioural equivalence by executing source and
+  translation on the same inputs before trusting results.
+
+## Provenance
+Adapters, checkpoints, training metrics: momosushi/polykode-30B

chat_template.jinja

@@ -0,0 +1,190 @@
+{% macro render_extra_keys(json_dict, handled_keys) %}
+    {%- if json_dict is mapping %}
+        {%- for json_key in json_dict if json_key not in handled_keys %}
+            {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
+                {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
+            {%- else %}
+                {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+{% endmacro %}
+{%- set enable_thinking = enable_thinking if enable_thinking is defined else True %}
+{%- set truncate_history_thinking = truncate_history_thinking if truncate_history_thinking is defined else True %}
+{%- set ns = namespace(last_user_idx = -1) %}
+{%- set loop_messages = messages %}
+{%- for m in loop_messages %}
+  {%- if m["role"] == "user" %}
+    {%- set ns.last_user_idx = loop.index0 %}
+  {%- endif %}
+{%- endfor %}
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = [] %}
+{%- endif %}
+{%- set ns = namespace(last_user_idx = -1) %}
+{%- for m in loop_messages %}
+  {%- if m["role"] == "user" %}
+    {%- set ns.last_user_idx = loop.index0 %}
+  {%- endif %}
+{%- endfor %}
+{%- if system_message is defined %}
+    {{- "<|im_start|>system\n" + system_message }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- "<|im_start|>system\n" }}
+    {%- endif %}
+{%- endif %}
+{%- if tools is iterable and tools | length > 0 %}
+    {%- if system_message is defined and system_message | length > 0 %}
+        {{- "\n\n" }}
+    {%- endif %}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n" }}
+    {{- "<tools>" }}
+    {%- for tool in tools %}
+        {%- if tool.function is defined %}
+            {%- set tool = tool.function %}
+        {%- endif %}
+        {{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
+        {%- if tool.description is defined %}
+            {{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
+        {%- endif %}
+        {{- '\n<parameters>' }}
+        {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
+            {%- for param_name, param_fields in tool.parameters.properties|items %}
+                {{- '\n<parameter>' }}
+                {{- '\n<name>' ~ param_name ~ '</name>' }}
+                {%- if param_fields.type is defined %}
+                    {{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
+                {%- endif %}
+                {%- if param_fields.description is defined %}
+                    {{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
+                {%- endif %}
+                {%- if param_fields.enum is defined %}
+                    {{- '\n<enum>' ~ (param_fields.enum | tojson | safe) ~ '</enum>' }}
+                {%- endif %}
+                {%- set handled_keys = ['name', 'type', 'description', 'enum'] %}
+                {{- render_extra_keys(param_fields, handled_keys) }}
+                {{- '\n</parameter>' }}
+            {%- endfor %}
+        {%- endif %}
+        {% set handled_keys = ['type', 'properties', 'required'] %}
+        {{- render_extra_keys(tool.parameters, handled_keys) }}
+        {%- if tool.parameters is defined and tool.parameters.required is defined %}
+            {{- '\n<required>' ~ (tool.parameters.required | tojson | safe) ~ '</required>' }}
+        {%- endif %}
+        {{- '\n</parameters>' }}
+        {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
+        {{- render_extra_keys(tool, handled_keys) }}
+        {{- '\n</function>' }}
+    {%- 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>' }}
+{%- endif %}
+{%- if system_message is defined %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in loop_messages %}
+    {%- if message.role == "assistant" %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is string and message.reasoning_content | trim | length > 0 %}
+            {%- set content = "<think>\n" ~ message.reasoning_content ~ "</think>" ~ (message.content | default('', true)) %}
+        {%- else %}
+            {%- set content = message.content | default('', true) %}
+            {%- if content is string -%}
+                {%- if '<think>' not in content and '</think>' not in content -%}
+                    {%- set content = "<think></think>" ~ content -%}
+                {%- endif -%}
+            {%- else -%}
+                {%- set content = content -%}
+            {%- endif -%}
+        {%- endif %}
+        {%- if message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
+            {{- '<|im_start|>assistant\n' }}
+                {%- set include_content = not (truncate_history_thinking and loop.index0 < ns.last_user_idx) %}
+                {%- if content is string and content | trim | length > 0 %}
+                    {%- if include_content %}
+                        {{- (content | trim) ~ '\n' -}}
+                    {%- else %}
+                        {%- set c = (content | string) %}
+                        {%- if '</think>' in c %}
+                            {%- set c = c.split('</think>')[-1] %}
