Phase 3: Shruti-Soft fine-tune (source: Umranz/Shruti-Soft-2.6b-run-b)

.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

.leap_ray_final_metrics.json

@@ -0,0 +1 @@
+{"epoch": 4.0, "eval_loss": 0.40741124749183655, "eval_runtime": 14.2417, "eval_samples_per_second": 35.108, "eval_steps_per_second": 8.777, "grad_norm": 0.23573072254657745, "grad_norm_history": [4.058745861053467, 3.9815444946289062, 2.6251626014709473, 1.2011679410934448, 1.1679165363311768, 0.404476135969162, 0.3265282213687897, 0.28703418374061584, 0.2587428689002991, 0.19774864614009857, 0.18679051101207733, 0.1732676774263382, 0.1878974288702011, 0.17219124734401703, 0.16141967475414276, 0.19137342274188995, 0.17077548801898956, 0.21034348011016846, 0.20671485364437103, 0.18505659699440002, 0.19827695190906525, 0.17547348141670227, 0.18044963479042053, 0.175068199634552, 0.20564821362495422, 0.19814783334732056, 0.1591830849647522, 0.1939147263765335, 0.18335798382759094, 0.1940874457359314, 0.19031044840812683, 0.2189788818359375, 0.1994149386882782, 0.1647401601076126, 0.1824384182691574, 0.20154958963394165, 0.17695632576942444, 0.20108473300933838, 0.18510442972183228, 0.194630965590477, 0.2001911699771881, 0.22190146148204803, 0.20429418981075287, 0.17748309671878815, 0.1915348321199417, 0.1903117299079895, 0.21312402188777924, 0.20088177919387817, 0.20017875730991364, 0.2149970680475235, 0.19488243758678436, 0.22705690562725067, 0.21331031620502472, 0.19080452620983124, 0.20524203777313232, 0.1885342001914978, 0.21870635449886322, 0.190370574593544, 0.21587225794792175, 0.21488641202449799, 0.2201114296913147, 0.22049778699874878, 0.21339896321296692, 0.2245381623506546, 0.194489985704422, 0.23113641142845154, 0.22329998016357422, 0.21329869329929352, 0.2204977422952652, 0.21949785947799683, 0.19868579506874084, 0.20381498336791992, 0.23892825841903687, 0.240747332572937, 0.20668494701385498, 0.21275918185710907, 0.2295587658882141, 0.2540450692176819, 0.2259698361158371, 0.2140018492937088, 0.21624968945980072, 0.22460561990737915, 0.23372429609298706, 0.24144119024276733, 0.23365530371665955, 0.2309986799955368, 0.21239043772220612, 0.24690458178520203, 0.28184208273887634, 0.2252269685268402, 0.24582383036613464, 0.23313838243484497, 0.24200984835624695, 0.2184435874223709, 0.2398524433374405, 0.2375684678554535, 0.2492256909608841, 0.23062969744205475, 0.24646103382110596, 0.22581052780151367, 0.24397146701812744, 0.24820585548877716, 0.23313775658607483, 0.24482564628124237, 0.2277684211730957, 0.22804470360279083, 0.2584152817726135, 0.2540855407714844, 0.2483542263507843, 0.23797990381717682, 0.2645752727985382, 0.24128858745098114, 0.23573072254657745], "learning_rate": 3.557273753149737e-09, "learning_rate_history": [0.0, 2.647058823529412e-06, 5.588235294117647e-06, 8.529411764705883e-06, 1.1470588235294118e-05, 1.4411764705882353e-05, 1.735294117647059e-05, 1.9999956080468243e-05, 1.9994686203441232e-05, 1.9980637723841005e-05, 1.9957822980826257e-05, 1.992626201320137e-05, 1.9885982541815805e-05, 1.983701994521612e-05, 1.977941722857203e-05, 1.9713224985903828e-05, 1.9638501355644274e-05, 1.955531196957405e-05, 1.9463729895175594e-05, 1.936383557145595e-05, 1.9255716738295035e-05, 1.913946835938132e-05, 1.9015192538802664e-05, 1.8882998431365545e-05, 1.874300214672144e-05, 1.8595326647384594e-05, 1.8440101640730706e-05, 1.827746346507147e-05, 1.8107554969904943e-05, 1.7930525390446965e-05, 1.7746530216553855e-05, 1.7555731056151485e-05, 1.7358295493290653e-05, 1.7154396940953507e-05, 1.694421448874024e-05, 1.6727932745569866e-05, 1.6505741677533204e-05, 1.627783644104057e-05, 1.6044417211410606e-05, 1.5805689007050906e-05, 1.5561861509384826e-05, 1.5313148878682617e-05, 1.5059769565958692e-05, 1.4801946121100206e-05, 1.4539904997395468e-05, 1.427387635263394e-05, 1.4004093846952397e-05, 1.373079443760497e-05, 1.3454218170837165e-05, 1.3174607971046782e-05, 1.2892209427416847e-05, 