Upload BharatLLM adapter

README.md

@@ -0,0 +1,87 @@
+---
+language:
+- mr
+license: apache-2.0
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+tags:
+- lora
+- qlora
+- education
+- k12
+- indian-languages
+- cbse
+- ncert
+- bharatllm
+- foundryailabs
+datasets:
+- FoundryAILabs/k12-indian-curriculum-4.9m
+pipeline_tag: text-generation
+---
+
+# BharatLLM Marathi -- K-12 Education LoRA
+
+A **QLoRA adapter** for Mistral-7B, fine-tuned on **CBSE/NCERT K-12 curriculum** data in **Marathi** (मराठी).
+
+Part of the **BharatLLM** project: 13 LoRA adapters (12 K-12 languages + 1 BTech Engineering).
+
+## Model Details
+
+| Property | Value |
+|----------|-------|
+| **Base Model** | mistralai/Mistral-7B-Instruct-v0.3 |
+| **Method** | QLoRA (4-bit quantization + LoRA, r=64) |
+| **Trainable Parameters** | 167,772,160 (2.26% of 7.4B) |
+| **Training Library** | Unsloth |
+| **Language** | Marathi (मराठी) |
+| **Domain** | K-12 Education (CBSE/NCERT, Grades 6-12) |
+| **Training Data** | ~408K curriculum-aligned Q&A pairs |
+| **License** | Apache 2.0 |
+
+## Quick Start (Unsloth -- Fastest)
+
+```python
+from unsloth import FastLanguageModel
+
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name="FoundryAILabs/bharat-marathi-7b-lora",
+    max_seq_length=2048,
+    load_in_4bit=True,
+)
+FastLanguageModel.for_inference(model)
+
+inputs = tokenizer("[INST] What is photosynthesis? [/INST]", return_tensors="pt").to("cuda")
+outputs = model.generate(**inputs, max_new_tokens=512)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## Using with HuggingFace Transformers
+
+```python
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+base = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3", load_in_4bit=True, device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3")
+model = PeftModel.from_pretrained(base, "FoundryAILabs/bharat-marathi-7b-lora")
+```
+
+## All BharatLLM Models
+
+| Model | Language | Type |
+|-------|----------|------|
+| [FoundryAILabs/bharat-english-7b-lora](https://huggingface.co/FoundryAILabs/bharat-english-7b-lora) | English | K-12 |
+| [FoundryAILabs/bharat-hindi-7b-lora](https://huggingface.co/FoundryAILabs/bharat-hindi-7b-lora) | Hindi | K-12 |
+| [FoundryAILabs/bharat-bengali-7b-lora](https://huggingface.co/FoundryAILabs/bharat-bengali-7b-lora) | Bengali | K-12 |
+| [FoundryAILabs/bharat-telugu-7b-lora](https://huggingface.co/FoundryAILabs/bharat-telugu-7b-lora) | Telugu | K-12 |
+| [FoundryAILabs/bharat-tamil-7b-lora](https://huggingface.co/FoundryAILabs/bharat-tamil-7b-lora) | Tamil | K-12 |
+| [FoundryAILabs/bharat-kannada-7b-lora](https://huggingface.co/FoundryAILabs/bharat-kannada-7b-lora) | Kannada | K-12 |
+| [FoundryAILabs/bharat-malayalam-7b-lora](https://huggingface.co/FoundryAILabs/bharat-malayalam-7b-lora) | Malayalam | K-12 |
+| [FoundryAILabs/bharat-marathi-7b-lora](https://huggingface.co/FoundryAILabs/bharat-marathi-7b-lora) | Marathi | K-12 |
+| [FoundryAILabs/bharat-gujarati-7b-lora](https://huggingface.co/FoundryAILabs/bharat-gujarati-7b-lora) | Gujarati | K-12 |
+| [FoundryAILabs/bharat-odia-7b-lora](https://huggingface.co/FoundryAILabs/bharat-odia-7b-lora) | Odia | K-12 |
+| [FoundryAILabs/bharat-punjabi-7b-lora](https://huggingface.co/FoundryAILabs/bharat-punjabi-7b-lora) | Punjabi | K-12 |
+| [FoundryAILabs/bharat-urdu-7b-lora](https://huggingface.co/FoundryAILabs/bharat-urdu-7b-lora) | Urdu | K-12 |
+| [FoundryAILabs/bharat-btech-7b-lora](https://huggingface.co/FoundryAILabs/bharat-btech-7b-lora) | English | BTech Engineering |
+
+**Website**: [foundryailabs.io](https://foundryailabs.io) | **GitHub**: [github.com/foundryailabs/BharatLLM](https://github.com/foundryailabs/BharatLLM)

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "MistralForCausalLM",
+    "parent_library": "transformers.models.mistral.modeling_mistral",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4b5e0aca90f0800527b1e3c6e6c96da0bbed1755ae43f92ebf0af76a71da120
+size 671149168

chat_template.jinja

@@ -0,0 +1,87 @@
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
+
+{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
+{%- set ns = namespace() %}
+{%- set ns.index = 0 %}
+{%- for message in loop_messages %}
+    {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
+        {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
+            {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
+        {%- endif %}
+        {%- set ns.index = ns.index + 1 %}
+    {%- endif %}
+{%- endfor %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if message["role"] == "user" %}
+        {%- if tools is not none and (message == user_messages[-1]) %}
+            {{- "[AVAILABLE_TOOLS] [" }}
+            {%- for tool in tools %}
+                {%- set tool = tool.function %}
+                {{- '{"type": "function", "function": {' }}
+                {%- for key, val in tool.items() if key != "return" %}
+                    {%- if val is string %}
+                        {{- '"' + key + '": "' + val + '"' }}
+                    {%- else %}
+                        {{- '"' + key + '": ' + val|tojson }}
+                    {%- endif %}
+                    {%- if not loop.last %}
+                        {{- ", " }}
+                    {%- endif %}
+                {%- endfor %}
+                {{- "}}" }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- else %}
+                    {{- "]" }}
+                {%- endif %}
+            {%- endfor %}
+            {{- "[/AVAILABLE_TOOLS]" }}
+            {%- endif %}
+        {%- if loop.last and system_message is defined %}
+            {{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
+        {%- else %}
+            {{- "[INST] " + message["content"] + "[/INST]" }}
+        {%- endif %}
+    {%- elif message.tool_calls is defined and message.tool_calls is not none %}
+        {{- "[TOOL_CALLS] [" }}
+        {%- for tool_call in message.tool_calls %}
+            {%- set out = tool_call.function|tojson %}
+            {{- out[:-1] }}
+            {%- if not tool_call.id is defined or tool_call.id|length != 9 %}
+                {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+            {%- endif %}
+            {{- ', "id": "' + tool_call.id + '"}' }}
+            {%- if not loop.last %}
+                {{- ", " }}
+            {%- else %}
+                {{- "]" + eos_token }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif message["role"] == "assistant" %}
+        {{- " " + message["content"]|trim + eos_token}}
+    {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
+        {%- if message.content is defined and message.content.content is defined %}
+            {%- set content = message.content.content %}
+        {%- else %}
+            {%- set content = message.content %}
+        {%- endif %}
+        {{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
+        {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
+            {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+        {%- endif %}
+        {{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
+    {%- else %}
+        {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
+    {%- endif %}
+{%- endfor %}

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "is_local": false,
+  "legacy": false,
+  "model_max_length": 32768,
+  "pad_token": "[control_768]",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}