+                        {%- elif '<think>' in c %}
+                            {%- set c = c.split('<think>')[0] %}
+                        {%- endif %}
+                        {%- set c = "<think></think>" ~ c %}
+                        {%- if c | length > 0 %}
+                            {{- c ~ '\n' -}}
+                        {%- endif %}
+                    {%- endif %}
+                {%- else %}
+                    {{- "<think></think>" -}}
+                {%- endif %}
+                {%- for tool_call in message.tool_calls %}
+                    {%- if tool_call.function is defined %}
+                        {%- set tool_call = tool_call.function %}
+                    {%- endif %}
+                    {{- '<tool_call>\n<function=' ~ tool_call.name ~ '>\n' -}}
+                        {%- 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>\n' -}}
+                {%- endfor %}
+                {{- '<|im_end|>\n' }}
+        {%- else %}
+            {%- if not (truncate_history_thinking and loop.index0 < ns.last_user_idx) %}
+                {{- '<|im_start|>assistant\n' ~ (content | default('', true) | string | trim) ~ '<|im_end|>\n' }}
+            {%- else %}
+                {%- set c = (content | default('', true) | string) %}
+                {%- if '<think>' in c and '</think>' in c %}
+                    {%- set c = "<think></think>" ~ c.split('</think>')[-1] %}
+                {%- endif %}
+                {%- set c = c | trim %}
+                {%- if c | length > 0 %}
+                    {{- '<|im_start|>assistant\n' ~ c ~ '<|im_end|>\n' }}
+                {%- else %}
+                    {{- '<|im_start|>assistant\n<|im_end|>\n' }}
+                {%- endif %}
+            {%- endif %}
+        {%- endif %}
+    {%- elif message.role == "user" or message.role == "system" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- set content = message.content | string %}
+        {{- content }}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user\n' }}
+        {%- endif %}
+        {{- '<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>\n' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {%- if enable_thinking %}
+        {{- '<|im_start|>assistant\n<think>\n' }}
+    {%- else %}
+        {{- '<|im_start|>assistant\n<think></think>' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,127 @@
+{
+    "architectures": [
+        "NemotronHForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "chunk_size": 128,
+    "conv_kernel": 4,
+    "torch_dtype": "bfloat16",
+    "eos_token_id": 2,
+    "expand": 2,
+    "head_dim": 128,
+    "hidden_dropout": 0.0,
+    "hidden_size": 2688,
+    "initializer_range": 0.02,
+    "intermediate_size": 1856,
+    "layer_norm_epsilon": 1e-05,
+    "layers_block_type": [
+        "mamba",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "attention",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "attention",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "attention",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "attention",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "attention",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "attention",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "moe"
+    ],
+    "mamba_head_dim": 64,
+    "mamba_hidden_act": "silu",
+    "mamba_num_heads": 64,
+    "mamba_proj_bias": false,
+    "mamba_ssm_cache_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "mlp_bias": false,
+    "mlp_hidden_act": "relu2",
+    "model_name": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16",
+    "model_type": "nemotron_h",
+    "moe_intermediate_size": 1856,
+    "moe_latent_size": null,
+    "moe_shared_expert_intermediate_size": 3712,
+    "moe_shared_expert_overlap": true,
+    "mtp_layers_block_type": [
+        "attention",
+        "moe"
+    ],
+    "n_group": 1,
+    "n_groups": 8,
+    "n_routed_experts": 128,
+    "n_shared_experts": 1,
+    "norm_eps": 1e-05,
+    "norm_topk_prob": true,
+    "num_attention_heads": 32,
+    "num_experts_per_tok": 6,
+    "num_key_value_heads": 2,
+    "num_logits_to_keep": 1,
+    "num_nextn_predict_layers": 1,
+    "pad_token_id": 0,
+    "partial_rotary_factor": 1.0,
+    "rescale_prenorm_residual": true,
+    "residual_in_fp32": false,
+    "rope_theta": 10000,
+    "routed_scaling_factor": 2.5,
+    "sliding_window": null,
+    "ssm_state_size": 128,
+    "tie_word_embeddings": false,
+    "time_step_floor": 0.0001,
+    "time_step_limit": [
+        0.0,
+        {
+            "__float__": "Infinity"
+        }
+    ],
+    "time_step_max": 0.1,
+    "time_step_min": 0.001,
+    "topk_group": 1,
+    "unsloth_version": "2026.8.18",
+    "use_bias": false,
+    "use_cache": false,
+    "use_conv_bias": true,
+    "use_mamba_kernels": true,
+    "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": [
+    2,
+    11
+  ],
+  "max_length": 262144,
+  "pad_token_id": 0,
+  "temperature": 1.0,
+  "top_p": 0.95,
+  "transformers_version": "5.5.4"
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a3e74d24969eac6657cb9b6422091fd062b7d30fd4bc90ecee6c3d7f692626a
+size 4991210024