1.2607270578208029e-05, 1.2320041692899922e-05, 1.2030775052372623e-05, 1.1739724727321618e-05, 1.1447146355100638e-05, 1.1153296915188474e-05, 1.0858434503476969e-05, 1.0562818105578426e-05, 1.0266707369351565e-05, 9.970362376845795e-06, 9.674043415864134e-06, 9.378010751345414e-06, 9.08252439676656e-06, 8.78784388576573e-06, 8.494228044186925e-06, 8.201934762746269e-06, 7.91122077051963e-06, 7.622341409450542e-06, 7.3355504100764956e-06, 7.0510996686705555e-06, 6.769239025994063e-06, 6.4902160478547626e-06, 6.2142758076630624e-06, 5.941660671177463e-06, 5.6726100836281435e-06, 5.407360359405793e-06, 5.146144474500268e-06, 4.889191861871515e-06, 4.636728209932404e-06, 4.388975264320519e-06, 4.146150633132958e-06, 3.9084675957952845e-06, 3.67613491573246e-06, 3.4493566570062763e-06, 3.2283320050803966e-06, 3.013255091870384e-06, 2.8043148252324083e-06, 2.601694723040368e-06, 2.4055727519971948e-06, 2.2161211713219044e-06, 2.0335063814496625e-06, 1.857888777877801e-06, 1.68942261028612e-06, 1.5282558470552444e-06, 1.374530045301986e-06, 1.2283802265459144e-06, 1.0899347581163222e-06, 9.59315240403721e-07, 8.366364000549487e-07, 7.220059892056508e-07, 6.155246908386869e-07, 5.172860303515314e-07, 4.273762934104053e-07, 3.458744501632483e-07, 2.728520858780992e-07, 2.0837333806782877e-07, 1.5249484015643078e-07, 1.052656717363587e-07, 6.672731546059185e-08, 3.691362060730397e-08, 1.58507733491331e-08, 3.557273753149737e-09], "loss": 0.3500630855560303, "loss_history": [4.274528503417969, 4.30503675672743, 4.023840713500976, 3.1126949310302736, 2.2529233932495116, 1.2629572868347168, 0.9729546546936035, 0.8025846481323242, 0.6885480403900146, 0.5911908626556397, 0.5829123497009278, 0.5445427417755127, 0.5436184883117676, 0.5342414855957032, 0.5477189540863037, 0.5301987171173096, 0.5187788486480713, 0.5249112606048584, 0.5241843700408936, 0.5290304183959961, 0.5417416572570801, 0.4959384918212891, 0.4863734722137451, 0.4770023822784424, 0.4504709243774414, 0.47392773628234863, 0.45351557731628417, 0.45760383605957033, 0.4751412391662598, 0.4724257469177246, 0.4262892723083496, 0.44242563247680666, 0.44112391471862794, 0.42954049110412595, 0.42758798599243164, 0.4263291358947754, 0.42679638862609864, 0.43794960975646974, 0.4290309429168701, 0.4230069637298584, 0.425800085067749, 0.41313948631286623, 0.44257683753967286, 0.4154197692871094, 0.4386721611022949, 0.4394208908081055, 0.41255826950073243, 0.42099738121032715, 0.45169677734375, 0.41330924034118655, 0.4252933025360107, 0.4133157730102539, 0.42060627937316897, 0.40218605995178225, 0.41743946075439453, 0.4089807987213135, 0.4333989143371582, 0.4106279373168945, 0.3920194149017334, 0.4158449172973633, 0.414194393157959, 0.37076098918914796, 0.3894587516784668, 0.40344653129577634, 0.4023941993713379, 0.37771775722503664, 0.41034417152404784, 0.38796286582946776, 0.3789432287216187, 0.4067594051361084, 0.3981183528900146, 0.36903772354125974, 0.38149936199188234, 0.37212405204772947, 0.37762691974639895, 0.38533310890197753, 0.38396689891815183, 0.38934361934661865, 0.3690116167068481, 0.3773930549621582, 0.3881913423538208, 0.37703886032104494, 0.3857056379318237, 0.3781966924667358, 0.39438135623931886, 0.3793693780899048, 0.37108488082885743, 0.3373234272003174, 0.36213247776031493, 0.3817882537841797, 0.3607470512390137, 0.384859561920166, 0.38453288078308107, 0.33631856441497804, 0.3684308767318726, 0.35716125965118406, 0.3676045656204224, 0.3731567621231079, 0.37070579528808595, 0.35826132297515867, 0.36622047424316406, 0.37392120361328124, 0.3565518856048584, 0.35999796390533445, 0.3590352773666382, 0.38181390762329104, 0.3732086896896362, 0.3892883539199829, 0.3858488082885742, 0.37219283580780027, 0.3594131231307983, 0.36963865756988523, 0.3500630855560303], "total_flos": 5.027651349643264e+16, "train_loss": 0.5420034373482914, "train_runtime": 2860.4781, "train_samples_per_second": 6.293, "train_steps_per_second": 0.394}

.wandb_run_id_shruti-soft-run-b

@@ -0,0 +1 @@
+kwjiiipd

LFM2.5-2.6B-heretic-sft-shruti-tra-all-lr2em05-w0p1-lora_a-e0s100-20260813_093801/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Umranz/LFM2.5-2.6B-heretic
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Umranz/LFM2.5-2.6B-heretic
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.20.0

LFM2.5-2.6B-heretic-sft-shruti-tra-all-lr2em05-w0p1-lora_a-e0s100-20260813_093801/adapter_config.json

@@ -0,0 +1,52 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Umranz/LFM2.5-2.6B-heretic",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "feed_forward.w1",
+    "self_attn.out_proj",
+    "feed_forward.w2",
+    "feed_forward.w3",
+    "conv.in_proj",
+    "conv.out_proj",
+    "self_attn.k_proj",
+    "self_attn.q_proj",
+    "self_attn.v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

LFM2.5-2.6B-heretic-sft-shruti-tra-all-lr2em05-w0p1-lora_a-e0s100-20260813_093801/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b697c6be3d30b257dea99286385259cea02ae1742f4f81c09357e2722ea3f4c
+size 14709

LFM2.5-2.6B-heretic-sft-shruti-tra-all-lr2em05-w0p1-lora_a-e0s100-20260813_093801/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13f2a057337b7e8a78894a8394cf4f12cd5d889c18c16cf891a0769fb716f6c8
+size 1465

LFM2.5-2.6B-heretic-sft-shruti-tra-all-lr2em05-w0p1-lora_a-e0s100-20260813_093801/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:307027ef77b3f5ebbb4efddbd4ea99dd24cde32a7fd1d55c3bae3be487aa5853
+size 17905759

LFM2.5-2.6B-heretic-sft-shruti-tra-all-lr2em05-w0p1-lora_a-e0s100-20260813_093801/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "is_local": false,
+  "legacy": false,
+  "local_files_only": false,
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|pad|>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "tokenizer_class": "TokenizersBackend",
+  "use_default_system_prompt": false
+}

adapter_config.json

@@ -0,0 +1,52 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Umranz/LFM2.5-2.6B-heretic",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "feed_forward.w1",
+    "self_attn.out_proj",
+    "feed_forward.w2",
+    "feed_forward.w3",
+    "conv.in_proj",
+    "conv.out_proj",
+    "self_attn.k_proj",
+    "self_attn.q_proj",
+    "self_attn.v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:629d699caa008c5c8e716f54a344bf6ec4129c9b82226c654b21d94c50cf86f4
+size 195735144