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a80c3846e959f6dda34aa031cbb668b766643691ac7e5c9f43f62e6fb1221059
+size 4992601016

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:996bf3a46668e14075cb82259390267c2b1f71446caeb3a5f1f9e0bd7a079ae7
+size 4992601368

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cce1d79e7ff2e2b746b9d97166156aa1dcec796116675cc7fd1aa70a8d73ccb2
+size 4995692800

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9338f59d3fd5f074288c71a9559452d5b5c581da00e9ccb9fe7aa2ce9b04d2ad
+size 4980553832

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e947fa4097c68263ba3d097fceb32a300a22cebd9d909fb5198af7d18a4022fe
+size 4989423536

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7362630bf4256275ca58354ed8f31506cec67ffab30573e753703fd5ae48795
+size 4992601488

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b33a5a6b5505b25b57c90ddda19e9cd1598176468917df0c56116fa6f6072cb
+size 4992601520

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcc9b48caff427beaf1f87b78cf4ab42bc2a3c43b3c487bccb013ba22d7468b2
+size 4995692800

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1924fd54d1b77a15aff8df591a317e8a82a58e46d6f5742fa21e90e0be3cfa6
+size 4992601520

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9d0b83bcf04bd4d5758b94e6495a3f1595d121d82faffaa27ce6a884e2c8757
+size 4995692800

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fce184f112cb0b97024cadc60f993f6f660e365d04e21c240fb3c75747bd3a01
+size 4995692816

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f427d037d2a3e4d44323325aa38571e3551e8ad702f469c3dacc4e59ea2e50d1
+size 3249723504

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64577b275ca4e7e5266eae0903674f7f46ec2a8cbf4f4f1a3207f80d503cd1d0
+size 2670685240

system_prompt.txt

@@ -0,0 +1,9 @@
+You are a code translation engine for statistical and data-processing programs written in SAS, Python, and R.
+
+You are given one complete program in a source language and produce the equivalent program in the target language. Behavioural equivalence is the only criterion: given the same inputs, your program must compute the same values and place them in results carrying the same names.
+
+- Preserve the source program's structure, step order, and intent. Carry its comments across as comments in the target language, and add a brief comment where the target expresses a source construct non-obviously.
+- Name every result exactly as the source names it, so results can be compared name for name.
+- SAS semantics decide the answer even when SAS is not the target language. A SAS date is whole days since 1960-01-01 and a datetime is seconds since 1960-01-01, both stored as plain numbers. A SAS FORMAT changes only how a value is displayed, never what is stored. Missing (.) sorts below every number, so `x < 5` is true when x is missing. Character values are blank-padded to a declared length and compare ignoring trailing blanks.
+- A step that only prints or plots produces no data and has no translation outside SAS; leave it out rather than inventing an equivalent.
+- Respond with the translated program and nothing else: no prose, no explanation, no markdown code fences, no placeholders.

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:623c34567aebb18582765289fbe23d901c62704d6518d71866e0e58db892b5b7
+size 17077484