chat_template.jinja

@@ -0,0 +1,125 @@
+{{- bos_token -}}
+{%- set preserve_thinking = preserve_thinking | default(false) -%}
+
+{%- macro format_arg_value(arg_value) -%}
+    {%- if arg_value is string -%}
+        {{- "'" + (arg_value | replace("\\", "\\\\") | replace("'", "\\'") | replace("\n", "\\n") | replace("\r", "\\r")) + "'" -}}
+    {%- elif arg_value is mapping or arg_value is iterable -%}
+        {{- arg_value | tojson -}}
+    {%- else -%}
+        {{- arg_value | string -}}
+    {%- endif -%}
+{%- endmacro -%}
+
+{%- macro parse_content(content) -%}
+    {%- if content is string -%}
+        {{- content -}}
+    {%- elif content is mapping -%}
+        {{- content | tojson -}}
+    {%- elif content is iterable -%}
+        {%- set _ns = namespace(result="") -%}
+        {%- for item in content -%}
+            {%- if item is string -%}
+                {%- set _ns.result = _ns.result + item -%}
+            {%- elif item is mapping and item.get("type") == "image" -%}
+                {%- set _ns.result = _ns.result + "<image>" -%}
+            {%- elif item is mapping and item.get("type") == "text" -%}
+                {%- set _ns.result = _ns.result + ((item.get("text") or "") | string) -%}
+            {%- else -%}
+                {%- set _ns.result = _ns.result + (item | tojson) -%}
+            {%- endif -%}
+        {%- endfor -%}
+        {{- _ns.result -}}
+    {%- endif -%}
+{%- endmacro -%}
+
+{%- macro render_tool_calls(tool_calls) -%}
+    {%- set tool_calls_ns = namespace(tool_calls=[]) -%}
+    {%- for tool_call in tool_calls -%}
+        {%- set func = tool_call["function"] if "function" in tool_call else tool_call -%}
+        {%- set func_name = func["name"] -%}
+        {%- set func_args = func.get("arguments") -%}
+        {%- set args_ns = namespace(arg_strings=[]) -%}
+        {%- if func_args is mapping -%}
+            {%- for arg_name, arg_value in func_args.items() -%}
+                {%- set args_ns.arg_strings = args_ns.arg_strings + [arg_name + "=" + format_arg_value(arg_value)] -%}
+            {%- endfor -%}
+        {%- elif func_args is string and (func_args | trim) not in ["", "{}", "null"] -%}
+            {{- raise_exception("Tool call arguments must be a mapping, got a JSON-encoded string: parse arguments with json.loads() before applying the chat template") -}}
+        {%- endif -%}
+        {%- set tool_calls_ns.tool_calls = tool_calls_ns.tool_calls + [func_name + "(" + (args_ns.arg_strings | join(", ")) + ")"] -%}
+    {%- endfor -%}
+    {{- "<|tool_call_start|>[" + (tool_calls_ns.tool_calls | join(", ")) + "]<|tool_call_end|>" -}}
+{%- endmacro -%}
+
+{%- set ns = namespace(system_prompt="", last_user_index=-1) -%}
+{%- if messages and messages[0]["role"] == "system" -%}
+    {%- if messages[0].get("content") -%}
+        {%- set ns.system_prompt = parse_content(messages[0]["content"]) -%}
+    {%- endif -%}
+    {%- set messages = messages[1:] -%}
+{%- endif -%}
+{%- if tools -%}
+    {%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
+    {%- for tool in tools -%}
+        {%- if tool is not string -%}
+            {%- set tool = tool | tojson -%}
+        {%- endif -%}
+        {%- set ns.system_prompt = ns.system_prompt + tool -%}
+        {%- if not loop.last -%}
+            {%- set ns.system_prompt = ns.system_prompt + ", " -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {%- set ns.system_prompt = ns.system_prompt + "]" -%}
+{%- endif -%}
+{%- if ns.system_prompt -%}
+    {{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
+{%- endif -%}
+{%- for message in messages -%}
+    {%- if message["role"] == "user" -%}
+        {%- set ns.last_user_index = loop.index0 -%}
+    {%- endif -%}
+{%- endfor -%}
+{%- for message in messages -%}
+    {{- "<|im_start|>" + message.role + "\n" -}}
+    {%- if message.role == "assistant" -%}
+        {%- generation -%}
+        {%- set keep_thinking = preserve_thinking or loop.index0 > ns.last_user_index -%}
+        {%- set thinking = message.thinking or message.reasoning or message.reasoning_content -%}
+        {%- set thinking = thinking if thinking is string else "" -%}
+        {%- if thinking and keep_thinking -%}
+            {{- "<think>" + thinking + "</think>" -}}
+        {%- endif -%}
+        {%- set _cfm_tag = "CONTINUE_FINAL_MESSAGE_TAG " -%}
+        {%- set _has_cfm = false -%}
+        {%- set content = "" -%}
+        {%- if message.get("content") -%}
+            {%- set content = parse_content(message.content) -%}
+        {%- endif -%}
+        {%- if not keep_thinking and "</think>" in content -%}
+            {%- set content = content.split("</think>")[-1] | trim -%}
+        {%- endif -%}
+        {%- if content.endswith(_cfm_tag) -%}
+            {%- set _has_cfm = true -%}
+            {%- set _trunc_len = (content | length) - (_cfm_tag | length) -%}
+            {%- set content = content[:_trunc_len] -%}
+        {%- endif -%}
+        {{- content -}}
+        {%- if message.tool_calls -%}
+            {{- render_tool_calls(message.tool_calls) -}}
+        {%- endif -%}
+        {%- if _has_cfm -%}
+            {{- _cfm_tag -}}
+        {%- endif -%}
+        {{- "<|im_end|>\n" -}}
+        {%- endgeneration -%}
+    {%- else %}
+        {%- if message.get("content") -%}
+            {{- parse_content(message["content"]) -}}
+        {%- endif -%}
+        {{- "<|im_end|>\n" -}}
+    {%- endif %}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{- "<|im_start|>assistant\n<think>" -}}
+{%- endif -%}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:307027ef77b3f5ebbb4efddbd4ea99dd24cde32a7fd1d55c3bae3be487aa5853
+size 17905759

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "is_local": false,
+  "legacy": false,
+  "local_files_only": false,
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|pad|>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "tokenizer_class": "TokenizersBackend",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13d0e1f2d4c222b029eab52b9346b804a42934e927437478f9b24d155f348ca9
+size 5393